JP2019161249A - Image processing device, mounting device, image processing method, and program - Google Patents

Abstract

An object of the present invention is to appropriately image imaging targets having different sizes while suppressing equipment costs. An image processing device (30) for recognizing a component based on image data input from a single image capturing device (32) includes a mode selector (41) for selecting a standard mode or an image quality priority mode. An image generation unit (45) for generating a standard image from imaging data under normal imaging conditions; an image conversion unit (46) for converting an image from a standard image to a high-quality image in an image quality priority mode; And an image recognizing unit (47) for recognizing an image of a component. [Selection diagram] FIG.

Description

  The present invention relates to an image processing device, a mounting device, an image processing method, and a program used for image recognition of a captured image.

  2. Description of the Related Art Conventionally, as an imaging system mounted on various manufacturing apparatuses, one that uses an imaging field of view of an imaging apparatus depending on the size of an imaging target is known (see, for example, Patent Document 1). In the imaging system described in Patent Document 1, a standard-size imaging target is imaged by a standard visual field imaging device, and a minute-shaped imaging target is imaged by a high-resolution visual field imaging device. The captured image captured by each imaging device is sent to a capture board and digitized. Then, the captured image is subjected to various image processing by a processor or the like, and the imaging target is recognized. .

Japanese Patent Laid-Open No. 2005-064048

  However, in the imaging system described in Patent Document 1, a plurality of imaging systems must be prepared for changing the imaging field of view, which increases the equipment cost of the imaging system. Although it is conceivable to capture an imaging target with a single imaging system, with only a standard visual field imaging device, a resolution error and recognition accuracy deteriorate due to insufficient resolution for an imaging target with a minute shape. On the other hand, there is a problem that only an imaging device with a high resolution field of view has to be divided and recognized depending on the size of the imaging target, resulting in a long processing time.

  The present invention has been made in view of the above points, and an object thereof is to provide an image processing device, a mounting device, an image processing method, and a program capable of appropriately capturing images of imaging objects having different sizes while reducing facility costs. One of them.

  An image processing apparatus according to an aspect of the present invention is an image processing apparatus that recognizes an image of an imaging target based on imaging data input from a single imaging apparatus, and selects a standard mode or an image quality priority mode. An image generation unit that generates a standard image from imaging data under normal imaging conditions, an image conversion unit that converts a standard image to a high-quality image in the image quality priority mode, and an imaging target from the standard image or the high-quality image And an image recognition unit for recognizing the image.

  An image processing method according to an aspect of the present invention is an image processing method for recognizing an imaging target based on imaging data input from a single imaging device, and selecting a standard mode or an image quality priority mode; Generating a standard image from imaging data under normal imaging conditions, converting an image from a standard image to a high-quality image in an image quality priority mode, and recognizing an imaging target from the standard image or the high-quality image. It is characterized by that.

  According to these configurations, the imaging target is image-recognized by the standard image in the standard mode, and the imaging target is image-recognized by the high-quality image in the image quality priority mode. Therefore, by appropriately using the standard mode and the image quality priority mode according to the size of the imaging target, it is possible to appropriately recognize the imaging target. In addition, since a high-quality image is generated from the standard image by processing on the software module side, it is not necessary to prepare a plurality of imaging devices, and the equipment cost can be reduced.

  In the image processing apparatus, the mode selection unit selects a standard mode or an image quality priority mode according to the size of the imaging target. According to this configuration, a mode suitable for the size of the imaging target is automatically selected.

  In the image processing apparatus, the image conversion unit performs image conversion by super-resolution processing. According to this configuration, by using the super-resolution processing, the resolution can be sufficiently increased even in the processing on the software module side, and a reduction in recognition accuracy due to insufficient resolution can be suppressed.

  The image processing apparatus includes a transfer condition setting unit that receives imaging data from the imaging apparatus via a capture board and sets a transfer condition of the imaging data for the capture board. According to this configuration, the transfer rate of the capture board can be set on the image processing apparatus side, and the transfer speed of the imaging data from the capture board to the image processing apparatus can be increased. An increase in tact time can be suppressed by allocating a reduction in the transfer time of imaging data to the processing time of image conversion.

  In the above-described image processing apparatus, the transfer condition setting unit sets the presence / absence of cutout transfer according to the outer size of the imaging target as the transfer condition. According to this configuration, it is possible to increase the transfer speed by reducing the data size of the imaging data by cutout transfer.

  The image processing apparatus includes an imaging condition setting unit that sets imaging conditions for the imaging apparatus. According to this configuration, the imaging condition of the imaging device can be set on the image processing device side, and the transfer speed of the captured image from the imaging device to the image processing device can be increased.

  In the above image processing apparatus, the mode selection unit selects any one of a standard mode, an image quality priority mode, and a speed priority mode, and the imaging condition setting unit sets normal imaging conditions in the standard mode and the image quality priority mode. In the speed priority mode, an image pickup condition having a lower image quality than the normal image pickup condition is set. The image generation unit generates a standard image from normal image pickup data in the standard mode and the image quality priority mode, and lower in the speed priority mode. A low-quality image is generated from image-captured image data, and the image conversion unit converts the standard image into a high-quality image in an image quality priority mode, and the image recognition unit converts the standard image, the high-quality image, and the low-quality image from Image recognition is performed on the imaging target. According to this configuration, in the speed priority mode, the image quality is lowered, and thus the transfer speed of the captured image from the imaging device to the image processing device can be increased.

  In the image processing apparatus, the imaging condition setting unit sets a binning process of the imaging apparatus in a speed priority mode as an imaging condition with low image quality. According to this configuration, by performing the binning operation of the imaging device, it is possible to increase the transfer speed of the captured image from the imaging device to the image processing device using a binning image with a reduced data size.

  The image processing apparatus includes a mode designating unit that accepts designation of a standard mode, an image quality priority mode, and a speed priority mode from a user, and has a mode designated by the mode designating unit rather than a mode selected by the mode selection unit. Prioritize. According to this structure, the mode automatically selected by the mode selection part can be changed by a user's judgment.

  In the image processing apparatus, the image recognition of the image recognition unit and the image conversion of the image conversion unit are executed in parallel by a multiprocessor or a multicore processor. According to this configuration, a core is assigned to each of image recognition and image conversion, and the processing speed can be increased by moving image recognition and image conversion in parallel.

  A mounting device according to an aspect of the present invention includes the image processing device described above and an imaging device that inputs a component image as a captured image to the image processing device, and recognizes a component from the component image by the image processing device. It is characterized by doing. According to this configuration, the image of the component can be appropriately recognized according to the component size, and thus the component can be appropriately mounted according to the recognition result.

  A program according to one aspect of the present invention is a program for an image processing device that recognizes an image of an imaging target based on imaging data input from a single imaging device, and selects a standard mode or an image quality priority mode. Generating a standard image from imaging data of normal imaging conditions, converting an image from a standard image to a high-quality image in an image quality priority mode, and recognizing an imaging target from the standard image or the high-quality image, The image processing apparatus is executed. According to this configuration, by installing the program in the image processing apparatus, it is possible to appropriately capture images of imaging objects having different sizes while suppressing facility costs.

  According to the present invention, by properly using the standard mode and the image quality priority mode, it is possible to appropriately capture images of imaging objects having different sizes while suppressing the equipment cost.

It is a schematic diagram which shows the whole mounting apparatus of this Embodiment. It is a schematic diagram which shows the mounting head periphery of this Embodiment. It is a block diagram of an imaging device and an image processing device of this embodiment. It is a flowchart of the mode selection process of this Embodiment.

  Hereinafter, the mounting apparatus of the present embodiment will be described with reference to the accompanying drawings. FIG. 1 is a schematic diagram showing the entire mounting apparatus of the present embodiment. FIG. 2 is a schematic diagram showing the periphery of the mounting head of the present embodiment. In addition, the mounting apparatus of this Embodiment is only an example, and can be changed suitably.

  As shown in FIG. 1, the mounting apparatus 1 is configured to mount a component P (see FIG. 2) supplied by a feeder 13 at a predetermined position on a substrate W by a mounting head 12. A substrate transport unit 11 that transports the substrate W in the X-axis direction is disposed on the base 10 of the mounting apparatus 1. The board transport unit 11 loads and positions the board W before component mounting from one end side in the X-axis direction below the mounting head 12, and moves the board W after component mounting from the other end side in the X-axis direction to the outside of the apparatus. I am carrying it out. A feeder bank 14 in which a plurality of feeders 13 are arranged side by side in the X-axis direction is detachably connected to both sides of the substrate transport unit 11.

  A tape reel 15 is detachably mounted on the feeder 13, and a carrier tape in which a large number of parts P are packaged is wound around the tape reel 15. The feeder 13 sequentially feeds the parts P toward the supply position picked up by the mounting head 12 by the rotation of the sprocket wheel in the apparatus. At the supply position of the mounting head 12, the cover tape on the surface is peeled from the carrier tape, and the component P in the pocket of the carrier tape is exposed to the outside. In the present embodiment, a tape feeder is illustrated as the feeder 13, but another feeder may be provided.

  A moving mechanism 16 that horizontally moves the pair of mounting heads 12 in the X-axis direction and the Y-axis direction is provided on the base 10. The moving mechanism 16 has a pair of Y-axis drive units 17 extending in the Y-axis direction and an X-axis drive unit 18 extending in the X-axis direction. The pair of Y-axis drive parts 17 are supported by support parts (not shown) erected at the four corners of the base 10, and the X-axis drive part 18 is movable to the pair of Y-axis drive parts 17 in the Y-axis direction. is set up. The mounting head 12 is installed on the X-axis drive unit 18 so as to be movable in the X-axis direction. The mounting head 12 is horizontally moved by the X-axis drive unit 18 and the Y-axis drive unit 17 and picked up from the feeder 13. The component P is mounted at a desired position on the substrate W.

  As shown in FIG. 2, the mounting head 12 is configured by providing a plurality of suction nozzles 22 (only one is shown in the present embodiment) on a head body 21 supported by an X-axis drive unit 18 (see FIG. 1). Has been. Each suction nozzle 22 is supported by the head main body 21 via a nozzle driving unit 23, and moves up and down in the Z-axis direction and rotates about the Z-axis by the nozzle driving unit 23. Each suction nozzle 22 is connected to a suction source (not shown), and holds the component P by a suction force from the suction source. The suction nozzle 22 is provided with a coil spring, and the component P sucked by the suction nozzle 22 is mounted on the substrate W while the coil spring is contracted.

  The head main body 21 is provided with a height measurement sensor 24 (see FIG. 1) for detecting the height from the substrate W, and a component detection unit 25 for performing image recognition of component shapes and detection of suction mistakes. In the height measurement sensor 24, the distance from the substrate W to the suction nozzle 22 is detected by reflection of the inspection light, and the vertical movement amount of the suction nozzle 22 is controlled based on the detection result. In the component detection unit 25, the light emitting unit 26 and the light receiving unit 27 are opposed to each other in the horizontal direction, and the component shape, suction error, and the like are inspected from the light shielding state in which the light from the light emitting unit 26 is shielded by the component P. The component detection unit 25 may emit LED light from the light emitting unit toward the light receiving unit, or may emit laser light from the light emitting unit toward the light receiving unit.

  The head main body 21 includes a substrate imaging unit 28 (see FIG. 1) that images the BOC mark on the substrate W from directly above, and a component imaging unit 29 that images the mounting operation of the component P by the suction nozzle 22 from obliquely above. Is provided. In the board imaging unit 28, the position, warpage, and the like of the board W are image-recognized based on the captured image of the BOC mark, and the mounting position of the component P on the board W is corrected based on these recognition results. In the component imaging unit 29, whether or not the component P is sucked by the suction nozzle 22 and whether or not the component P is mounted on the substrate W is inspected according to the captured image of the component P. Imaging data is input from the imaging device 32 such as the component imaging unit 29 to the image processing device 30 (see FIG. 3), and the image processing device 30 recognizes the image of the component P based on the imaging data.

  By the way, in a general mounting apparatus, various components are mounted on a substrate, but depending on the component size, imaging must be performed by changing the field of view of the imaging device. For this reason, in addition to the standard visual field imaging device, an imaging device and a lens corresponding to the high resolution visual field are provided as an option, and imaging is performed while switching between the standard visual field and the high resolution visual field according to the component size. However, it is necessary to prepare an imaging device and a lens with a high resolution visual field, and there is a problem that the equipment cost increases. On the other hand, only an imaging device with a high-resolution field of view must be divided and recognized depending on the component size, and the processing time is increased by repeating the imaging process.

  Therefore, in the image processing apparatus of the present embodiment, instead of having the super resolution visual field imaging device as an option, the software module performs image conversion such as super resolution conversion on the standard image acquired from the standard visual field imaging device. To improve image quality. By creating a high-quality image corresponding to a super-resolution field of view with a software module, it is possible to integrate an image pickup device with a standard field of view and an image pickup device with a high-resolution field of view to reduce equipment costs. Further, the increase in the tact time is suppressed by increasing the transfer speed of the imaging data and using the image conversion processing time on the software module side as the transfer time reduction time.

  Hereinafter, the imaging apparatus and the image processing apparatus will be described with reference to FIG. FIG. 3 is a block diagram of the imaging apparatus and the image processing apparatus of the present embodiment. In the block diagram of FIG. 3, the imaging device and the image processing device are described in a simplified manner. However, it is assumed that the imaging device and the image processing device normally include the configuration. The operations of the captured image and the image processing apparatus in FIG. 3 are merely examples, and the present invention is not limited to this configuration.

  As shown in FIG. 3, an imaging device 32 is connected to the image processing device 30 via a capture board 31, and imaging data captured by the imaging device 32 is digitized by the capture board 31 and image processing device 30. Has been entered. In the image processing apparatus 30, various processes are performed on the captured data according to the component size, so that the component P is recognized from the captured image, and positioning, inspection, measurement, and the like are performed. The image processing apparatus 30 includes a mode selection unit 41, a mode specification unit 42, a transfer condition setting unit 43, an imaging condition setting unit 44, an image generation unit 45, an image conversion unit 46, and an image recognition unit 47.

  In the mode selection unit 41, the standard mode or the image quality priority mode is automatically selected according to the component size. In this case, the external size or electrode size of the component is compared with the reference value as the component size. For example, the standard mode is selected if the short side size of the component is greater than or equal to the reference value, and the image quality priority mode is selected if the short side size of the component is less than the reference value. For example, if the electrode length of the component P is equal to or greater than the reference length, the standard mode is selected, and if the electrode length of the component P is less than the reference length, the image quality priority mode is selected. The mode selection unit 41 is not limited to the configuration in which the mode is selected according to the component size, and the mode may be selected according to the component name and other selection conditions.

  The mode selection unit 41 may select the speed priority mode in addition to the standard mode and the image quality priority mode. The standard mode is a mode in which a standard image captured under normal imaging conditions is used, and is mainly used in an imaging process from a medium-sized component to a large component. The image quality priority mode is a mode that uses a high-quality image in which the image quality is higher than that of a standard image, and is mainly used for imaging processing of small parts. The speed priority mode is a mode in which a low-quality image with a lower image quality than that of a standard image is used, and is used when it is desired to prioritize the processing speed over the component recognition accuracy regardless of the component size.

  The mode designation unit 42 accepts from the user the mode designation of the standard mode, the image quality priority mode, and the speed priority mode. When the mode is specified by the mode specification unit 42 from the user, the mode specified by the mode specification unit 42 is given priority over the mode selected by the mode selection unit 41. For this reason, the mode automatically selected by the mode selection unit 41 according to the component size can be changed by the user's judgment. For example, the speed priority mode can be designated if the error level accuracy is lowered, and the accuracy priority mode can be used if the error level speed is lowered, and the mode can be flexibly changed according to the user's application. .

  In the transfer condition setting unit 43, the transfer condition of the imaging data for the capture board 31 is set. As the transfer condition, the presence or absence of cut-out transfer is set according to the external size of the part in the standard mode and the image quality priority mode. When a transfer condition is input from the transfer condition setting unit 43 to the capture board 31, the transfer condition is reflected on the capture board 31. When the cut-out transfer is set to “invalid”, the entire imaging data is transferred from the capture board 31 to the image processing apparatus 30, and when the cut-out transfer is set to “valid”, the image is captured from the capture board 31 to the image processing apparatus 30. A part of the data is cut out and transferred.

  For example, if the component size is equal to or larger than the reference value, the cut-out transfer is set to “invalid”, and the captured data is transferred without being cut out by the capture board 31. On the other hand, if the component size is less than the reference value, the cut-out transfer is set to “valid”, and the central area of the imaging data is cut out according to the transfer size by the capture board 31 and transferred. Since the imaging device 32 captures an image with the component in the center, the component image is not lost by cutting out the central region of the imaging data. The transfer speed can be increased by reducing the data size of the imaging data by cut-out transfer. Therefore, even in the standard mode, it is possible to prioritize speed by cut-out transfer.

  In the imaging condition setting unit 44, imaging conditions for the imaging device 32 are set. As the imaging condition, “normal” is set in the standard mode and the image quality priority mode, and “low image quality” in which the image quality is lower than “normal” is set in the speed priority mode. When an imaging condition is input from the imaging condition setting unit 44 to the imaging device 32 via the capture board 31, the imaging condition is reflected to the imaging device 32. When the image pickup condition is “normal”, the image pickup device 32 picks up the part with the standard specification, and when the image pickup condition is “low image quality”, the image pickup device 32 lowers the resolution and the compression rate from the standard specification and the part is picked up. Imaged.

  For example, in the standard mode and the image quality priority mode, the parts are imaged with the standard specifications, and thus the images are captured without reducing the data size. On the other hand, in the speed priority mode, since a binning process is performed at the time of imaging, imaging is performed with a reduced data size by reading a plurality of pixels as one pixel. In the speed priority mode, by performing the binning operation of the imaging device 32, the transfer speed can be increased by a binning image with a reduced data size. In addition to the binning process, a thinning process that thins out pixels at a predetermined rate may be set as the low image quality imaging condition.

  In the image generation unit 45, a standard image is generated from imaging data under normal imaging conditions in the standard mode and image quality priority mode, and a low quality image is generated from imaging data under low image quality conditions in the speed priority mode. Further, the image conversion unit 46 performs image conversion from the standard image to the high-quality image in the image quality priority mode. The standard image is a standard size and standard pixel rate image, the low resolution image is a reduced size and high pixel rate image, and the high resolution image is an enlarged size and low pixel rate image. In this way, a standard image, a low resolution image, and a high resolution image are generated for each mode.

  Further, super-resolution processing is used for image conversion of the image conversion unit 46 of the present embodiment, and high resolution is realized by estimating the correct pixel value from the standard image and increasing the number of pixels. By using the super-resolution processing, the resolution can be sufficiently increased even in the processing on the software module side, and a reduction in recognition accuracy due to insufficient resolution can be suppressed. Note that image conversion is not limited to super-resolution processing. For example, bilinear interpolation for performing image conversion using a weighted average of luminance values of four pixels around the pixel of interest, or luminance of 16 pixels around the pixel of interest. Bicubic interpolation that approximates and interpolates values by a cubic equation may be used.

  The image recognition unit 47 recognizes the component P from the standard image in the standard mode, recognizes the component P from the high quality image in the image quality priority mode, and recognizes the component P from the low quality image in the speed priority mode. Since the mode is selected according to the component size and the like and the image is recognized with an appropriate image quality, the recognition error and the deterioration of the recognition accuracy due to insufficient resolution are suppressed. For example, for a small component, a high-quality image is generated in the high-quality mode, and the small component is recognized with high accuracy from the high-quality image. Based on the recognition result of the image recognition unit 47, various processes such as a positioning process, an inspection process, and a measurement process are performed.

  The mode selection unit 41, the mode specification unit 42, the transfer condition setting unit 43, the imaging condition setting unit 44, the image generation unit 45, the image conversion unit 46, and the image recognition unit 47 are configured by a processor, a memory, and the like that execute various processes. Has been. As the processor, a multi-core processor having a plurality of processor cores or a multi-processor is provided. The memory is composed of one or a plurality of storage media such as a ROM (Read Only Memory) and a RAM (Random Access Memory) depending on the application. The memory stores a program that causes the image processing apparatus 30 to execute the image processing method.

  Here, the processor core 51 is assigned for image recognition and the like performed in a general image processing apparatus, and the processor core 52 is assigned for newly added image conversion and the like. Processing speed is increased by moving image recognition and image conversion in parallel. In addition to the image conversion, the processor core 52 may be assigned any one or all of the processes of mode selection, mode designation, transfer condition setting, and imaging condition setting. Moreover, it is not limited to the two processor cores 51 and 52, and three or more processor cores may be provided.

  Next, the flow of processing operations of the image processing apparatus 30 will be described. First, the mode selection unit 41 selects a mode according to the component size. As described above, either the standard mode or the image quality priority mode is selected by comparing the external size or electrode length as the component size with the reference value. Further, when the mode is specified by the user in the mode specifying unit 42, the mode selection of the mode selecting unit 41 is reversed. For example, the speed priority mode is manually selected when the degradation in recognition accuracy is small even when the image quality is lowered. Details of mode selection according to the component size by the mode selection unit 41 will be described later.

  When the mode of the image processing device 30 is confirmed, the transfer condition setting unit 43 sets the transfer condition on the capture board 31 and the imaging condition setting unit 44 sets the imaging condition on the imaging device 32. The transfer condition setting unit 43 sets the cutout transfer to “invalid” or “valid” by comparing the outer size with the reference value. In the imaging condition setting unit 44, “normal” is set in the standard mode and image quality priority mode, and “low image quality” is set in the speed priority mode. When a part is imaged with a standard field of view (for example, a 54 mm field of view) by the imaging device 32, imaging data is transferred from the imaging device 32 to the image processing device 30 via the capture board 31.

  When the standard mode is selected, since the imaging condition is set to “normal”, imaging data of a standard size (for example, 1024 × 1024) is transferred from the imaging device 32 to the capture board 31. When the cut-out transfer of the capture board 31 is set to “invalid”, standard-size imaging data is transferred from the capture board 31 to the image processing apparatus 30. On the other hand, when the cutout transfer of the capture board 31 is set to “valid”, the image pickup data cut out from the image pickup data only in the central area (for example, 512 × 512) is transferred from the capture board 31 to the image processing device 30. The

  When the image quality priority mode is selected, imaging data of a standard size (for example, 1024 × 1024) is transferred from the imaging device 32 to the capture board 31 as in the case of selecting the standard mode. Further, depending on whether or not the capture board 31 is cut out and transferred, the central area is cut out from the standard size image data or the image data and transferred. When the speed priority mode is selected, since the imaging condition is set to “low image quality”, imaging data of a reduced size (for example, 512 × 512) is transferred from the imaging device 32 to the capture board 31. Further, reduced-size imaging data is transferred from the capture board 31 to the image processing apparatus 30.

  When captured data is input to the image processing device 30, a captured image is generated by the image generation unit 45. In the standard mode, a standard image with a standard pixel rate (for example, 56 μm) is generated from the imaging data with a standard size (for example, 1024 × 1024). In the image quality priority mode, the standard image is converted by the image conversion unit 46, and a high-quality image with an enlarged size (for example, 2048 × 2048) and a low pixel rate (for example, 28 μm) is generated. In the speed priority mode, a low-quality image with a reduced size (for example, 512 × 512) and a high pixel rate (for example, 112 μm) is generated from the captured image data.

  When a standard image, a high-quality image, and a low-quality image are input to the image recognition unit 47, components are recognized from the standard image, the high-quality image, and the low-quality image. As described above, in the image quality priority mode, a high-quality image is generated from the standard image by image conversion, so that it is not necessary to prepare an imaging device for high image quality as an option. Further, when cut-out transfer is set to “valid” as the transfer condition, the data size of the imaging data is reduced by cut-out transfer, and the reduced transfer time can be used as the image conversion processing time. Therefore, it is possible to appropriately recognize the image of the component without increasing the equipment cost and the entire processing time.

  Next, the mode selection process will be described with reference to FIG. FIG. 4 is a flowchart of the mode selection process of the present embodiment. In the flowchart of FIG. 4, the short side size is used for mode selection as the external size of the part. However, this flowchart shows an example and is not limited to this configuration. Further, in FIG. 4, description will be made using the reference numerals in FIG. 3 as appropriate.

  As shown in FIG. 4, when the mode selection process is started by the mode selection unit 41, the mode designation unit 42 determines whether or not the user has designated a mode (step S01). If it is determined that “mode is specified” (Yes in step S01), the mode specified by the user is preferentially set (step S02). As a result, the mode can be set manually regardless of the component size. When it is determined that “no mode is specified” (No in step S01), the mode selection unit 41 refers to the dimension data of the component to determine the presence or absence of the electrode of the component (step S03).

  When it is determined that “there is no component electrode” (No in step S03), it is determined whether the short side size of the component is equal to or larger than a reference value (for example, 0.5 mm) (step S04). When it is determined that the short side size of the component is equal to or larger than the reference value (Yes in step S04), the standard mode in which the imaging condition is “normal” and the transfer condition cut-out transfer is set to “invalid” is selected ( Step S05). When it is determined that the short side size of the component is less than the reference value (No in step S04), the image quality priority mode in which the imaging condition is “normal” and the transfer condition cut-out transfer is set to “valid” is selected. (Step S06).

  If it is determined that “there is an electrode for the component” (Yes in step S03), it is determined whether the electrode length of the component is a reference value (for example, 0.4 mm) or more (step S07). If it is determined that the electrode length of the component is less than the reference value (No in step S07), the image quality priority mode in which the imaging condition is set to “normal” and the transfer condition cut-out transfer is set to “invalid” is selected ( Step S08). When it is determined that the electrode length of the component is greater than or equal to the reference value (Yes in step S07), it is determined whether or not the short side size of the component is greater than or equal to a reference value (for example, 0.5 mm) (step S09).

  When it is determined that the short side size of the component is equal to or larger than the reference value (Yes in step S9), the standard mode in which the imaging condition is “normal” and the transfer condition cut-out transfer is set to “invalid” is selected ( Step S10). When it is determined that the short side size of the component is less than the reference value (No in step S9), the standard mode in which the imaging condition is “normal” and the transfer condition cut-out transfer is set to “valid” is selected ( Step S11). Note that the speed priority mode in which the imaging condition is “low image quality” is manually designated by the user in the mode designation unit 42 in step S02 regardless of the external size of the component and the electrode length.

  As described above, in the image processing apparatus 30 according to the present embodiment, the component P is image-recognized by the standard image in the standard mode, and the component P is image-recognized by the high-quality image in the image quality priority mode. Therefore, by properly using the standard mode and the image quality priority mode according to the size of the imaging target, it is possible to appropriately recognize the image of the component P. In addition, since a high-quality image is generated from the standard image by processing on the software module side, it is not necessary to prepare a plurality of imaging devices, and the equipment cost can be reduced.

  In the present embodiment, the configuration has been described in which a component is imaged as an imaging target by the imaging device of the component imaging unit, but the present invention is not limited to this configuration. For example, a configuration in which a substrate mark is imaged as an imaging target by an imaging device of a substrate imaging unit may be used.

  In the present embodiment, the high-quality image is not necessarily determined by the size of the resolution. High-quality images include images that look good at the same resolution as standard images. Therefore, the image conversion unit is not limited to image conversion with high resolution.

  In the present embodiment, the low-quality image is not necessarily determined by the size of the resolution. Low-quality images include images that look bad at the same resolution as standard images. Therefore, the imaging condition with low image quality is not limited to the imaging condition that reduces the resolution.

  In the present embodiment, the mode selection unit selects the mode based on the component size such as the external size of the component and the electrode length. However, the present invention is not limited to this configuration. The mode selection unit only needs to be able to select the mode based on the selection condition. For example, the mode selection unit may automatically select the mode depending on the type of the component using the component name as the selection condition.

  In this embodiment, the image processing apparatus is configured to be able to set the standard mode, the image quality priority mode, and the speed priority mode. However, the present invention is not limited to this configuration. The image processing apparatus only needs to be able to set at least the standard mode and the image quality priority mode.

  In the present embodiment, the mode selection unit selects the standard mode and the image quality priority mode. However, the present invention is not limited to this configuration. The mode selection unit may select the speed priority mode in addition to the standard mode and the image quality priority mode.

  In the present embodiment, the presence / absence of cut-out transfer is set as the transfer condition. However, the present invention is not limited to this configuration. The transfer condition may be any condition at the time of transferring the imaging data. For example, a transfer speed may be set.

  In the present embodiment, in the cutout transfer, the cutout amount is set according to the external size of the component, but the present invention is not limited to this configuration. In the cut-out transfer, the central area may be cut out from the imaging data with a certain size.

  In the present embodiment, a configuration for setting a condition for reducing the image quality depending on the resolution such as binning processing or thinning-out processing is set as the imaging condition for low image quality. However, the present invention is not limited to this configuration. As the low image quality imaging condition, a condition for reducing the image quality by compression processing may be set.

  In the present embodiment, the mode designated by the mode designation unit is prioritized over the mode selected by the mode selection unit. However, the present invention is not limited to this configuration. The image processing apparatus may not be provided with the mode specifying unit.

  Further, in the present embodiment, the parts are exemplified as the imaging target, but the present invention is not limited to this configuration. The imaging target is not particularly limited as long as it is captured by the imaging device.

  In the present embodiment, the configuration in which the mounting apparatus includes the image processing apparatus has been described. However, the image processing apparatus can be applied to other apparatuses including the imaging device. For example, the image processing apparatus can be applied to a printing apparatus that prints paste solder on a substrate, an inspection apparatus that inspects the printed state of solder, a reflow apparatus that melts solder and attaches components.

  Moreover, in this Embodiment, although the suction nozzle was illustrated as a nozzle, it is not limited to this structure. The nozzle is not particularly limited as long as it can hold a component, and may be, for example, a gripper nozzle.

  In the present embodiment, the substrate is not limited to a printed circuit board as long as various components can be mounted, and may be a flexible substrate placed on a jig substrate.

  Moreover, the program of this Embodiment may be memorize | stored in a storage medium. The recording medium is not particularly limited, but may be a non-transitory recording medium such as an optical disk, a magneto-optical disk, or a flash memory.

  Moreover, although embodiment and modification of this invention were demonstrated, what combined the said embodiment and modification as the other embodiment of this invention entirely or partially may be sufficient.

  The embodiments of the present invention are not limited to the above-described embodiments and modifications, and various changes, substitutions, and modifications may be made without departing from the spirit of the technical idea of the present invention. Furthermore, if the technical idea of the present invention can be realized in another way by technological advancement or another derived technique, the method may be used. Accordingly, the claims cover all embodiments that can be included within the scope of the technical idea of the present invention.

  Furthermore, in the above-described embodiment, the image processing apparatus recognizes an image to be captured based on imaging data input from a single imaging apparatus, and includes a mode selection unit that selects a standard mode or an image quality priority mode, An image generation unit that generates a standard image from imaging data under imaging conditions, an image conversion unit that converts a standard image to a high-quality image in image quality priority mode, and image recognition that recognizes an imaging target from the standard image or high-quality image And a section. According to this configuration, the imaging target is image-recognized by the standard image in the standard mode, and the imaging target is image-recognized by the high-quality image in the image quality priority mode. Therefore, by appropriately using the standard mode and the image quality priority mode according to the size of the imaging target, it is possible to appropriately recognize the imaging target. In addition, since a high-quality image is generated from the standard image by processing on the software module side, it is not necessary to prepare a plurality of imaging devices, and the equipment cost can be reduced.

  As described above, the present invention has an effect that it is possible to appropriately capture images of imaging objects having different sizes while suppressing equipment costs, and in particular, an image processing device used for image recognition of components of a mounting device. This is useful for mounting apparatuses, image processing methods, and programs.

1: mounting device 30: image processing device 31: capture board 32: imaging device 41: mode selection unit 42: mode specification unit 43: transfer condition setting unit 44: imaging condition setting unit 45: image generation unit 46: image conversion unit 47 : Image recognition unit 51: Processor core 52: Processor core P: Parts (imaging target)
W: Substrate

Claims (13)

An image processing apparatus that recognizes an image of an imaging target based on imaging data input from a single imaging apparatus,
A mode selection unit for selecting a standard mode or an image quality priority mode;
An image generation unit that generates a standard image from imaging data under normal imaging conditions;
An image conversion unit that converts a standard image to a high-quality image in the image quality priority mode;
An image processing apparatus comprising: an image recognition unit that recognizes an imaging target from a standard image or a high-quality image.   The image processing apparatus according to claim 1, wherein the mode selection unit selects a standard mode or an image quality priority mode according to a size of an imaging target.   The image processing apparatus according to claim 1, wherein the image conversion unit performs image conversion by super-resolution processing. Imaging data is input from the imaging device via the capture board,
The image processing apparatus according to claim 1, further comprising a transfer condition setting unit configured to set a transfer condition of imaging data with respect to the capture board.   The image processing apparatus according to claim 4, wherein the transfer condition setting unit sets the presence or absence of cutout transfer according to an outer size of an imaging target as a transfer condition.   The image processing apparatus according to claim 1, further comprising an imaging condition setting unit that sets an imaging condition for the imaging apparatus. The mode selection unit selects one of a standard mode, an image quality priority mode, and a speed priority mode,
The imaging condition setting unit sets a normal imaging condition in the standard mode and the image quality priority mode, sets an imaging condition having a lower image quality than the normal imaging condition in the speed priority mode,
The image generation unit generates a standard image from normal imaging data in a standard mode and an image quality priority mode, and generates a low quality image from low-quality imaging data in a speed priority mode,
The image conversion unit converts an image from a standard image to a high-quality image in an image quality priority mode,
The image processing apparatus according to claim 6, wherein the image recognition unit recognizes an imaging target from a standard image, a high-quality image, and a low-quality image.   The image processing apparatus according to claim 7, wherein the imaging condition setting unit sets a binning process of the imaging apparatus in a speed priority mode as an imaging condition with low image quality. It has a mode specification part that accepts specification of standard mode, image quality priority mode, speed priority mode from the user,
The image processing apparatus according to claim 7, wherein the mode specified by the mode specifying unit is prioritized over the mode selected by the mode selecting unit.   The image processing apparatus according to claim 1, wherein the image recognition of the image recognition unit and the image conversion of the image conversion unit are executed in parallel by a multiprocessor or a multicore processor. An image processing apparatus according to any one of claims 1 to 10,
An imaging device for inputting a component image as a captured image to the image processing device;
A mounting apparatus for recognizing a part from a part image by the image processing apparatus. An image processing method for recognizing an image of an imaging target based on imaging data input from a single imaging device,
Selecting standard mode or image quality priority mode;
Generating a standard image from imaging data under normal imaging conditions;
Image conversion from standard image to high-quality image in image quality priority mode;
An image processing method comprising: recognizing an imaging target from a standard image or a high-quality image. A program for an image processing device that recognizes an image of an imaging target based on imaging data input from a single imaging device,
Selecting standard mode or image quality priority mode;
Generating a standard image from imaging data under normal imaging conditions;
Image conversion from standard image to high-quality image in image quality priority mode;
A program for causing the image processing apparatus to execute a step of recognizing an imaging target from a standard image or a high-quality image.

Images