JP5326990B2 - Application state inspection apparatus and method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a simpler, less expensive apparatus for the inspection of coated state, capable of improving an inspection accuracy. <P>SOLUTION: The apparatus for the inspection of coated state includes an imaging device photographing a coated part with a coating substance on a work surface, and an image processing device using a first threshold to split a photographed image obtained from the imaging device into a coated range with the coating substance and a non-coated range, selecting the non-coated range surrounded by the coated range as a processing object range, using a second threshold to determine whether the processing object range is a gloss range corresponding to gloss or a work range corresponding to the work surface, and changing the non-coated range selected as the processing object range to the coated range when determined as the gloss range. <P>COPYRIGHT: (C)2011,JPO&amp;INPIT

Description

 The present invention relates to an application state inspection apparatus, method, and program for inspecting the application state of an application.

  Conventionally, when assembling a machine that has a drive unit and requires lubricating oil, a liquid substance called a sealant made of silicone is applied to the joints of machine parts to prevent oil leakage from the joints. Techniques for preventing it are widely used. Problems of this method include the occurrence of oil leakage due to the cutting of the sealing agent and the mixing of foreign matter into the drive unit due to scattering. For this reason, conventionally, a dye or the like is added to the sealing agent to cause a color difference between the workpiece surface to be applied and the sealing agent, and whether the sealing agent is correctly applied by visual or image processing methods. I was inspecting.

 When image processing is used as an inspection method, binarization processing is performed on a photographed image obtained by photographing a sealant application portion on a workpiece, so that the photographed image corresponds to a sealant application region and a work surface. An inspection image obtained by the binarization process divided into a work area and a reference image acquired in advance (a photographed image obtained by photographing a normally applied sealant is binarized. In general, it is determined whether or not the sealant has been normally applied by performing pattern matching with the above. In recent years, in order to automate the inspection process, it has become the mainstream to inspect the application state of the sealant using image processing, but inspection by image processing is easily affected by ambient light such as room lighting. However, depending on the inspection environment, there is a problem that the inspection accuracy decreases.

 In response to the above-described problem, the following Patent Document 1 is provided with illumination that can change the irradiation direction and the irradiation luminance so that only a limited inspection region is irradiated with uniform light so that a sealant is applied. A technique for photographing a part is disclosed. Japanese Patent Application Laid-Open No. H10-228688 discloses a technique for performing imaging by irradiating a coating material with light in a wavelength band having a large absorbance and selectively transmitting only light in the wavelength band toward an imaging device such as a camera. Is disclosed.

JP-A-10-170242 Japanese Patent Laid-Open No. 2002-45766

The technique disclosed in Patent Document 1 requires an illumination light source having a drive unit, which leads to a complicated inspection apparatus. In addition, there is a problem that it is necessary to perform imaging a plurality of times while changing the irradiation condition depending on the size and shape of the inspection target, and the inspection time becomes long. In addition, when irradiating from one direction, it is possible to completely prevent the occurrence of harmful luster (that is, a decrease in inspection accuracy) due to direct reflection somewhere on the surface of the sealant that is piled up. I can't. As described above, the gloss generated on the surface of the sealant is erroneously recognized as a part of the work area by the binarization process, and in fact, the inspection result is abnormal even though the sealant application state is normal. Will be obtained.
On the other hand, the technique disclosed in Patent Document 2 requires a monochromatic light source suitable for the light absorption characteristics of the coating material and a filter for selectively transmitting the wavelength band, which increases the cost of the apparatus. In addition, since the light absorption characteristics depend on the components of the coated material, it is difficult to cope with changes in the components of the coated material.

 The present invention has been made in view of the above-described circumstances, and provides an application state inspection apparatus, method, and program capable of improving inspection accuracy and realizing simplification and cost reduction of the apparatus. For the purpose.

  In order to solve the above-mentioned problem, in the present invention, as a first solution means for an application state inspection device, there is provided an application state inspection device for inspecting the application state of a coating applied to a workpiece, An imaging device that captures the coating portion of the coating material, and a captured image obtained from the imaging device is divided into a coating region and a non-coating region of the coating material using a first threshold, and the coating region The enclosed non-application area is selected as a process target area, and it is determined whether the process target area is a gloss area corresponding to gloss or a work area corresponding to the workpiece surface using a second threshold value. And an image processing device that changes the non-application area selected as the process target area to the application area when it is determined as an area to be processed.

  Further, as a second solving means related to the application state inspection apparatus, in the first solving means, the image processing apparatus uses the second threshold when the area of the processing target area is a predetermined value or less. It is determined whether the processing target area is the glossy area or the work area, and when the area of the processing target area is larger than a predetermined value, the processing target area is determined as the work area. .

  Further, as a third solving means related to the application state inspection apparatus, in the first or second solving means, the image processing apparatus uses the second threshold value to set the processing target area as the glossy area and the workpiece. When the ratio of the glossy area in the processing target area is equal to or greater than a predetermined value, the processing target area is determined as the glossy area, and when the ratio of the glossy area is less than the predetermined value, The processing target area is determined as the work area.

  Further, as a fourth solving means related to the application state inspection apparatus, in any one of the first to third solving means, the image processing apparatus includes a storage device that stores a reference image acquired in advance. By comparing the reference image with an inspection image obtained by image processing, it is determined whether or not the application state of the application is normal.

  On the other hand, in the present invention, as a first solving means related to the application state inspection method, there is an application state inspection method for inspecting the application state of the application applied to the workpiece, and the application portion of the application on the workpiece A first image processing step of dividing the photographed image obtained by the imaging step into a coating region and a non-coating region of the coating material using a first threshold, and the coating region The non-application area surrounded by is selected as a processing target area, and a second threshold is used to determine whether the processing target area is a gloss area corresponding to gloss or a work area corresponding to the work surface, And a second image processing step of changing the non-application area selected as the process target area to the application area when it is determined to be a glossy area.

  Further, as a second solving means related to the application state inspection method, in the first solving means, in the second image processing step, when the area of the processing target region is a predetermined value or less, the second threshold value is set. Determining whether the processing target area is the glossy area or the work area, and determining that the processing target area is the work area when the area of the processing target area is larger than a predetermined value. Features.

  Further, as a third solving means relating to the application state inspection method, in the first or second solving means, in the second image processing step, the processing target area is set to the glossy area using the second threshold value. And the work area, and when the ratio of the gloss area in the process target area is equal to or greater than a predetermined value, the process target area is determined as the gloss area, and the ratio of the gloss area is less than the predetermined value In this case, the processing target area is determined as the work area.

  Further, as a fourth solving means related to the application state inspection method, in any one of the first to third solving means, the inspection images obtained by the first and second image processing steps are acquired in advance. It is characterized by having a third image processing step of determining whether or not the application state of the applied material is normal by comparing with the reference image.

 Furthermore, in the present invention, as a first solving means related to the application state inspection program, there is provided an application state inspection program used for inspecting the application state of a coating applied to a workpiece, wherein the application on the workpiece is performed. A first image processing that divides a photographed image obtained from an image pickup device that photographs an application part of an object into two using a first threshold value to be an application area and a non-application area of the application object, and is surrounded by the application area The non-application area is selected as a processing target area, and a second threshold is used to determine whether the processing target area is a gloss area corresponding to gloss or a work area corresponding to the work surface, and the gloss area If it is determined, the computer executes the second image processing for changing the non-application area selected as the process target area to the application area.

  Further, as a second solving means relating to the application state inspection program, in the first solving means, as the second image processing, when the area of the processing target region is a predetermined value or less, the second threshold value is set. And determining whether the processing target area is the glossy area or the work area, and determining that the processing target area is the work area when the area of the processing target area is larger than a predetermined value. The computer is executed.

  Further, as a third solving means relating to the application state inspection program, in the first or second solving means, as the second image processing, the processing target area is set as the glossy area using the second threshold value. When the work area is divided into two, and when the ratio of the glossy area in the processing target area is equal to or greater than a predetermined value, the processing target area is determined to be the glossy area, and the ratio of the glossy area is less than the predetermined value In addition, the computer is caused to execute a process of determining the processing target area as the work area.

  Further, as a fourth solving means related to the application state inspection program, in any one of the first to third solving means, a reference image is read from a storage device and obtained by the first and second image processing. By comparing the inspection image with the reference image, the computer is caused to execute a third image processing for determining whether or not the application state of the application is normal.

 According to the present invention, it is possible to eliminate the influence of the gloss produced on the surface of the coated product due to the reflection of light, which has been a cause of a decrease in inspection accuracy in the past (the glossy region corresponding to the gloss is applied to the coated region of the coated product). Therefore, it is possible to improve the inspection accuracy. In addition, according to the present invention, in order to eliminate the influence of the gloss generated on the surface of the coated object by image processing, an illumination light source or a monochromatic light source provided with a conventional drive unit is not required, and the apparatus can be simplified and reduced. Cost reduction can be realized.

1 is a schematic configuration diagram of a coating state inspection apparatus 1 according to an embodiment of the present invention. 4 is an operation flowchart of the application state inspection device 1. It is an example of the picked-up image obtained by image | photographing the application part of the sealing agent S with the imaging device 2 in the application state inspection apparatus 1. FIG. It is explanatory drawing regarding the 1st threshold value and 2nd threshold value which the image processing apparatus 3 in the application | coating state inspection apparatus 1 uses for the image process of a picked-up image. It is a figure which shows the image obtained when the image processing apparatus 3 performs a 1st image process with respect to a picked-up image. It is a figure which shows the test | inspection image finally obtained by the image processing apparatus 3 performing the 1st and 2nd image processing with respect to a picked-up image.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a schematic configuration diagram of a coating state inspection apparatus 1 according to the present embodiment. As shown in FIG. 1, the application state inspection device 1 in this embodiment inspects the application state of a sealant (application material) S applied to a workpiece W, and includes an imaging device 2 and an image processing device 3. And a storage device 4. In the present embodiment, it is assumed that a color difference is generated between the surface of the workpiece W, which is an application target, and the sealing agent S by adding a dye or the like to the sealing agent S.

  The imaging device 2 is, for example, a CCD (Charge Coupled Devices) camera, which is arranged immediately above the workpiece W, images the application portion of the sealant S on the workpiece W, and displays image data representing the captured image as an image processing device. 3 is output. Here, assuming that the resolution of the imaging device 2 is VGA (Video Graphics Array), the image data output from the imaging device 2 indicates the brightness (luminance) of each of the 640 × 480 pixels constituting the captured image. Contains luminance data. If the number of bits of each luminance data is assumed to be 8 bits, the luminance of each pixel is represented by a gradation value from 0 to 255.

  The image processing device 3 executes the predetermined image processing based on the image data input from the imaging device 2 in accordance with the application state inspection program 4a stored in the storage device 4 to thereby apply the sealing agent S Is a computer that determines whether or not is normal and outputs the determination result as an inspection result. As such an image processing apparatus 3, a microcomputer, CPU (Central Processing Unit), etc. can be used.

 Although details will be described later, the image processing apparatus 3 performs first image processing based on the application state inspection program 4a to divide a photographed image into two parts, that is, an application area and a non-application area of the sealant S using a first threshold value. The non-application area surrounded by the image processing and the application area is set as the process target area, and the process target area is the gloss area corresponding to the gloss generated by the reflection of light using the second threshold value, or the work W surface. Second image processing for determining whether the region is a work region and changing the processing target region determined to be a glossy region to a coating region, and an inspection image and storage device finally obtained by the first and second image processing 3 is compared with the reference image 4b stored in 4, and third image processing for determining whether or not the application state of the sealant S is normal is executed.

  The storage device 4 is, for example, an HDD (Hard Disk Drive), and an application state inspection program 4a executed by the image processing device 3 and a reference image 4b (a sealant S applied normally) acquired in advance. An image obtained by performing first and second image processing (to be described later) is stored in advance in a photographed image obtained by photographing in advance, and the application is performed in response to a read request from the image processing device 3 The state inspection program 4a and the reference image 4b are output to the image processing apparatus 3.

  Next, the operation of the application state inspection apparatus 1 configured as described above will be described in detail with reference to the flowchart of FIG. In addition, since the application | coating state inspection apparatus 1 in this embodiment does not require special special illumination, it shall be installed in the room | chamber interior provided with general illumination, such as a fluorescent lamp.

  As shown in FIG. 2, at the start of the inspection, first, the imaging device 2 images the application part of the sealant S on the workpiece W, and outputs image data representing the captured image to the image processing device 3 (step). S1: Imaging step). FIG. 3 is an example of a photographed image obtained by photographing the application part of the sealing agent S on the workpiece W. In the present embodiment, for convenience of explanation, as shown in FIG. 3, for example, a red sealing agent S is applied in an endless state so as to draw a circle on the workpiece W, and the interior lighting is reflected to gloss the surface of the sealing agent S. Assume that SL occurs and gloss WL occurs on the surface of the workpiece W.

  Subsequently, the image processing device 3 performs the binarization process using the first threshold value based on the image data input from the imaging device 2 as the first image processing based on the application state inspection program 4a. The photographed image is divided into two parts, that is, an application area and a non-application area of the sealant S (step S2: first image processing step). Here, since the image data input from the imaging device 2 includes luminance data corresponding to the three primary colors R (red), G (green), and B (blue), the captured image is also R, G. , B for each color. Therefore, the luminance difference (R−B) between red and the color of the work W (for example, blue) is calculated, the calculation result (hereinafter referred to as a difference image) is considered as the intensity of red, and the difference image is binarized. It is preferable to process.

  FIG. 4 is a diagram showing the respective luminances of the sealing agent S, the gloss SL on the surface of the sealing agent S, the surface of the workpiece W, and the gloss WL on the surface of the workpiece W based on the luminance data of each pixel constituting the difference image. . As shown in FIG. 4, the brightness of the sealant S is the highest while the brightness of the surface of the work W is the lowest, and the gloss SL of the surface of the sealant S and the gloss WL of the work W surface are close to white. Therefore, it can be seen that the luminances thereof are substantially the same and are intermediate values between the luminance of the sealing agent S and the luminance of the surface of the workpiece W.

  Based on FIG. 4 as described above, the first threshold value is a threshold value set in advance to divide the difference image into two parts, that is, the application area and the non-application area of the sealant S. Specifically, the first threshold value is determined as a pixel corresponding to the brightness of the sealant S as a constituent pixel of the application area of the sealant S, and the other surface of the workpiece W, the gloss SL of the surface of the sealant S, and The pixels corresponding to the brightness of the gloss WL on the surface of the workpiece W are set so as to be determined as the constituent pixels of the non-application area.

  In other words, by binarizing the difference image using the first threshold, among the pixels constituting the difference image, the pixel having the luminance equal to or higher than the first threshold is set to the first luminance value (for example, the maximum floor). Is converted into a tone value “255”) to become a pixel constituting the application region of the sealant S, and a pixel having a luminance less than the first threshold value has its luminance set to the second luminance value (for example, the minimum gradation value “−255”). )) To become pixels constituting the non-application area.

  FIG. 5 shows an image obtained by the first image processing as described above. In FIG. 5, the symbol SA indicates the application area of the sealant S, and the symbol NSA indicates the non-application area. As shown in FIG. 5, when the difference image is binarized using the first threshold value, a plurality of non-application areas NSA surrounded by the application area SA of the sealant S are generated. At this time, it is not possible to determine whether the non-application area NSA surrounded by the application area SA is a gloss area corresponding to the gloss SL on the surface of the sealant S or a work area corresponding to the surface of the workpiece W.

  Now, returning to FIG. 2 and continuing the description, as described above, the image processing apparatus 3 executes step S2 as the first image processing, whereby the difference image is not applied to the application area SA of the sealant S. After being divided into two regions NSA, the following steps S3 to S9 (second image processing step) are executed as second image processing. That is, as the second image processing, the image processing apparatus 3 first selects one of the non-application areas NSA surrounded by the application area SA of the sealant S as a process target area (step S3), It is determined whether or not the area of the selected processing target area is a predetermined value or less (step S4).

 Here, the predetermined value used for the area determination is set to a value that can determine whether or not the selected processing target area is likely to be a glossy area. For example, as shown in FIG. 5, the non-application area NSA surrounded by the application area SA has a small area inside the sealant S (which is likely to be a glossy area), and a circular shape. And those present in a large area at the center of the sealing agent S applied to the surface (those that are less likely to be glossy regions). Processing to such a non-application area NSA that is unlikely to be a glossy area causes an increase in processing time. Therefore, first, the processing target area (area that is highly likely to be a glossy area) to be processed is selected by the process of step S4.

  If “Yes” in step S4, that is, if the area of the processing target area is equal to or smaller than a predetermined value (in other words, if the area is likely to be a glossy area), the image processing apparatus 3 By performing the binarization process using the threshold value, the processing target area is divided into a gloss area and a work area (step S5). In the binarization processing of the processing target area in step S5, it is necessary to use the luminance data before executing step S2 (first image processing) (the luminance data of the processing target area after step S2 is (Because it has been converted to the minimum gradation value “−255”).

Here, as shown in FIG. 4, a threshold set in advance to divide the processing target area into two areas, that is, the gloss area and the work area, is the second threshold. Specifically, the second threshold value is determined such that a pixel corresponding to the brightness SL of the surface of the sealant S is determined as a constituent pixel of the gloss area, and a pixel corresponding to the brightness of the surface of the work W is set as a constituent pixel of the work area. It is set to be discriminated.
That is, by performing the binarization process using the second threshold value, among the pixels included in the processing target region, the pixel having the luminance equal to or higher than the second threshold value has the luminance value set to the first luminance value (for example, the maximum gradation value). “255”) to become a pixel constituting the glossy region, and a pixel having a luminance less than the second threshold is converted into a second luminance value (for example, the minimum gradation value “−255”). The pixels that make up the work area.

  Then, the image processing device 3 determines whether or not the ratio of the glossy area in the processing target area is equal to or greater than a predetermined value (step S6). Here, if the processing target region is a glossy region, the ratio of the glossy region in the processing target region should be large. Conversely, if the processing target region is a work region, the glossy region in the processing target region The ratio should be small. That is, the predetermined value used for the ratio determination is set to a value that can be determined that the processing target area is a glossy area.

  If “Yes” in step S6, that is, if the ratio of the glossy area in the processing target area is equal to or greater than a predetermined value, the image processing apparatus 3 determines that the processing target area is a glossy area and selects it as the processing target area. The applied non-application area NSA is changed to the application area SA (step S7). Specifically, the image processing apparatus 3 converts the luminance of each pixel included in the non-application area NSA selected as the processing target area into a first luminance value (maximum gradation value “255”), thereby applying the application area. Change to SA.

  On the other hand, if “No” in step S4, that is, if the area of the processing target area is larger than a predetermined value (in other words, if the area is less likely to be a glossy area), the image processing apparatus 3 The processing target area is determined as a work area, and the process proceeds to step S9 described later (step S8). In this case, the non-application area NSA selected as the process target area is not changed to the application area SA, and is maintained as the non-application area NSA.

  If “No” in step S6, that is, if the ratio of the glossy area in the processing target area is less than a predetermined value, the image processing apparatus 3 determines that the processing target area is a work area and performs step S9 described later. (Step S8). Also in this case, the non-application area NSA selected as the processing target area is not changed to the application area SA and is maintained as the non-application area NSA.

  Then, after step S7 or S8, the image processing apparatus 3 determines whether there is another non-application area NSA surrounded by the application area SA (step S9). Returning to step S3, in the case of “No”, the process proceeds to step S10 described later. That is, the image processing device 3 is generated on the surface of the sealant S by performing the above-described steps S3 to S9 (second image processing) for all the non-application areas NSA surrounded by the application area SA. All the gloss areas corresponding to the gloss SL are included in the application area SA of the sealant S, and a final inspection image is created.

 FIG. 6 shows inspection images obtained by the first and second image processing. As can be seen by comparing FIG. 6 and FIG. 5, the non-application area NSA determined as the glossy area in the non-application area NSA surrounded by the application area SA is changed to the application area SA, and the sealant S An inspection image representing the application state of the original sealant S, which is not affected by the gloss SL generated on the surface, is obtained.

  Then, as the third image processing, the image processing device 3 reads the reference image 4b from the storage device 4, and compares the inspection image with the reference image 4b to determine whether or not the application state of the sealant S is normal. (Step S10: third image processing step). In such comparison and determination between the inspection image and the reference image 4b, for example, the area of the non-matching portion is obtained by superimposing the application areas SA of the sealant S extracted from the inspection image and the reference image 4b. A known pattern matching technique such as determination based on the area, measurement of the distance between the contour line and the center line of the application region SA, and calculation of the degree of geometric mismatch can be used.

  If the image processing apparatus 3 determines “normal” in step S10, the image processing apparatus 3 outputs an inspection result indicating that the application state of the sealant S is normal (step S11), while determining “abnormal”. If so, an inspection result indicating that the application state of the sealant S is abnormal is output to the outside (step S12).

  As described above, according to the application state detection apparatus 1 in the present embodiment, it is possible to exclude the influence of the glossy SL that is generated on the surface of the sealant S due to the reflection of light, which has been a factor of the decrease in inspection accuracy in the past. (A gloss area corresponding to the gloss SL can be included in the application area SA of the sealant S), so that the inspection accuracy can be improved. In addition, the application state detection device 1 in the present embodiment does not require an illumination light source or a monochromatic light source that includes a conventional driving unit in order to exclude the influence of the gloss SL generated on the surface of the sealant S by image processing, It is possible to realize simplification and cost reduction of the apparatus.

  In the above-described embodiment, the sealant S is exemplified as the application to be inspected, but the present invention can be applied to other application. In addition, the present invention, for example, in order to prevent oil leakage at a joint part of a mechanical part, when inspecting the application state of a coating applied to the joint part, or a circuit board and a counter substrate that constitute a liquid crystal panel For bonding, it can be widely applied to the inspection of the application state of various application materials, such as when the application state of the application material applied to one substrate is inspected.

  DESCRIPTION OF SYMBOLS 1 ... Application state inspection apparatus, 2 ... Imaging device, 3 ... Image processing apparatus, 4 ... Memory | storage device, 4a ... Application state inspection program, 4b ... Reference | standard image, S ... Sealing agent (application | coating material), W ... Workpiece | work, SL, WL: Glossy, SA: Application area, NSA: Non-application area

Claims (12)

An application state inspection device for inspecting the application state of a coating applied to a workpiece,
An imaging device for photographing the coating portion of the coated material on the workpiece;
A photographed image obtained from the imaging device is divided into a coating area and a non-coating area of the coating material using a first threshold value, and the non-coating area surrounded by the coating area is selected as a processing target area. Then, it is determined whether the processing target area is a glossy area corresponding to gloss or a work area corresponding to the work surface by using the second threshold value, and when the glossy area is determined, the processing target area is selected as the processing target area. An image processing apparatus for changing the non-application area to the application area;
An application state inspection apparatus comprising:   The image processing apparatus determines whether the processing target area is the glossy area or the work area using the second threshold when the area of the processing target area is a predetermined value or less. The application state inspection apparatus according to claim 1, wherein when the area of the region is larger than a predetermined value, the processing target region is determined as the work region.   The image processing apparatus divides the processing target area into two parts, the glossy area and the work area, using the second threshold, and when the ratio of the glossy area in the processing target area is equal to or greater than a predetermined value, 3. The application state according to claim 1, wherein the processing target area is determined as the gloss area, and the processing target area is determined as the work area when a ratio of the gloss area is less than a predetermined value. Inspection device. A storage device for storing a reference image acquired in advance;
The said image processing apparatus determines whether the application | coating state of the said coating material is normal by comparing the said reference | standard image and the test | inspection image obtained by image processing. The application | coating state inspection apparatus as described in any one. An application state inspection method for inspecting the application state of a coating applied to a workpiece,
An imaging step of photographing the application part of the application on the workpiece;
A first image processing step of dividing the photographed image obtained by the imaging step into a coating region and a non-coating region of the coating using a first threshold;
The non-application area surrounded by the application area is selected as a process target area, and a second threshold value is used to determine whether the process target area is a gloss area corresponding to gloss or a work area corresponding to the workpiece surface. And, when it is determined that the gloss region, a second image processing step of changing the non-application region selected as the processing target region to the application region;
An application state inspection method comprising:   In the second image processing step, when the area of the processing target area is equal to or less than a predetermined value, the second threshold is used to determine whether the processing target area is the glossy area or the work area, 6. The application state inspection method according to claim 5, wherein when the area of the processing target area is larger than a predetermined value, the processing target area is determined as the work area.   In the second image processing step, when the processing target area is divided into the glossy area and the work area by using the second threshold, and the ratio of the glossy area in the processing target area is equal to or greater than a predetermined value. The processing target area is determined as the gloss area, and the processing target area is determined as the work area when the ratio of the gloss areas is less than a predetermined value. Coating state inspection method.   A third image processing step of determining whether or not the application state of the application is normal by comparing the inspection images obtained by the first and second image processing steps with a reference image acquired in advance. The coating state inspection method according to claim 5, wherein the coating state inspection method comprises: An application state inspection program used for inspecting the application state of a coating applied to a workpiece,
First image processing that divides a photographed image obtained from an imaging device that photographs the coating portion of the coating material on the workpiece into a coating region and a non-coating region of the coating material using a first threshold value; ,
The non-application area surrounded by the application area is selected as a process target area, and a second threshold value is used to determine whether the process target area is a gloss area corresponding to gloss or a work area corresponding to the workpiece surface. And, when it is determined that the gloss region, second image processing for changing the non-application region selected as the processing target region to the application region;
A computer-executable program for inspecting the application state.   As the second image processing, when the area of the processing target area is equal to or smaller than a predetermined value, the second threshold value is used to determine whether the processing target area is the glossy area or the work area, 10. The application state inspection program according to claim 9, wherein when the area of the processing target area is larger than a predetermined value, the computer executes a process of determining the processing target area as the work area.   As the second image processing, when the processing target area is divided into the glossy area and the work area by using the second threshold, and the ratio of the glossy area in the processing target area is a predetermined value or more. The computer is caused to execute a process of determining the processing target area as the glossy area, and determining the processing target area as the work area when a ratio of the glossy area is less than a predetermined value. Item 11. The application state inspection program according to Item 9 or 10.   A reference image is read from the storage device, and the inspection image obtained by the first and second image processing is compared with the reference image, thereby determining whether or not the application state of the application is normal. The application state inspection program according to any one of claims 9 to 11, wherein the image processing is executed by a computer.

Images