JP2018189564A - Image inspection device and image inspection method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the accuracy of image inspection by reducing the influence of ambient light in an image inspection apparatus provided with a plurality of light sources having different lighting colors. An image inspection device acquires a plurality of spectroscopic images of an object corresponding to each lighting color while irradiating the object with illumination light having a plurality of lighting colors different from each other. The image inspection device stops the irradiation of the illumination light of a plurality of lighting colors, and acquires the disturbance light image of the object to which only the disturbance light is irradiated. The image inspection device subtracts the ambient light image from each of the plurality of spectroscopic images. [Selection diagram] Fig. 9

Description

  The present invention relates to an image inspection apparatus and an image inspection method using multispectral imaging.

  An image inspection apparatus that inspects an image obtained by imaging a workpiece in order to determine whether or not a product (work) is produced as designed is very useful. In such image inspection, the shape, dimensions, color, etc. of the workpiece are inspected. According to Patent Document 1, a color inspection apparatus that captures color information by imaging an inspection object such as a printed matter and performs color inspection with high accuracy has been proposed.

JP 09-126890 A

  The image inspection apparatus illuminates the workpiece with an appropriately adjusted illumination device to acquire an image of the workpiece, and determines whether the workpiece satisfies the acceptance criteria. Since the image inspection apparatus is based on the premise that the workpiece is illuminated by the illumination device, the inspection accuracy is reduced when ambient light is irradiated onto the workpiece. In particular, in multispectral imaging, illumination light with a different lighting color is individually irradiated onto the workpiece to generate multiple spectral images, so ambient light with a color different from the lighting color can be a major factor in reducing inspection accuracy. . Since the image inspection apparatus is installed in a factory that manufactures workpieces, light from a fluorescent lamp installed in the factory or sunlight incident from a window of the factory can be disturbance light. These disturbance lights may change over time. For example, there may be an installation environment where sunlight is incident in the morning but not in the afternoon. Accordingly, an object of the present invention is to improve the accuracy of image inspection by reducing the influence of disturbance light in an image inspection apparatus including a plurality of light sources having different lighting colors.

The present invention is, for example,
A plurality of light emitting elements that generate illumination light of a plurality of lighting colors different from each other, and an illumination unit that irradiates an object with illumination light of each lighting color;
An imaging unit that receives reflected light from the object and generates a spectral image of the object;
A control unit that controls the illumination unit and the imaging unit;
A generating unit that generates a test image by combining a plurality of spectral images acquired by the imaging unit;
An inspection unit that inspects the object using the inspection image;
The control unit turns off the plurality of light emitting elements, causes the imaging unit to receive reflected light from the object due to disturbance light, and obtains a disturbance light image of the object,
The generator is
A subtractor that subtracts the disturbance light image from each of the plurality of spectral images;
There is provided an image inspection apparatus comprising: a combining unit that combines the plurality of spectral images obtained by subtracting the disturbance light image to generate the inspection image.

  According to the present invention, since the influence of disturbance light is reduced in an image inspection apparatus provided with a plurality of light sources having different lighting colors, the accuracy of image inspection is improved.

Diagram showing an image inspection device The figure which shows a lighting device The figure which shows the components which comprise an illuminating device The figure which shows the electrical structure of an illuminating device The figure which shows the function of the image processing device Diagram showing the principle of color tone conversion in multispectral imaging Diagram showing the foreground / background image creation process The figure which shows color extraction UI The figure which shows the color extraction process including the reduction process of disturbance light Flow chart showing image inspection Diagram explaining the problem of workpiece movement Diagram explaining the principle of movement correction in multispectral imaging The figure which shows the user interface regarding movement correction The figure which shows the user interface regarding movement correction The figure which shows the user interface regarding movement correction Flow chart showing image inspection Diagram showing lighting pattern

  An embodiment of the present invention is shown below. The individual embodiments described below will help to understand various concepts, such as the superordinate concept, intermediate concept and subordinate concept of the present invention. Further, the technical scope of the present invention is determined by the scope of the claims, and is not limited by the following individual embodiments.

  FIG. 1 is a diagram illustrating an example of an appearance inspection system (image inspection apparatus). A line 1 is a conveyance belt that conveys a workpiece 2 that is an inspection object. The illuminating device 3 is an example of an illuminating unit that has a plurality of light emitting elements that generate inspection light (illumination light) having different wavelengths and irradiates an object with illumination light of each wavelength individually. In order to irradiate the work 2 with illumination light from a plurality of directions, a plurality of light emitting elements having the same wavelength may be provided. The camera 4 is an example of an imaging unit that receives reflected light from an inspection object illuminated by illumination light and generates a luminance image (spectral image). The image processing device 5 illuminates the inspection object to be subjected to the image inspection by sequentially turning on the light emitting elements with the illumination intensity set for each wavelength, and uses the plurality of inspection images acquired by the imaging unit. An inspection apparatus having an inspection unit that performs image inspection. The display unit 7 is a display device that displays a user interface for setting control parameters related to inspection, an image for inspection, and the like. The input unit 6 is a console, a pointing device, a keyboard, or the like, and is used for setting control parameters.

<Configuration of lighting device>
FIG. 2A is a perspective view of the lighting device 3. FIG. 2B is a top view of the lighting device 3. FIG. 2C is a bottom view of the lighting device 3. FIG. 2D is a side view of the lighting device 3. The housing of the lighting device 3 has an upper case 21 and a lower case 22. A light diffusion member 23 for diffusing light output from each of a plurality of light sources (light emitting elements such as LEDs) is disposed below the lower case 22. As shown in FIGS. 2A and 2C, the light diffusion member 23 has an annular shape as in the upper case 21 and the lower case 22. As shown in FIGS. 2B and 2D, a connector 24 is provided on the upper surface of the upper case 21. Connected to the connector 24 is a cable for communication between the illumination control board stored in the illumination device 3 and the image processing device 5. Some functions mounted on the lighting control board may be provided outside the lighting device 3 as a lighting controller. That is, an illumination controller may be interposed between the illumination device 3 and the image processing device 5.

  FIG. 3A is a side view showing the control board 31 and the LED board 32 stored in the lighting device 3. The control board 31 is an example of a second board on which a lighting control unit is mounted. The LED substrate 32 is an example of a first substrate on which a plurality of light sources are mounted. FIG. 3B is a top view of the LED substrate 32. FIG. 3C is an enlarged cross-sectional view of the vicinity of the LED 33 in the illumination device 3. FIG. 3D is a bottom view of the LED substrate 32. FIG. 3E is an enlarged side view of the vicinity of the LED 33 in the LED substrate 32.

  An illumination control board and a connector 24 are disposed on the control board 31. Light emitting elements such as LEDs constituting the light source group are mounted on the LED substrate 32. As shown in FIG. 3B, in this embodiment, four LED substrates 32 are provided to irradiate illumination light from four directions. By enabling illumination light from four directions, an image for photometric stereo can be acquired. That is, the illumination device 3 may be used not only for multispectral imaging but also for photometric stereo. It is assumed that four LEDs 33 are arranged on one LED substrate 32. Thereby, the light source group is composed of 16 light emitting elements. However, a larger number of light emitting elements may be provided. For example, eight LEDs 33 are arranged on one LED substrate 32, and the wavelengths of light emitted by the eight LEDs 33 may be different from each other. As shown in FIGS. 3C, 3 </ b> D, and 3 </ b> E, a light shielding member 35 is disposed between two adjacent LEDs 33 among the plurality of LEDs 33. When a large number of LEDs 33 are arranged closely, illumination light emitted from two adjacent LEDs 33 may pass through the same region of the light diffusion member 23 in some cases. In this case, depending on the lighting pattern, one LED 33 is not lit and the other LED 33 is lit, and the other LED 33 is not lit and one LED 33 is lit. The surface is irradiated with illumination light with the same amount of light from the same illumination direction. This makes it difficult to generate an inspection image with high accuracy. Therefore, the light shielding member 35 is disposed between the two adjacent LEDs 33 to balance the uniformity of the light amount and the independence of the light source for the two adjacent LEDs 33. As shown in FIG. 3C, the light emission direction A1 of the LED 33 does not coincide with the main illumination direction A2. Therefore, by arranging the reflecting mirror 34, the light emitted from the LED 33 is deflected in the direction of the light diffusion member 23. Thereby, the light emitted from the LED 33 can be efficiently irradiated onto the workpiece 2. In this example, the emission direction A1 and the reflection direction of the reflecting mirror 34 are substantially perpendicular to each other, but this is because the cross-sectional shape of the light diffusing member 23 forms an arc (FIG. 3C), and the angle ( This is because the central angle is about 90 degrees. By increasing the central angle in this way, it becomes easy to irradiate the surface of the work 2 with substantially uniform parallel light even if the illumination device 3 is moved away from or closer to the work 2.

<Circuit configuration of lighting device>
FIG. 4 shows an example of the circuit configuration of the illumination device 3. In this example, one group of four LED groups constituting the light source group is shown. The four LEDs 33a to 33d are connected in series. The variable power supply 41 having a variable voltage generates and outputs a voltage having a voltage value (for example, 2V to 20V) designated by the illumination control board 40. The variable constant current source 42 adjusts the current flowing through the LED group so that the current value (for example, 0A to 1A) specified by the illumination control board 40 is obtained. By adopting such a current control method, it becomes easy to realize dimming with high linearity. The variable constant current source 42 detects the value of the voltage applied to the variable constant current source 42 and feeds it back to the illumination control board 40 to protect the variable constant current source 42 from overvoltage. A switch 43a to a switch 43d are connected in parallel to each of the LEDs 33a to 33d. The lighting control unit 45 of the illumination control board 40 can individually switch between lighting and non-lighting of the LEDs 33a to 33d by individually opening and closing these switches 43a to 43d. In this way, by connecting the switches 43a to 43d in parallel to the LEDs 33a to 33d, individual lighting such as lighting any one of the LEDs 33a to 33d or lighting all of them can be performed. This is useful for realizing various lighting patterns. The lighting control unit 45 executes lighting control in units of one LED group by switching on / off of a main switch 43e inserted between the variable constant current source 42 and the ground. The communication unit 44 receives a control signal for instructing a lighting pattern and a trigger signal for instructing start of lighting from the illumination control unit of the image processing device 5, and passes them to the lighting control unit 45. The lighting control unit 45 reads the lighting pattern data 47 corresponding to the control signal from the storage unit 46, and controls the switches 43 a to 43 d according to the lighting pattern data 47.

<Functional block>
FIG. 5 is a block diagram of the inspection apparatus. In this example, the illumination device 3, the camera 4, and the image processing device 5 are each housed in separate housings, but this is only an example and may be appropriately integrated. The illuminating device 3 is an illuminating device that realizes multispectral imaging. However, the illuminating device 3 may be used as an illuminating unit that illuminates an inspection object according to a photometric stereo method. The illumination apparatus 3 includes a light source group 501 and an illumination control board 40 that controls the light source group 501. As already shown in FIG. 3, one segment may be constituted by a plurality of light emitting elements, and the light source group 501 may be constituted by a plurality of segments. The number of segments is generally four, but may be three or more. This is because if the work 2 can be irradiated with illumination light from three or more illumination directions, an inspection image can be generated by the photometric stereo method. Each segment is provided with a plurality of light emitting elements (LEDs 33) that output illumination light having different wavelengths. The plurality of light emitting elements may include white LEDs. The white LED is not used for multispectral imaging, and is used to create another inspection image or an image for correcting the movement of the work 2. As shown in FIGS. 1 and 3, the outer shape of the illumination device 3 may be ring-shaped. Moreover, the illuminating device 3 may be comprised by the some illumination unit each isolate | separated. The illumination control board 40 controls the lighting timing and illumination pattern (lighting pattern) of the light source group 501 according to the control command received from the image processing device 5. In order to obtain a spectral image by multispectral imaging, the illumination light with an alternatively selected wavelength is irradiated onto the work 2, but when a technique other than multispectral imaging is adopted, illumination light with a plurality of wavelengths is emitted. It may be irradiated at the same time. Although the illumination control board 40 will be described as being built in the lighting device 3, it may be built in the camera 4, or may be built in the image processing device 5, or a housing independent from these. It may be accommodated in.

  The camera 4 is an example of an imaging unit that receives reflected light from an inspection object illuminated by the illumination device 3 and generates a luminance image, and executes an imaging process in accordance with a control command from the image processing device 5. The camera 4 may create a luminance image of the work 2 and transfer it to the image processing device 5, or transfer a luminance signal obtained from the image sensor to the image processing device 5, and the image processing device 5 generates a luminance image. May be. Since the luminance signal is a signal from which the luminance image is based, the luminance signal is also a luminance image in a broad sense. The camera 4 functions as an imaging unit that receives the reflected light from the object for each illumination light of each wavelength output from the illumination device 3 and generates an image of the object.

  The image processing device 5 is a kind of computer, and a processor 510 such as a CPU or ASIC, a storage device 520 such as a RAM, a ROM, or a portable storage medium, an image processing unit 530 such as an ASIC, and a communication such as a network interface. Part 550. The processor 510 is in charge of setting an inspection tool, adjusting control parameters, generating an inspection image, and the like. In particular, the MSI processing unit 511 creates a gray image of the work 2 from a plurality of luminance images (spectral images) acquired by the camera 4 according to multispectral imaging (MSI), or creates an inspection image from the gray image. To do. The subtracting unit 561 subtracts the disturbance light image from each of the plurality of spectral images. The disturbance light image is an image obtained by turning off all of the plurality of light emitting elements included in the illumination device 3 and imaging the workpiece 2 irradiated with only disturbance light. The synthesizing unit 562 generates a test image by synthesizing a plurality of spectral images obtained by subtracting the disturbance light image. The color extraction unit 563 extracts a registered color based on the color distribution of the pixels included in the extraction region from each of the plurality of spectral images. The synthesizing unit 562 may include a conversion unit 564 that converts a plurality of spectral images into gray images (color gray images) using registered colors. The illumination control unit 512 controls a lighting pattern, illumination switching timing, and the like by transmitting a control command to the illumination control board 40. The imaging control unit 513 controls the camera 4.

  The UI management unit 514 displays a user interface (UI) for setting an inspection tool, a UI for setting parameters necessary for generating an inspection image, and the like on the display unit 7 and inputs from the input unit 6. The inspection tool and parameters are set according to the information provided. The inspection tool includes a tool for measuring the length of a specific feature (eg pin) of the workpiece 2, a tool for measuring the area of the feature, and a distance from one feature to another feature (eg pin spacing). A tool for measuring, a tool for measuring the number of specific features, a tool for inspecting whether a specific feature is flawed, or the like may be included. In particular, the UI management unit 514 displays a UI for setting control parameters related to multispectral imaging and movement correction on the display unit 7. The image selection unit 515 reads the image data of the image selected by the user through the UI from the storage device 520 and displays it in the image display area in the UI. The area designation unit 516 accepts designation of the inspection tool inspection area (measurement area), pattern area PW, search area SW, tracking area TW, and the like from the user for the displayed image. The pattern area PW and the tracking area TW are areas for registering feature patterns for movement correction. The search area SW is an area where feature patterns are searched. Further, the area designating unit 516 receives selection of the shape of these designated areas (eg, rectangle, circle, ellipse, arbitrary shape) and reflects the shape of the frame line indicating the designated area on the UI. The lighting color setting unit 517 sets the wavelength (lighting color) of illumination light for movement correction in accordance with a user instruction. The UI management unit 514 stores these control parameters set by the user in the setting information 523.

  The image processing unit 530 includes an inspection unit 531 that performs various measurements by applying an inspection tool to an inspection image acquired by multispectral imaging. The search unit 532 searches a feature set before the image inspection or a feature dynamically set during the image inspection in the search area SW arranged in the inspection image, and obtains the position of the found feature. The movement correction unit 533 corrects the coordinate system of the plurality of spectral images for multispectral imaging or the coordinates (position) of the workpiece 2 based on the amount of change in the position of the feature found from the movement correction image. This correction work may be divided into a step of creating a conversion formula (correction formula) for correction and a step of converting coordinates using the conversion formula. Either of these two steps may be executed by the movement correction unit 533, the former may be executed by the movement correction unit 533, the latter may be executed by the MSI processing unit 511, or both may be executed by the MSI processing unit. 511 may be executed. Note that the function of the image processing unit 530 may be implemented in the processor 510. Alternatively, the function of the processor 510 may be implemented in the image processing unit 530. Further, the processor 510 and the processor 510 may cooperate to realize a single function or a plurality of functions. For example, the image processing unit 530 may be in charge of some calculations related to movement correction, and the processor 510 may be in charge of the remaining calculations.

  The determination unit 540 functions as a determination unit that determines the quality of the workpiece 2 using the inspection image. For example, the determination unit 540 receives the result of the inspection performed using the inspection image in the image processing unit 530 and determines whether the inspection result satisfies a non-defective product condition (tolerance or the like).

  The storage device 520 stores spectral image data 521 that is spectral image data acquired by the camera 4, gray image data 522 that is gray image data generated by the MSI processing unit 511, and setting information that holds various control parameters. 523 is stored. The storage device 520 also stores various setting data, a program code for generating a user interface, and the like. The storage device 520 may also store and hold an inspection image generated from a gray image.

<Multispectral imaging>
In multispectral imaging, illumination light having different lighting colors (wavelengths) is irradiated onto the workpiece 2 one by one in order, and an image for each wavelength is acquired. For example, when illumination light with eight types of wavelengths is irradiated, eight images (spectral images) are acquired. The eight types of wavelengths are eight types of narrow band wavelengths from the ultraviolet wavelength to the near infrared wavelength. The narrow band wavelength means a wavelength narrower than the width of the wavelength of light emitted from the white LED (broadband wavelength). For example, the wavelength of the light emitted by the blue LED is much narrower than the wavelength of the light emitted by the white LED, so the wavelength of the light emitted by the blue LED is a narrow band wavelength. It should be noted that some image inspections do not require all eight spectral images. In this case, only the illumination light having a necessary wavelength is irradiated onto the workpiece 2. In general, eight images are rarely used for image inspection as they are, and one gray image is created from the eight images (color shading conversion), and this gray image (color shading image) is used for image inspection. The The color shading conversion is sometimes called color gray conversion. For example, a binarization process, an edge detection process, or a blob process is performed on a color grayscale image, and the position and dimensions (length, Area) and color are checked to see if they are within tolerance.

  An example of color shading conversion will be described with reference to FIG. In order to create a gray image of the work 2 that is the inspection object, a registered color of a good product (model) is required. This is because a gray image is created by converting eight spectral images based on color information of registered colors.

  First, in the setting mode, color information of registered colors is extracted from image regions (designated regions) designated by the user in eight spectral images acquired from non-defective products. For example, when the non-defective product is an instant food (eg, ramen) and the number of certain ingredients (eg, shrimp) is counted by image inspection, the user displays an image of the non-defective product, and the relevant material is displayed in the non-defective image. Is specified, and color information of the registered color is extracted from the pixels included in the specified area. The color information of the registered color includes an average pixel matrix, a variance covariance matrix, and the number of pixels included in the designated area.

  Next, in the inspection mode, eight spectral images are acquired for the workpiece 2 that is the inspection object. The distance d (x) with respect to the registered color is obtained for all the pixels included in each spectral image (x is an 8-dimensional vector whose elements are the pixel values of the eight spectral images). Further, the product obtained by multiplying the distance d (x) by a predetermined gain g is obtained, and the difference G obtained by subtracting the product from the maximum gradation Gmax that each pixel can take is the gray gradation of the target pixel x. It becomes.

  If there are a plurality of registered colors, a plurality of gray images are created with each registered color as a reference.

<Foreground background image>
Color shading conversion is also used to create a foreground / background image in which the background color and the foreground color are separated. For example, suppose that the foreground color is shrimp and shellfish, and the background color is dry noodles or dry leek. In this case, a plurality of foreground colors and a plurality of background colors will be registered. Further, in order to count the number of shrimps and shellfish by image inspection, it is necessary that the shrimps and shellfish are appropriately separated from the background.

  FIG. 7 shows a process of creating a foreground / background image FBimg which is a kind of inspection image. The MSI processing unit 511 functioning as an inspection image generation unit calculates the distance (Mahalanobis distance) between each of the foreground colors FC1 to FC9 belonging to the foreground group FG and the color of each pixel of the color image of the work 2, and foreground colors FC1 to FC9. Nine distance images corresponding to are created. The conversion unit 564 described above may include a distance image generation unit. The distance image generation unit calculates the distance between the foreground color FC1 and the color of each pixel of the color image of the work 2, and creates one distance image corresponding to the foreground color FC1. Similarly, the distance image generation unit calculates the distance between the foreground color FC2 and the color of each pixel of the color image of the work 2, and creates one distance image corresponding to the foreground color FC2. The distance image generation unit also creates distance images for the remaining foreground colors FC3 to FC9. Further, the distance image generation unit calculates the distance (Mahalanobis distance) between each of the background colors BC1 to BC3 belonging to the background group BG and the color of each pixel of the color image of the work 2, and the three corresponding to the background colors BC1 to BC3. Create a range image. As described above, the value of each pixel constituting the distance image is a distance. The distance to the registered colors such as the foreground color and the background color is a distance with reference to the representative color (distribution center coordinates) in the registered color distribution.

  The conversion unit 564 may include a foreground image generation unit, a background image generation unit, and a foreground / background image generation unit. The foreground image generation unit compares the nine distance images corresponding to the foreground colors FC1 to FC9, finds the minimum distance among the nine distances for each coordinate, and adopts the minimum distance as the representative distance of each coordinate. A foreground distance image Fimg consisting of the minimum distance is created. For example, the distance of the target coordinate (xi, yi) is read from nine distance images, and the pixel of the target coordinate (xi, yi) in the foreground distance image Fimg is the smallest distance among the nine distances read out. The value of is adopted. Similarly, the background image generation unit compares the three distance images corresponding to the background colors BC1 to BC3, finds the minimum distance among the three distances for each coordinate, and determines the minimum distance as the representative distance of each coordinate. Is used to create a background distance image Bimg consisting of the minimum distance.

The foreground / background image generator generates a foreground / background image FBimg by performing a difference calculation between the background distance image Fimg and the background distance image Bimg. For example, the pixel value G (xi, yi) at the target coordinate (xi, yi) in the foreground / background image FBimg is calculated from the following equation.
G (xi, yi) = g (db (xi, yi) −df (xi, yi)) + Gmid (1)
Here, g is a gain adjusted by the user in the adjustment tab 720. db (xi, yi) is the value of the pixel at the target coordinate (xi, yi) in the background distance image Bimg. df (xi, yi) is the value of the pixel at the target coordinate (xi, yi) in the foreground distance image Fimg. Gmid is an intermediate gradation. For example, if the maximum gradation is 255, Gmid is 128.

<Color extraction>
Color extraction refers to extracting and registering a selectable color from the image of the work 2 as the foreground color or the background color. The color extracted by this operation is the registered color.

  FIG. 8 shows a color extraction UI 800 displayed on the display unit 7 by the UI management unit 514 in order to assist color extraction by the user. The image display area 801 is an area for displaying the image selected by the pull-down menu 811. The pull-down menu 811 is a UI for designating a color image stored in the storage device 520 or a color image acquired by the camera 4. An image that is not registered in the pull-down menu 811 can be specified by selecting “Reference” in the pull-down menu 811. The image selection unit 515 displays the image selected by the pull-down menu 811 in the image display area 801. A pull-down menu 812 is a UI for selecting the shape of the extraction area 802 from which registered colors are extracted. Examples of the shape options include a rectangle, a circle, and an ellipse. The extraction button 813 is a button for instructing execution of color extraction. When the extraction button 813 is pressed, the UI management unit 514 changes the pointer icon (arrow shape) to the dropper 803. The area designation unit 516 accepts the area designated by the dropper 803 as the extraction area 802. The color extraction unit 563 creates color information of registered colors based on the colors of the pixels in the extraction area 802 and stores them in the storage device 520. Note that an extraction button 813 for extracting the foreground color and an extraction button 813 for extracting the background color may be individually provided. The confirmation button 815 is a button for instructing confirmation of the color extraction result. A cancel button 814 is a button for discarding the color extraction result.

<Reduction of disturbance light>
As described above, the plurality of spectral images are acquired by the monochrome camera 4 by irradiating the work 2 with illumination light of a predetermined lighting color. Further, the lighting color and the spectral image have a one-to-one correspondence. Therefore, if light (disturbance light) from a light source different from the illumination device 3 is mixed with illumination light of a lighting color that is determined to be used to acquire a certain spectral image, the spectral image and The relationship with the lighting color will collapse. Therefore, in this embodiment, when the spectral image is acquired, the disturbance light image is also acquired, and the disturbance light image is subtracted from the spectral image, thereby reducing the influence of the disturbance light on the spectral image.

  FIG. 9 is a flowchart showing a color extraction method including disturbance light reduction processing. Here, the registered color is extracted based on the spectral image acquired from the non-defective product of the work 2. The MSI processing unit 511 starts acquiring a disturbance light image and a spectral image based on a trigger signal input from an external device such as a PLC (programmable controller).

  In step S901, the MSI processing unit 511 acquires a disturbance light image. The lighting control unit 512 turns off the lighting device 3. When the lighting device 3 is already turned off, the turn-off process is omitted. Thereby, only the disturbance light is irradiated to the workpiece | work 2 from the light source different from the illuminating device 3. FIG. The MSI processing unit 511 instructs the imaging control unit 513 to capture a disturbance light image. The imaging control unit 513 instructs the camera 4 to perform imaging. Thereby, the image acquired by the camera 4 is stored in the storage device 520 as a disturbance light image.

  In step S <b> 902, the MSI processing unit 511 acquires a spectral image through the illumination control unit 512 and the imaging control unit 513. The illumination control unit 512 controls the illumination device 3 to irradiate the work 2 with illumination light while switching the lighting color at regular intervals. The imaging control unit 513 also causes the camera 4 to acquire a spectral image at a constant interval synchronized with the lighting color switching timing. The imaging control unit 513 stores the acquired plurality of spectral images as spectral image data 521 in the storage device 520. Thereby, a spectral image corresponding to the lighting colors from UV to IR2 is acquired.

  In step S903, the subtraction unit 561 of the MSI processing unit 511 performs disturbance light reduction processing on each of the plurality of spectral images. For example, the subtraction unit 561 subtracts the disturbance light image from each of the plurality of spectral images. In the spectral image (UV image) corresponding to the UV lighting color, each pixel has a luminance value of reflected light generated when the illumination light of the UV lighting color is reflected by the work 2. However, this luminance value is a luminance value to which ambient light is added. In the disturbance light image, each pixel has a luminance value of reflected light generated by the disturbance light being reflected by the work 2. Therefore, the net UV luminance value can be obtained by subtracting the disturbance light luminance value from the UV luminance value to which the disturbance light is added. The reduction process is similarly executed for other lighting colors.

  In step S904, the color extraction unit 563 of the MSI processing unit 511 displays a good color image based on the spectral image with reduced disturbance light on the display unit 7, and extracts a registered color from the extraction region 802 designated by the user.

  Since the influence of disturbance light is reduced from the plurality of spectral images before the registered color is extracted in this way, the accuracy of the registered color is improved.

  FIG. 10 is a flowchart showing an image inspection method including disturbance light reduction processing. In FIG. 10, S901 to S903 are the same processes as S901 to S903 in FIG. However, the subject is a work 2 that is an inspection object. When the processing from S901 to S903 is completed for the workpiece 2 to be inspected, the MSI processing unit 511 proceeds to S1001.

  In step S1001, the conversion unit 564 of the MSI processing unit 511 creates an inspection image based on the registered color and the color image of the inspection object. The color image of the inspection object is a plurality of spectral images with reduced disturbance light. The inspection image may be different for each inspection tool. For example, the conversion unit 564 may convert the color image into a gray image (foreground image) according to the Mahalanobis distance between the registered color (foreground color) of the foreground region in the color space and the color of each pixel of the color image. The conversion unit 564 may convert the color image into a gray image (background image) according to the Mahalanobis distance between the registered color (background color) of the background region in the color space and the color of each pixel of the color image. These images may be further subjected to further image processing such as binarization.

  In step S1002, the inspection unit 531 performs an image inspection by applying an inspection tool to the inspection image. As an example, it is assumed that the inspection object is a metal terminal provided on a resin plate, and the area of the metal terminal and the surrounding area are obtained by an area inspection tool provided in the inspection unit 531. The foreground color is the representative color of the metal terminal, and the background color is the representative color of the resin plate. The inspection unit 531 converts the color of the resin plate to white by binarizing the foreground image, converts the color of the metal terminal to black, and calculates the area of the metal terminal by counting the number of black pixels. To do. Similarly, the inspection unit 531 converts the color of the resin plate to black by binarizing the background image, converts the color of the metal terminal to white, and counts the number of black pixels to count the metal terminals. Calculate the area of the surrounding resin plate. The determination unit 540 determines pass / fail by comparing the area of the metal terminal with a threshold value such as tolerance. The determination unit 540 determines pass / fail by comparing the area around the metal terminal with a threshold such as tolerance.

  Thus, since the influence of disturbance light is reduced from the plurality of spectral images acquired from the inspection object, the accuracy of the inspection image is improved. This improves the accuracy of the image inspection.

<Movement correction>
In multispectral imaging, a large number of lighting colors are irradiated onto the workpiece 2 one by one in order, and a large number of spectral images are generated. For example, as shown in FIG. 11, illumination light of eight kinds of lighting colors from UV to IR2 is sequentially irradiated onto the work 2 to obtain eight spectral images, and the eight spectral images are synthesized. A single gray image is created. When the workpiece 2 is conveyed along the line 1, the position of the workpiece 2 in the first UV image is shifted from the position of the workpiece 2 in the eighth IR2 image. As the number of lighting colors increases and the conveyance speed of the line 1 increases, the amount of displacement of the position of the workpiece 2 increases. If the gray image G1 is generated while ignoring this shift, the correct gray image cannot be obtained, and the accuracy of the image inspection is lowered. Therefore, if a gray image is created after performing movement correction on the workpiece 2, a correct gray image is created.

  A disturbance light image must also be acquired in the process of acquiring a series of spectral images. That is, since the workpiece 2 moves, it is necessary to correct the position of the workpiece 2 even in the disturbance light image.

  The movement correction may be omitted when the workpiece 2 is stationary or when the conveyance speed of the workpiece 2 in the line 1 is extremely low.

  FIG. 12 shows the concept of movement correction involving acquisition of the disturbance light image AB. In this example, movement correction images (corrected images MC1 and MC2) are acquired before and after acquiring eight types of spectral images for multispectral imaging. Moreover, the disturbance light image AB is acquired between the timing which acquires correction | amendment image MC1, and the timing which acquires correction | amendment image MC2. In FIG. 12, the disturbance light image AB is acquired between the corrected image MC1 and the UV image.

  The conveyance speed of the workpiece 2 in the line 1 is constant. The interval at which the camera 4 acquires an image is also constant. Therefore, the position of the workpiece 2 in each image is different, and these positions draw a linear locus. Accordingly, if the correspondence relationship between the coordinates of the pixels constituting the work 2 in each spectral image (shift amount in the x direction and shift amount in the y direction) is obtained, the position of the work 2 in each spectral image is overlapped to obtain a gray image. G2 can be created. Here, it is assumed that disturbance light is reduced by the disturbance light image AB subjected to movement correction in each spectral image.

  In the movement correction, the feature f of the workpiece 2 is detected by the pattern search by the search unit 532 in the corrected images MC1 and MC2, and the positions p1 and p2 of the feature f are obtained, respectively. The feature f may be a shape or edge (interval between two characteristic edges) that can be detected by pattern search. If a linear equation indicating changes in the positions p1 and p2 is obtained, the position of the workpiece 2 in each spectral image can be corrected. That is, a coordinate conversion formula indicating the correspondence of the coordinate system in each spectral image is determined.

  When the workpiece 2 moves linearly, movement correction can be performed using two correction images. When the workpiece 2 moves nonlinearly, three or more corrected images are required. Here, in order to simplify the description, a case where two corrected images are used will be mainly described.

User Interface FIGS. 13, 14 and 15 show user interfaces for setting parameters relating to movement correction. FIG. 13 shows a setting UI for a pattern search mode (pre-registration mode) in which a registered pattern is registered in the setting mode. In FIG. 13, the setting UI 900 is displayed on the display unit 7 by the UI management unit 514 before executing the image inspection. FIG. 14 shows a tracking mode setting UI for dynamically registering a registration pattern in the operation mode. As shown in FIG. 14, in the tracking mode, a feature pattern serving as a reference for movement correction is registered in an operation mode in which image inspection is executed. The UI management unit 514 displays the feature pattern registration UI in the setting UI 900 on the display unit 7 in the operation mode. The user arranges (sets) a tracking area TW for extracting a registered pattern in the operation mode. Thereby, the features in the tracking area TW are extracted. Items common to FIGS. 13 and 14 are given the same reference numerals.

  The image selection button 902 is a UI for selecting an image displayed in the image display area 901, and passes a selection result to the image selection unit 515. 13 and 14, C indicates a color image created by combining a plurality of spectral images. AL indicates all eight types of spectral images. When the AL is operated by the pointer 906, as shown in FIG. 15, the image selection unit 515 displays all the spectral images side by side in the image display area 901. A plurality of corrected images may be selected by clicking with the pointer 906 from the plurality of spectral images displayed side by side in this way. The UI management unit 514 and the setting UI 900 may function as a reception unit that receives selection of the first correction image and the second correction image.

  13, 14, and 15, UV indicates a spectral image obtained by illumination light having an ultraviolet wavelength. B shows a spectral image acquired by the blue wavelength illumination light. G indicates a spectral image acquired by illumination light having a green wavelength. AM indicates a spectral image acquired by illumination light having an amber wavelength. OR indicates a spectral image obtained by illumination light having an orange wavelength. R indicates a spectral image acquired by the illumination light having a red wavelength. IR1 and IR2 represent spectral images acquired by illumination light having infrared wavelengths. However, the wavelength of IR1 is shorter than the wavelength of IR2. MC1 is a first corrected image. MC2 is a second corrected image. AB indicates a disturbance light image. 13 and 14, the image of the work 2 is displayed in the image display area 901.

  An image name display field 911 is a text box for displaying the name of the image displayed in the image display area 901. The image selection unit 515 inputs the name of the image in the text box. In FIG. 13, an edit button 912 is a button for editing the size and position of the pattern area PW, which is an area including a feature to be subjected to pattern search. The edit button 913 is a button for editing the size and position of the range (search area SW) for searching the feature f for movement correction in the first correction image MC1. In FIG. 14, an edit button 914 is a button for editing the size and position of the range (tracking area TW) for dynamically registering the movement correction feature f in the second correction image MC2. Note that the pattern area PW and the tracking area TW are areas for extracting a feature f for movement correction, and have a common function. As described above, the feature f used for detecting the position of the workpiece 2 may be pre-registered in the setting mode, or may be dynamically registered in the operation mode. Registration of the search area SW and the pattern area PW is performed in the setting mode in principle. When it is detected that the edit button has been pressed by the pointer 906, the area designating unit 516 sets each area according to the movement of the pointer 906. In addition, the image processing unit 530 extracts features in the pattern area PW or the tracking area TW and writes them in the setting information 523. The extracted feature may be an image itself, a contour, or a plurality of edges.

  The lighting color selection unit 915 is a pull-down menu for selecting the wavelength (lighting color) of the illumination light used for acquiring the corrected image. The lighting color setting unit 517 writes the identification information of the lighting color selected from the pull-down menu of the lighting color selection unit 915 in the setting information 523 as identification information for designating the lighting color for illumination light. When the lighting device 3 is equipped with a white LED, the lighting color selection unit 915 can select W indicating the white LED as the lighting color of the illumination light. In addition, AL, which means that all the light emitting elements of the lighting color are turned on, may be selected by the lighting color selection unit 915. When W or AL is selected, the feature search for movement correction is often stabilized. When any narrow band wavelength from UV to IR2 is selected, the correction image and the spectral image for creating the inspection image may be used together. For example, when UV is selected, the UV image is used not only as a correction image but also as an element image for creating an inspection image. As a result, the number of images to be acquired is reduced, and the work time for movement correction is shortened.

  An edit button 916 is a button for editing detailed settings. The detailed setting may include selecting one movement correction method from among a plurality of movement correction methods, setting a search angle in a pattern search, and the like. The confirm button 917 is a button for confirming settings relating to movement correction. A cancel button 918 is a button for canceling the current setting and returning to the previous setting or default setting.

Flowchart FIG. 16 is a flowchart showing an image inspection (operation mode) executed by the processor 510. Here, the pattern search mode is applied as the search mode for movement correction. Therefore, it is assumed that the control parameter relating to movement correction has already been determined in the setting mode. Note that the order of S1601 to S1604 can be freely changed as long as movement correction can be realized. However, S1604 is executed after S1601. The MSI processing unit 511 starts the following processing based on a trigger signal input from an external device such as a PLC (programmable controller).

  In step S1601, the processor 510 acquires a first corrected image. The processor 510 determines the lighting color of the illumination light of the first corrected image according to the setting information 523 and sets it in the illumination control unit 512. The illumination control unit 512 instructs the illumination control board 40 to turn on the light emitting element of the designated lighting color. The illumination control board 40 lights the light emitting element of the designated lighting color. The processor 510 sets an imaging condition (such as an exposure condition) according to the setting information 523 in the imaging control unit 513, and acquires an image of the work 2. The imaging control unit 513 controls the camera 4 according to the designated imaging condition, acquires a first corrected image that is an image of the work 2, and writes it in the storage device 520.

  In S1602, the MSI processing unit 511 acquires a disturbance light image. The MSI processing unit 511 turns off the lighting device 3 through the lighting control unit 512. Thereby, only the disturbance light is irradiated to the workpiece 2. The MSI processing unit 511 instructs the imaging control unit 513 to capture a disturbance light image. The imaging control unit 513 instructs the camera 4 to perform imaging. Thereby, the image acquired by the camera 4 is stored in the storage device 520 as a disturbance light image.

  In S1603, the MSI processing unit 511 acquires a spectral image for multispectral imaging. The MSI processing unit 511 sets the lighting color of the illumination light in the illumination control unit 512 according to the setting information 523. The illumination control unit 512 instructs the illumination control board 40 to turn on the light emitting element of the designated lighting color. The illumination control board 40 lights the light emitting element of the designated lighting color. The processor 510 sets an imaging condition (such as an exposure condition) according to the setting information 523 in the imaging control unit 513, and acquires an image of the work 2. The imaging control unit 513 controls the camera 4 according to the designated imaging condition, acquires a spectral image that is an image of the work 2, and writes the spectral image in the storage device 520. In principle, the spectral image may be acquired for all the eight types of lighting colors, or may be acquired for some of the lighting colors. The lighting color used for acquiring the spectral image depends on the setting information 523. When all the spectral images designated by the setting information 523 are acquired, the processor 510 moves to S1103.

  In step S1604, the processor 510 acquires a second corrected image. The processor 510 determines the lighting color of the illumination light of the second corrected image according to the setting information 523 and sets it in the illumination control unit 512. The illumination control unit 512 instructs the illumination control board 40 to turn on the light emitting element of the designated lighting color. The illumination control board 40 lights the light emitting element of the designated lighting color. The processor 510 sets an imaging condition (such as an exposure condition) according to the setting information 523 in the imaging control unit 513, and acquires an image of the work 2. The imaging control unit 513 controls the camera 4 according to the designated imaging condition to acquire a second corrected image that is an image of the work 2 and writes the second corrected image in the storage device 520.

  In step S1605, the processor 510 causes the image processing unit 530 to calculate a parameter for movement correction, and applies the movement correction to the disturbance light image and each spectral image using the parameter. For example, in the pattern search mode, the movement correction unit 533 causes the search unit 532 to search for a feature in the first correction image and to search for a feature in the second correction image. In the tracking mode, the movement correction unit 533 causes the search unit 532 to search for the feature registered from the first correction image in the second correction image. The movement correction unit 533 calculates the amount of change between the feature position in the first correction image and the feature position in the second correction image. The movement correction unit 533 corrects the correspondence between the coordinates of each pixel in the plurality of spectral images and the disturbance light image based on the amount of change. For example, the correspondence between the coordinates of the work 2 in the UV image and the coordinates of the work 2 in the IR1 image is obtained. By correcting the coordinates in each spectral image and the disturbance light image using the obtained correspondence (coordinate conversion formula), the position of the work 2 in each spectral image overlaps as shown in FIG. And an accurate gray image is created.

  In step S <b> 1606, the subtraction unit 561 of the MSI processing unit 511 performs disturbance light reduction processing on each of the plurality of spectral images. The plurality of spectral images and disturbance light images used here are each subjected to movement correction. The subtracting unit 561 subtracts the disturbance light image from each of the plurality of spectral images.

  In step S1607, the MSI processing unit 511 converts the plurality of spectral images to which the movement correction and the disturbance light reduction process are applied to create a gray image (inspection image). Note that an inspection image may be created by applying some image processing to the gray image.

  In step S1608, the processor 510 causes the inspection unit 531 to perform image inspection. The inspection unit 531 performs image inspection on the inspection image created by the MSI processing unit 511 using the inspection tool specified by the setting information 523. The determination unit 540 receives the result of the image inspection from the inspection unit 531 and determines whether or not the work 2 satisfies the non-defective product condition.

Lighting Pattern An example of a lighting pattern of a light emitting element for acquiring a spectral image while performing movement correction has been described with reference to FIG. 12, but this is only an example. According to the example shown in FIG. 12, the light emitting element of the lighting color designated with respect to the 1st correction image lights up. Thereafter, all the light emitting elements included in the illumination device 3 to turn off the disturbance light image are turned off. Thereafter, the light emitting elements of UV, B, G, AM, OR, R, IR1, and IR2 are turned on. Finally, the light emitting element of the lighting color designated for the second corrected image is turned on.

  FIG. 17 shows six lighting patterns. Here, it is assumed that four lighting colors R, G, B, and Y are used for multispectral imaging. Y is any lighting color other than RGB. MC is a common lighting color for movement correction. FIG. 12 implies that a plurality of spectral images are acquired at regular intervals (constant time intervals).

  Cases (1) and (2) are lighting patterns for linear correction. Case (1) indicates that the light-emitting element for movement correction is turned on before and after the multispectral imaging, and two corrected images are acquired. Note that OFF means that all the light emitting elements included in the illumination device 3 are turned off in order to acquire a disturbance light image. Case (1) is the case shown in FIG. Case (2) indicates that the light-emitting element for light correction for movement correction is lit and two correction images are acquired before acquiring the disturbance light image and the spectral image for multispectral imaging.

  Cases (3) to (5) show lighting patterns for nonlinear correction. As described above, at least three corrected images are required to perform nonlinear correction. As the number of corrected images increases, the accuracy of movement correction increases, but the imaging time increases. If the corrected images are acquired in a distributed manner as in cases (3) and (5), the accuracy of movement correction will increase.

  Case (6) is a case where a spectral image for multispectral imaging is also used as a correction image. This reduces the total number of images and shortens the imaging time. That is, more image inspections can be executed in a short time.

<Summary>
As FIG. 1 etc. show, the illuminating device 3 has several light emitting element (LED33) which generate | occur | produces the illumination light of a mutually different lighting color, and illuminates each lighting color individually with a target object (example: Work 2) It is an example of the illumination part irradiated to a non-defective product. The camera 4 is an example of an imaging unit that receives reflected light from an object for each illumination light of one or more lighting colors and generates an image of the object. Since the camera 4 is a monochrome camera, the sensitivity is better than that of a camera having a color filter. The processor 510 (the MSI processing unit 511, the illumination control unit 512, the imaging control unit 513, etc.) controls the illumination device 3 to irradiate the object with a plurality of illumination lights each having a different lighting color, and also controls the camera 4. This is an example of a control unit that generates a plurality of images with the same or different lighting colors of illumination light. The processor 510 controls the camera 4 via the imaging control unit 513 and causes the camera 4 to generate a plurality of spectral images at regular time intervals. The MSI processing unit 511 is an example of a generating unit that generates a test image by combining a plurality of spectral images acquired by the imaging unit. The MSI processing unit 511 turns off the plurality of light emitting elements and causes the imaging unit to receive reflected light from the object due to disturbance light and acquire a disturbance light image of the object. The MSI processing unit 511 includes a subtracting unit 561 that subtracts the disturbance light image from each of the plurality of spectral images, and a combining unit 562 that combines the plurality of spectral images obtained by subtracting the disturbance light image to generate an inspection image. I'm. Therefore, according to the present embodiment, the influence of disturbance light is reduced in the image inspection apparatus including a plurality of light sources having different lighting colors, so that the accuracy of the image inspection is improved.

  The display unit 7 may display a plurality of spectral images obtained by subtracting the disturbance light image. The display unit 7 may display a true color image or a false color image generated from a plurality of spectral images obtained by subtracting the disturbance light image. A false color image is a color image generated by performing color clustering on a true color image. The area designation unit 516 functions as a reception unit that receives designation of an extraction area 802 for extracting a registered color for an image displayed on the display unit 7. The color extraction unit 563 extracts a registered color based on the color distribution of pixels included in the extraction region 802 from each of the plurality of spectral images. The combining unit 562 may include a conversion unit 564 that generates an inspection image by performing color gray conversion on a plurality of spectral images according to registered colors extracted from the extraction region 802. The plurality of spectral images are subtracted from the disturbance light image. Thus, since the registered color is color information extracted from a plurality of spectral images that have been subjected to disturbance light reduction processing, the accuracy of the registered color is improved.

  The area designation unit 516 may accept designation of a foreground area from which a foreground color is extracted and designation of a background area from which a background color is extracted. The color extraction unit 563 extracts the foreground color from the foreground area and the background color from the background area as registered colors. The conversion unit 564 obtains the color distance of each pixel in the plurality of spectral images with respect to the foreground color, and generates a foreground distance image using the obtained distance for each pixel as the value of each pixel. The conversion unit 564 obtains the color distance of each pixel in the plurality of spectral images with respect to the background color, and generates a background distance image with the distance obtained for each pixel as the value of each pixel. The conversion unit 564 may generate a difference image between the foreground distance image and the background distance image as the inspection image.

  When a single trigger signal is input from the PLC or the like, the MSI processing unit 511 may control the illumination unit and the imaging unit and continuously acquire the disturbance light image and the plurality of spectral images. As a result, the disturbance light image acquisition time and the spectral image acquisition time are close to each other, so the disturbance light component in the disturbance light image and the disturbance light component in the spectral image will be substantially the same. That is, the disturbance light reduction accuracy is improved.

  As described above, disturbance light reduction processing may be combined with movement correction. The MSI processing unit 511 and the movement correction unit 533 correct the coordinates of each pixel in the plurality of spectral images and the disturbance light image, and the first correction image and the second correction image for the object moving at a constant conveyance speed. The corrected image is acquired by the imaging unit. The MSI processing unit 511 and the movement correction unit 533 calculate the coordinates of each pixel in the plurality of spectral images and the disturbance light image from the position of the correction target in the first correction image and the position of the correction target in the second correction image. You may have a coordinate correction | amendment part which correct | amends. In particular, the movement correction unit 533 is an example of a coordinate correction unit. The subtracting unit 561 subtracts the disturbance light image whose coordinates are corrected by the movement correcting unit 533 from each of the plurality of spectral images whose coordinates are corrected by the movement correcting unit 533. Thereby, even in the case where the workpiece 2 is conveyed at high speed, the influence of disturbance light is appropriately reduced.

  The camera 4 may continuously acquire the first corrected image, the second corrected image, the plurality of spectral images, and the disturbance light image at a constant time interval. This greatly facilitates calculation of movement correction. In addition, since the accuracy of the movement correction is improved, the accuracy of the disturbance light reduction process will also be improved.

  The camera 4 may acquire the first corrected image first and the second corrected image last. That is, the disturbance light image and the spectral image are acquired after the first corrected image is acquired and before the second corrected image is acquired. This means that the coordinates of the workpiece 2 in the disturbance light image and the spectral image are corrected by interpolation. In general, extrapolation and interpolation are advantageous. Therefore, by adopting the interpolation, the accuracy of the movement correction between the disturbance light image and the spectral image is improved.

  The illumination device 3 may irradiate the object with illumination light of the same lighting color when acquiring the first correction image and the second correction image. Moreover, even if the lighting color at this time is white. All of these contribute to improving the accuracy of movement correction.

  Any one of the first corrected image and the second corrected image may be used as one of the plurality of spectral images. As a result, the number of images acquired by the camera 4 is reduced, so that the processing efficiency is improved. In addition, since the time difference between the time when the first correction image is acquired and the time when the second correction image is acquired is small, the accuracy of movement correction is improved.

  By the way, the search unit 532 includes a first correction image acquired under illumination light of the same lighting color among a plurality of images, and a second correction image generated after the first correction image. The position of the feature pattern is searched for each of. The MSI processing unit 511, the movement correction unit 533, and the like correspond to the coordinates of the coordinates of each pixel in a plurality of images based on the amount of change between the position of the feature pattern in the first correction image and the position of the feature pattern in the second correction image. Correct. The inspection unit 531 performs image inspection of the target object based on a plurality of images in which the correspondence between the coordinates of each pixel is corrected by the correction unit. For example, the inspection unit 531 generates a gray image by the MSI processing unit 511 combining a plurality of spectral images, and performs image inspection using the gray image or an inspection image obtained by further image processing of the gray image. Execute. Thereby, the accuracy of the image inspection for the moving workpiece in the image inspection apparatus provided with a plurality of light sources having different lighting colors is improved.

  As described above, the lighting color of the illumination light irradiated on the object to generate the first correction image, and the lighting color of the illumination light irradiated on the object to generate the second correction image Are the same lighting color. This improves the accuracy of movement correction. In other words, the illumination conditions are matched by using the same lighting color for at least two images for movement correction, so that the feature pattern is detected with high accuracy and the accuracy of movement correction is improved. In addition, the lighting color of the illumination light irradiated to the target object in order to generate the remaining plurality of images excluding the first correction image and the second correction image among the plurality of images is different. Thus, the remaining plurality of images may be spectral images for multispectral imaging.

  The processor 510 may turn on a plurality of light emitting elements simultaneously when generating the first correction image and the second correction image. As a result, illumination light that approximates white light is realized. That is, the white light source can be omitted.

  Of course, the illumination device 3 may further include a white light emitting element (white LED or the like) that generates white illumination light. The processor 510 turns on the white light emitting element when generating the first correction image and the second correction image. Some feature patterns are clarified by white light. White light is suitable for such a feature.

The lighting color of the illumination light applied to the object for generating the first correction image and the lighting color of the illumination light applied to the object for generating the second correction image are the same. The lighting color may belong to a narrow band wavelength (narrow wavelength band). For example, both the first correction image and the second correction image may be acquired by UV illumination light. However, the lighting color of the first correction image may be different from the lighting color of the second correction image as long as the accuracy of movement correction can be sufficiently ensured. For example, the first correction image and the second correction image may be acquired by illumination light such as IR1 and IR2, respectively.
The same feature pattern is searched for in both the first corrected image and the second corrected image. Therefore, if the same or similar lighting color is used, the feature pattern search accuracy will be improved.

  The display unit 7 may display a plurality of images side by side. The UI management unit 514 may function as a reception unit that receives selection of the first correction image and the second correction image from the plurality of images displayed on the display unit 7. By displaying a plurality of images side by side in this way, the user can easily select an image suitable for the corrected image.

  The UI management unit 514 and the region designation unit 516 function as a registration unit that registers the feature of the region designated by the user with respect to the displayed image of the target object as a feature pattern in the setting mode for performing settings relating to image inspection. May be. In the operation mode in which the image inspection is executed, the search unit 532 searches for a feature pattern registered in advance by the registration unit. Thus, the feature pattern may be registered in a setting mode that is executed before the inspection mode (operation mode). The UI management unit 514 registers the feature of the region designated by the user as a feature pattern for the first corrected image generated in the setting mode. Further, the UI management unit 514 and the region specifying unit 516 may accept a search region specified by the user for the first correction image or the second correction image generated in the setting mode. The coordinates of the search area are generally coordinates that do not depend on the position of the work 2, and are coordinates based on the upper left of the image, for example. In this case, the search unit 532 searches for a feature pattern in the search area in the operation mode. In the operation mode, the search unit 532 searches for a feature pattern in the search area of the first correction image and also searches for a feature pattern in the search area of the second correction image.

  Note that the feature pattern may be dynamically registered in an operation mode in which image inspection is executed. However, the search area for searching for the feature pattern is set in the setting mode. The UI management unit 514 and the region specification unit 516 function as a region reception unit that receives specification of a tracking region in which the characteristics of the inspection target are dynamically acquired in the operation mode in which image inspection is performed. The UI management unit 514 and the region specifying unit 516 also function as a registration unit that registers features existing in the tracking region of the first correction image acquired in the operation mode as a feature pattern. At this point, the feature coordinates in the first corrected image are fixed. Further, the search unit 532 searches the feature pattern registered by the registration unit in the second corrected image acquired in the operation mode. Thereby, the coordinates of the feature in the second corrected image are determined. That is, parameters necessary for linear correction are determined. Note that the area receiving unit may receive a tracking area designated by the user for the second corrected image among the first corrected image and the second corrected image. At this time, the feature coordinates in the second corrected image are fixed. The search unit 532 searches the feature pattern registered by the registration unit in the first correction image generated in the operation mode. Thereby, the coordinates of the feature in the first corrected image are determined. That is, parameters necessary for linear correction are determined.

  The first corrected image may be an image generated first among a plurality of images. The second corrected image may be an image generated last among a plurality of images. As described above, the correction image is acquired before and after acquiring the plurality of spectral images, so that the accuracy of the movement correction is improved. This is because the estimation accuracy of the feature position by interpolation is higher than the estimation accuracy of the feature position by extrapolation.

  The search unit 532 may further search for the position of the feature pattern for the third corrected image generated after the second corrected image. The movement correction unit 533 is configured to perform a plurality of operations from the first correction image to the second correction image based on the amount of change between the position of the feature pattern in the first correction image and the position of the feature pattern in the second correction image. The correspondence between the coordinates of each pixel in the image is corrected. In addition, the movement correction unit 533 is based on the amount of change between the position of the feature pattern in the second correction image and the position of the feature pattern in the third correction image, from the second correction image to the third correction image. The correspondence between the coordinates of each pixel in a plurality of images is corrected. By using three or more corrected images in this way, movement correction can be realized with high accuracy even in the case where the position of the workpiece 2 changes nonlinearly.

  2 ... Work, 3 ... Illumination device, 4 ... Camera, 5 ... Image processing device, 511 ... MSI processing unit, 512 ... Illumination control unit, 513 ... Imaging control unit, 531 ... Inspection unit

Claims (12)

A plurality of light emitting elements that generate illumination light of a plurality of lighting colors different from each other, and an illumination unit that irradiates an object with illumination light of each lighting color;
An imaging unit that receives reflected light from the object and generates a spectral image of the object;
A control unit that controls the illumination unit and the imaging unit;
A generating unit that generates a test image by combining a plurality of spectral images acquired by the imaging unit;
An inspection unit that inspects the object using the inspection image;
The control unit turns off the plurality of light emitting elements, causes the imaging unit to receive reflected light from the object due to disturbance light, and obtains a disturbance light image of the object,
The generator is
A subtractor that subtracts the disturbance light image from each of the plurality of spectral images;
An image inspection apparatus comprising: a combining unit that combines the plurality of spectral images obtained by subtracting the disturbance light image to generate the inspection image. A display unit for displaying the plurality of spectral images obtained by subtracting the disturbance light image or a true color image or a false color image generated from the plurality of spectral images;
A reception unit that receives designation of an extraction region for extracting a registered color for an image displayed on the display unit;
An extraction unit that extracts a registered color based on a color distribution of pixels included in the extraction region from each of the plurality of spectral images;
The synthesis unit is
A conversion unit that generates the inspection image by performing color gray conversion on the plurality of spectral images obtained by subtracting the disturbance light image in accordance with a registered color extracted from the extraction region. Item 2. The image inspection apparatus according to Item 1. The accepting unit accepts designation of a foreground area from which a foreground color is extracted and designation of a background area from which a background color is extracted;
The extraction unit extracts a foreground color from the foreground area as the registered color, extracts a background color from the background area,
The conversion unit obtains a color distance of each pixel in the plurality of spectral images with respect to the foreground color, generates a foreground distance image having a value obtained for each pixel as a value of each pixel, and Obtaining the color distance of each pixel in the plurality of spectral images, generating a background distance image using the distance obtained for each pixel as the value of each pixel, and a difference image between the foreground distance image and the background distance image The image inspection apparatus according to claim 2, wherein the inspection image is generated as the inspection image.   The image inspection apparatus according to claim 1, wherein the imaging unit is a monochrome camera.   When the controller receives a single trigger signal, the controller controls the illumination unit and the imaging unit to continuously acquire the disturbance light image and the plurality of spectral images. The image inspection apparatus according to claim 1. The control unit is configured to correct a coordinate of each pixel in the plurality of spectral images and the disturbance light image, and a first correction image and a second correction image for the object moving at a constant transport speed. From the position of the correction target in the first correction image and the position of the correction target in the second correction image, each pixel of the plurality of spectral images and the disturbance light image is obtained. A coordinate correction unit for correcting coordinates;
The subtracting unit subtracts the disturbance light image whose coordinates are corrected by the coordinate correcting unit from each of the plurality of spectral images whose coordinates are corrected by the coordinate correcting unit. The image inspection apparatus according to 1.   The image according to claim 6, wherein the imaging unit continuously acquires the first corrected image, the second corrected image, the plurality of spectral images, and the disturbance light image at a constant time interval. Inspection device.   The image inspection apparatus according to claim 7, wherein the imaging unit acquires the first corrected image first and acquires the second corrected image last.   The illumination unit irradiates the object with illumination light of the same lighting color when acquiring the first correction image and the second correction image. The image inspection apparatus according to item.   The image inspection apparatus according to claim 9, wherein the lighting color is white.   10. The device according to claim 6, wherein any one of the first corrected image and the second corrected image is also used as one spectral image of the plurality of spectral images. The image inspection apparatus described. Obtaining a plurality of spectral images of the object corresponding to each lighting color while irradiating the object with illumination lights of a plurality of lighting colors different from each other;
Obtaining a disturbance light image of the object that is irradiated only with disturbance light by not being irradiated with the illumination light of the plurality of lighting colors;
Subtracting the disturbance light image from each of the plurality of spectral images;
An image inspection method comprising: a step of synthesizing a plurality of spectral images subtracted from the disturbance light image to generate an inspection image; and a step of inspecting the object using the inspection image.