JP2004045273A - Inspection device - Google Patents

Abstract

Provided is an inspection device capable of detecting an abnormal portion (for example, rust or mold) even in a mouth portion (base) having a step or the like.
A color camera 221 to 224 in which an optical axis is inclined with respect to an axial direction of a mouth portion 110 of a container 100 placed on a conveyor 210 so as to be able to image a step of the mouth portion 110, and And an image analyzer for analyzing the image of the mouth of the container and inspecting the mouth.
[Selection diagram] FIG.

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to an inspection device for inspecting a mouth of a container.
[0002]
[Prior art]
As an inspection device for a mouth (a base) of a container such as a beer barrel, there is an inspection device for inspecting rust (typically, red rust) and mold on the mouth. In this type of conventional inspection apparatus, as shown in FIG. 1, an opening 110 of a container 100 is disposed directly below a camera 10, and the camera 10 captures an image of the opening 110.
[0003]
The image output from the camera 10 is analyzed by an analysis device (not shown), whereby rust and mold on the mouth 110 are detected.
[0004]
[Problems to be solved by the invention]
In the conventional inspection apparatus, as described above, the mouth 110 is disposed immediately below the camera 10 and the mouth 110 is imaged. However, since the mouth 110 generally has a step 111 as shown in FIG. 2, a conventional inspection apparatus in which the mouth 110 is disposed immediately below the camera 10 to perform imaging, as in the related art, has a step portion of the mouth 110. Even if there are rusts or molds, they cannot be detected because they are extremely small or cannot be resolved in the captured image.
[0005]
Further, conventionally, since the mouth portion 110 is imaged by the camera 10, only a single color image is obtained, and there is a problem that detection accuracy of rust and mold is low.
[0006]
Further, rust may vary in color depth depending on the degree of rust, but there has been no method for accurately detecting rust having such various colors.
[0007]
The present invention has been made based on the above problem recognition, and one aspect of the present invention is to provide an inspection device capable of detecting an abnormal portion (for example, rust, mold) even in a mouth having a step or the like. The purpose is to do.
[0008]
Another object of the present invention is to provide a detection device capable of detecting abnormal portions such as rust of different degrees with high accuracy.
[0009]
[Means for Solving the Problems]
A first aspect of the present invention relates to an inspection device for inspecting a mouth of a container, and a support mechanism for supporting the container, and an optical axis inclined with respect to an axial direction of the mouth of the container supported by the support mechanism. It is characterized by comprising imaging means arranged so as to be arranged, and image analysis means for analyzing an image of the mouth of the container taken by the imaging means and inspecting the mouth.
[0010]
According to a preferred embodiment of the present invention, it is preferable that the imaging unit is a unit that can capture a color image, and the image analysis unit has a detection unit that detects an abnormal portion having a specific color. Is preferred.
[0011]
According to a preferred embodiment of the present invention, it is preferable that the detection unit detects the abnormal portion based on a ratio of R, G, and B components forming a color image.
[0012]
According to a preferred embodiment of the present invention, it is preferable that the detection unit is configured to detect at least one of rust and mold.
[0013]
According to a preferred embodiment of the present invention, the imaging means preferably includes a plurality of cameras arranged so as to be able to image the mouth of the container over the entire circumference.
[0014]
Alternatively, according to another preferred embodiment of the present invention, the support mechanism includes a rotation unit that rotates the container so that the imaging unit can image the mouth of the container over the entire circumference. It is preferred to have.
[0015]
Alternatively, according to still another preferred embodiment of the present invention, the inspection device is configured to rotate around the axis of the mouth of the container so as to cause the imaging unit to image the mouth of the container over the entire circumference. It is preferable that the image forming apparatus further includes a rotation unit that rotates the imaging unit.
[0016]
According to a preferred embodiment of the present invention, it is preferable that the inspection apparatus further includes an illumination system that illuminates the container so that the mouth of the container is imaged under the same conditions over the entire circumference.
[0017]
A second aspect of the present invention relates to an inspection device that inspects a mouth of a container, the inspection device includes a color imaging unit that images the mouth of the container, and a mouth of the container that is imaged by the color imaging unit. Image analysis means for analyzing the color image of the container and inspecting the mouth, wherein the image analysis means detects an abnormality in the mouth of the container based on a ratio of R, G, and B components constituting the color image. It is characterized by doing.
[0018]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.
[0019]
FIG. 3 is a side view of the inspection apparatus according to the preferred embodiment of the present invention. FIG. 4 is a view of the inspection apparatus shown in FIG. 3 as viewed from above. The inspection apparatus according to the present embodiment is designed to inspect an abnormal portion in a mouth (base) 110 of a container 100 such as a beer barrel, more specifically, to inspect for occurrence of rust (typically, red rust) or mold. It is configured. The present invention is not limited to beer barrels, but is applicable to inspection of the mouth of any container.
[0020]
The inspection apparatus of this embodiment has a conveyor (transport mechanism) 210 that transports the container 100. The conveyor 210 conveys the container 100 placed thereon, and stops at a predetermined inspection area (inspection position). Here, the inspection area is an area centered on the axis A in this embodiment. That is, in this embodiment, the container 100 is arranged by the conveyor 210 at a position where the axis of the container 100 matches the axis A. In this embodiment, the axis of the container 100 and the axis of the mouth 110 coincide with each other.
[0021]
As shown in FIGS. 3 and 4, in this embodiment, a plurality of color cameras 221 to 224 in which the optical axes B to E are inclined with respect to the axial direction of the opening 110 of the container 100 (the direction of the axis A). Is installed. The optical axes of the color cameras 221 to 224 are directed substantially toward the center of the mouth 110 of the container 100. In this way, by arranging the color cameras 221 to 224 at an angle, the step 111 inside the mouth 110 can be clearly imaged. The number of color cameras is not particularly limited. Alternatively, a color camera may be additionally disposed directly above the mouth 110, or a monochrome camera may be additionally disposed.
[0022]
An illumination system 230 is arranged above the inspection area of the container 100. The illumination system 230 includes, for example, a white dome-shaped reflecting member 231 and a light source 232. The illumination system 230 provides uniform illumination light to the mouth 110. The color temperature of the light generated by the light source 232 and the characteristics of the reflection member 231 can be appropriately changed according to the characteristics of the abnormal part to be detected, the characteristics of the color cameras 221 to 224, the characteristics of image processing described later, and the like. . By covering the upper space of the mouth 110 with the dome-shaped reflecting member 231 as described above, it is possible to prevent an upper structure (for example, a manufacturing facility, a ceiling), an operator, and the like from being reflected on the mouth 110, An optimal observation environment can be provided.
[0023]
FIG. 5 is a side view of an inspection apparatus according to another embodiment of the present invention. Note that components common to FIGS. 3 and 4 are denoted by the same reference numerals. In the embodiment shown in FIG. 5, the number of color cameras may be one.
[0024]
In the embodiment shown in FIG. 5, the container 100 conveyed by the conveyor 210A is transferred onto the turntable 216 by the moving mechanism 215. At this time, the moving mechanism 215 transfers the container 100 such that the axis of the container 100 substantially matches the rotation axis A of the turntable 216. The rotary table 216 is driven to rotate by a motor 217. The container 100 for which the inspection has been completed is transferred to the conveyor 210B by the moving mechanism 215, and then is conveyed to the next process by the conveyor 210B.
[0025]
In the embodiment shown in FIG. 5, while the container 100 is rotated by a predetermined angle (for example, 60 degrees) by the motor 217, the color camera 221 captures an image of the mouth 110 over the entire circumference. Therefore, in this embodiment, the mouth 110 can be imaged over the entire circumference by one color camera. Note that the rotation angle of the container 100 per time can be appropriately changed according to, for example, the field of view of the color camera 221, required inspection accuracy, processing time, and the like.
[0026]
Further, in the embodiment shown in FIG. 5, by taking an image of the entire periphery of the mouth 110 with one color camera, the influence of the variation between the cameras and the field of view is eliminated, and the entire periphery of the mouth 110 is taken. Imaging can be performed under uniform conditions. Therefore, the inspection accuracy can be improved.
[0027]
In the embodiment shown in FIG. 5, the mouth 110 of the container 100 is imaged over its entire circumference while rotating or rotating the container 100. Alternatively, a color camera may be taken around the axis of the mouth 110. The mouth 110 may be imaged over the entire circumference while rotating or rotating the 110.
[0028]
Next, an image analysis device (image processing device) applied to the inspection device shown in FIGS. 3, 4, or 5 will be described. FIG. 6 is a diagram showing the image analysis device and its peripheral devices. Note that the color camera 220 in FIG. 6 includes the color cameras 221 to 224 in FIGS.
[0029]
The image analysis device 300 analyzes an image signal (that is, a color image of the mouth) provided from the color camera 200 and detects an abnormal portion in the mouth 110. The image analysis device 300 includes a rust detection block 301 and a mold detection block 302 as blocks for detecting an abnormal portion. The rust detection block 301 detects rust (for example, red rust) of the mouth 110 based on the color image. The mold detection block 302 detects mold at the mouth 110 based on the color image.
[0030]
The inspection result of the abnormal part is output to the output device 320. Here, the output device 320 is, for example, a printer, a display, a memory, a communication device, and further, a transport route of the container 100 (for example, a route for transporting a normal container, a route for removing an abnormal container) according to the inspection result. A control device or the like for switching may be included.
[0031]
Hereinafter, as an example of processing in the image analysis device 300, processing in the rust detection block 301 will be exemplarily described with reference to FIG. Note that the processing in the mold detection block 302 is different from the rust detection block 301 only in the criterion of determination (color to be detected), and thus the description thereof is omitted.
[0032]
Here, detection of red rust which may typically occur in the mouth 110 will be described. Since red rust is characterized by having a slightly red color, red rust can be detected by analyzing the color image provided from the color camera 220 using its properties.
[0033]
A color image provided from the color camera 220 (221 to 224) is composed of R (red), G (green), and B (blue) components. In step S401, the rust detection block 301 converts the value of each color component into an 8-bit value (256 gradations) according to the following equation (1).
[0034]
R = Rin / Rin × 255 = 255
G = Gin / Rin × 255
B = Bin / Rin × 255
... (1)
Here, Rin, Gin, and Bin indicate the values of the R, G, and B components of the color image provided from the color camera 220 (221 to 224), respectively. , B component values.
[0035]
Equation (1) means that the R, G, and B components are normalized by the R component and converted to an 8-bit value (256 gradations). This is equivalent to obtaining the ratio of the G and B components to the value of the R component.
[0036]
FIG. 7 exemplarily shows a result obtained by converting the R, G, and B components of the color image provided from the color cameras 220 (221 to 224) according to the equation (1).
[0037]
In step S402, the rust detection block 301 extracts each pixel in which the G component and the B component do not reach the predetermined thresholds, as pixels constituting the red rust area. For example, if the threshold values of the G and B components are respectively set to 240, five examples (pixels) shown in FIG. 7 are extracted as pixels constituting the red rust area. As described above, by extracting the red rust area based on the ratio of the values of the G and B components to the value of the R component, for example, a clear true red (that is, the values of the G and B components become the values of the R component) In addition to red, which is very small with respect to the red component, a reddish color (that is, a color in which the values of the G and B components are smaller than the values of the R components but close to it) can be detected. Also, although the R component of an image obtained by capturing a true red image rarely has the maximum gradation value, the above-described method generally indicates that the R component of the captured image is obtained. Regardless of the size, a red rust area can be extracted.
[0038]
Next, in step S403, the rust detection block 301 determines whether or not the red rust area extracted in step S402 is an actual red rust area, and thereby determines whether or not red rust exists in the mouth 110. In the determination of such an actual red rust area, for example, a red rust area having a predetermined area or more is determined as an actual red rust area in order to eliminate the influence of noise.
[0039]
Next, in step S404, the rust detection block 301 outputs the determination result (presence or absence of red rust) to the output device 320.
[0040]
【The invention's effect】
According to one aspect of the present invention, for example, an abnormal portion (for example, rust or mold) can be detected even in a mouth having a step or the like.
[0041]
Further, according to another aspect of the present invention, for example, abnormal portions such as rust of different degrees can be detected with high accuracy.
[Brief description of the drawings]
FIG. 1 is a view schematically showing a conventional inspection apparatus.
FIG. 2 is a diagram showing a mouth (a base) of a beer barrel.
FIG. 3 is a side view of the inspection apparatus according to the preferred embodiment of the present invention.
4 is a view of the inspection device shown in FIG. 3 as viewed from above.
FIG. 5 is a side view of an inspection apparatus according to another embodiment of the present invention.
FIG. 6 is a diagram showing an image analysis device and its peripheral devices.
FIG. 7 exemplarily shows the result of normalizing the R, G, and B components of a color image provided from a color camera with the value of the R component.
FIG. 8 is a diagram showing a flow of processing in a rust detection block.
[Explanation of symbols]
10 Camera 100 Container 110 Mouth 111 Step Mouth 210, 210A, 210B Conveyor 215 Moving Mechanism 216 Rotary Table 217 Motor 220 Color Camera 221 to 224 Color Camera A Container, Mouth, and Axis B to E of Rotary Table Camera Light Axis 230 Illumination system 231 Light source 300 Image analysis device 301 Rust detection block 302 Mold detection block 320 Output device

Claims (9)

An inspection device for inspecting the mouth of the container,
A support mechanism for supporting the container,
Imaging means arranged with the optical axis inclined with respect to the axial direction of the mouth of the container supported by the support mechanism,
Image analysis means for analyzing the image of the mouth of the container imaged by the imaging means and inspecting the mouth,
An inspection apparatus comprising: The inspection apparatus according to claim 1, wherein the imaging unit is a unit capable of capturing a color image, and the image analysis unit includes a detection unit that detects an abnormal portion having a specific color. The inspection apparatus according to claim 2, wherein the detection unit detects the abnormal portion based on a ratio of R, G, and B components forming a color image. The inspection device according to claim 2, wherein the detection unit is configured to detect at least one of rust and mold. 5. The apparatus according to claim 1, wherein the imaging unit includes a plurality of cameras arranged so as to be able to capture an image of a mouth of the container over the entire circumference. 6. Inspection equipment. 5. The support mechanism according to claim 1, further comprising a rotation unit configured to rotate the container so that the imaging unit can image the mouth of the container over the entire circumference. 6. 2. The inspection device according to claim 1. 4. The image forming apparatus according to claim 1, further comprising a rotating unit configured to rotate the image capturing unit about an axis of the container mouth so that the image capturing unit captures an image of the mouth of the container over the entire circumference. 5. The inspection device according to any one of 4. The inspection apparatus according to any one of claims 1 to 7, further comprising an illumination system that illuminates the container so that the mouth of the container is imaged under the same conditions over the entire circumference. . An inspection device for inspecting the mouth of the container,
Color imaging means for imaging the mouth of the container,
Image analysis means for inspecting the mouth by analyzing a color image of the mouth of the container imaged by the color imaging means,
Wherein the image analysis means detects an abnormality in the mouth of the container based on a ratio of R, G, and B components forming a color image.

Images