WO2012164654A1

WO2012164654A1 - Automatic inspection device and automatic inspection method for inspecting silk backing

Info

Publication number: WO2012164654A1
Application number: PCT/JP2011/062300
Authority: WO
Inventors: 昌年笹井
Original assignee: 株式会社メガトレード
Priority date: 2011-05-28
Filing date: 2011-05-28
Publication date: 2012-12-06
Also published as: JPWO2012164654A1

Abstract

[Problem] The objective of the present invention is to provide an automatic inspection device that is such that even if silk has a deviated position, the silk can be inspected with respect to the backing at which the silk was originally located. [Solution] An image is acquired of a printed substrate (8) that is the subject of inspection, and alignment is performed with respect to an image that eliminates silk (81) from a pre-recorded reference image. Also, the region of the silk (81) is extracted, and the post-moving region and original region of the silk are extracted. Also, the shape state of the silk (81) is inspected by means of a first inspection method for the post-moving region after position deviation, and is inspected by means of a second inspection method for the silk backing, which is the original region. Meanwhile, inspection is performed by means of a third inspection method for regions such as pads and wiring patterns. Also, at this time, inspection is performed on the basis of the color of the silk in the first inspection method, and on the basis of the color of a resist and substrate in the second inspection method.

Description

Automatic inspection device and automatic inspection method for inspecting silk substrate

The present invention relates to an automatic inspection apparatus that inspects the formation state of a printed circuit board.

Generally, pads, patterns, resists, silk, etc. on printed circuit boards are inspected by an automatic inspection device. When inspecting these pads, patterns, and the like, generally, an image is acquired from a printed circuit board that is an object to be inspected, and areas such as pads, patterns, resists, and silk are extracted from the brightness of the image. Each region is inspected using a unique inspection method or threshold value. At this time, for example, a method of inspecting with a low threshold value is used for silk because the positional deviation is large, while a method of inspecting with a strict threshold value is used for pads and patterns (Patent Document 1, etc.). ).

By the way, since the image of such a silk base cannot be obtained by a camera, it is impossible to inspect a resist or a pad formed under the silk. For this reason, conventionally, the base is not inspected, and when the silk is misaligned, there is no reference image for the base of the silk even in the area where the silk is based. I tried not to do the inspection.

JP 2003-086919 A

However, if the area where the silk was originally made is not inspected, there is a problem that the resist application state in the area cannot be inspected and the accuracy of the inspection is deteriorated.

Therefore, an object of the present invention is to provide an automatic inspection apparatus that can inspect even the base in the area where the silk originated even when the silk is misaligned.

That is, in order to solve the above-described problem, the present invention provides an image acquisition unit that acquires an image of a printed circuit board that is an inspection object, a reference image storage unit that stores a reference image, and an image acquired by the image acquisition unit. A silk area detecting means for detecting a silk area in the first embodiment, a first inspection means for inspecting a silk area detected by the silk area detecting means by a first inspection method, and a silk area detected by the silk area detecting means A second inspection means for inspecting a silk area in the reference image by a second inspection method, and an area other than the area to be inspected by the first inspection means and the second inspection means. A third inspection means for inspecting by a third inspection method different from the first inspection method and the second inspection method is provided.

If configured in this way, it is possible to inspect even the area where the silk was originally made, so that it is possible to inspect with high accuracy.

In such an invention, as a second inspection method, the inspection is performed based on whether or not the pixel is configured within a predetermined luminance width of the luminance of the resist or the substrate.

In this way, since silk is generally printed on a resist or base material, if inspection is performed based on the color of the resist or base material, it is possible to detect defects in the resist or base material. Become.

Furthermore, when the inspection is performed by the second inspection method, the inspection can be performed based on the brightness of the area around the area where the silk is originally formed.

In this way, for example, when a resist is applied on a pattern and silk is printed on the resist, the brightness around the silk also becomes RGB brightness in which the color of the pattern and the resist are mixed. Thus, if the inspection is performed based on the luminance of the surrounding area, it is possible to inspect the area where the silk is originally from with high accuracy.

According to the present invention, an image acquisition unit that acquires an image of a printed circuit board that is an inspection object, a reference image storage unit that stores a reference image, and a silk that detects a silk region in the image acquired by the image acquisition unit. An area detection means, a first inspection means for inspecting a silk area detected by the silk area detection means by a first inspection method, and an area other than the silk area detected by the silk area detection means, Second inspection means for inspecting a silk area in an image by the second inspection method, and areas other than the areas to be inspected by the first inspection means and the second inspection means, the first inspection method and the second Since the third inspection means for inspecting by the third inspection method different from the above inspection method is provided, it is possible to perform inspection with good inspection even for the area where the silk was originally formed.

Functional block diagram of an automatic inspection apparatus according to an embodiment of the present invention The figure which shows the state aligned by the 1st position alignment means in the form The figure which shows area | region A3 in which the variation | change_quantity of the luminance value in the same form is more than predetermined value, and area | region A1, A2 below predetermined value The figure which shows the state which aligns area | region A3 in which the variation | change_quantity of the luminance value in the same form is more than predetermined value The figure which shows the state which aligns area | region A1 in which the variation | change_quantity of the luminance value in the same form is below a predetermined value The figure which shows the test | inspection of the area | region after movement of the silk in the same form, and an original area Flow chart showing position correction processing of automatic inspection device Flowchart for generating reference data by automatic inspection device in the same form The flowchart which shows the process in the case of test | inspecting with the automatic test | inspection apparatus in the form

Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The automatic inspection apparatus 1 according to this embodiment can inspect the quality of the formation state of pads, wiring patterns, silk 81, resists, through holes, etc. formed on a printed circuit board 8. Image acquisition means 2 for acquiring eight images, reference image storage means 5 in which a reference image necessary for examination is stored in advance, and images acquired by the image acquisition means 2 among the images excluding silk. And positioning means 3 for positioning. Characteristically, after the registration of the image other than the silk with respect to the positioning means 3, the silk 81 area in the acquired image is extracted to detect the shift amount or area of the silk 81. The area detection means 6, the first inspection means 71 for inspecting the formation state of the shifted silk 81 (the area after movement in FIG. 6), and the original area of the silk 81 (the original area in the upper diagram of FIG. 6) A second inspection means 72 for inspecting the ground is also provided. Hereinafter, the automatic inspection apparatus 1 according to the present embodiment will be described in detail.

First, the image acquisition means 2 acquires the surface image from the printed circuit board 8 which is an inspection object. When acquiring a surface image from the printed circuit board 8, the surface image may be acquired by a gray scale, but if it is a gray scale, a pad area where metal is exposed, an area where a resist is applied on the pad, Luminance changes such as areas where resist is directly applied on the substrate are not clear. For this reason, the surface image of the printed circuit board 8 is preferably acquired by RGB. When the surface image of the printed circuit board 8 is acquired by the image acquisition means 2, light is emitted from an illumination device arranged obliquely above the printed circuit board 8, and the reflected light is reflected on the line sensor or the The image is acquired by the area sensor, and the image is temporarily stored in the image memory. Then, the difference between the image stored in the image memory and the image when the printed board 8 is not placed (for example, the image of the stage) is taken, and the image of only the printed board 8 is extracted.

On the other hand, the reference image storage means 5 stores an RGB image of the printed circuit board 8 serving as a reference in advance. Here, the “reference image” means an image of an inspection object that has been determined as a non-defective product by visual inspection or another inspection device in advance, or image data created from CAD data or the like. In the case where the reference image is stored in the reference image storage unit 5, at least an image having a resolution higher than the resolution used in the first alignment unit 31 and the second alignment unit 32 described later is stored. It is also preferable to store an image excluding the silk 81.

The alignment unit 3 includes a first alignment unit 31, a second alignment unit 32, and a third alignment unit 33. In addition to aligning the entire image of the printed circuit board 8, the printed circuit board 8 The silk 81 extracted from is aligned.

Among these, the first alignment means 31 aligns the image of the printed circuit board 8 acquired by the image acquisition means 2 in a rough state as shown in FIG. Specifically, the entire image of the printed circuit board 8 is made to correspond to the first resolution, which is a low resolution, while being shifted in the vertical direction, the horizontal direction, and the rotation direction, and the position where the degree of coincidence with the reference image becomes the maximum is correlated. (Fig. 2 (a)). Here, the case where the entire image of the printed circuit board 8 is aligned is illustrated, but when the alignment of the silk 81 is performed, an image corresponding to the luminance of the silk 81 is acquired and the same processing is performed. . Then, the image on the printed circuit board 8 is corrected in the vertical direction, the horizontal direction, and the rotation direction based on the position where the degree of coincidence is greatest. Next, an image of the printed circuit board 8 is extracted at a second resolution, which is higher than the first resolution, and the position in each of the vertical direction, the horizontal direction, and the rotation direction is similarly based on the image. The position where the degree of coincidence is maximized is calculated by cross-correlation. Then, based on the position, the image of the second resolution is corrected in the vertical direction, the horizontal direction, and the rotation direction (FIG. 2B). In the present embodiment, the first and second resolutions are roughly aligned. However, the overall alignment may be performed with a higher resolution image, or the first The entire alignment may be performed with only the resolution. In this way, the entire image is aligned with a relatively low resolution.

Next, the second alignment means 32 divides the image of the printed circuit board 8 aligned in a rough state into small regions (FIG. 3), and changes in luminance in the designated luminance region among the respective regions. Only a region with a large amount is extracted, and the regions are aligned independently. In general, the printed circuit board 8 has a large luminance change region such as a resist-only portion (A1) and a region (A2) consisting only of a wiring pattern and a pad portion, and the wiring pattern having a large luminance change. There is very little about the area | region which consists of the edge of this and the edge (A3) of a pad. For this reason, the entire calculation amount can be reduced by performing the alignment only for the region having a small ratio. Here, the wiring pattern and the pad portion of the printed circuit board 8 are also illustrated, but the present invention is also applied to the case where the silk 81 is aligned.

When it is detected whether or not the luminance change is large for each of the divided areas, the luminance information of each pixel in the divided area is output to the luminance change detecting means 4, where the luminance change amount is a predetermined threshold value. Is detected. When detecting the amount of change in luminance, as a first method, the luminance for each RGB of each pixel in the region is extracted, and the variance value is calculated. At this time, if the variance value is larger than a predetermined threshold value, it is determined that the region has a large change amount. Conversely, if the variance value of luminance in the region is smaller than the predetermined threshold value, Judged as “small area”. As the “region with a large amount of change”, for example, a region including a pad, a wiring pattern, or an edge of the silk 81 (A3) can be considered. As the “region with a small amount of change”, for example, a resist only A region, a substrate-only region, a central region of a pad or a wiring pattern, etc. can be considered (A1, A2). Here, although the variation in luminance is detected using the variance value, the width of the maximum luminance value and the minimum luminance value, or the number of pixels having a luminance value equal to or higher than the predetermined luminance value and the predetermined luminance value. The number of pixels having a luminance value equal to or lower than the luminance value may be used.

The second alignment means 32 extracts only the region determined as “a region having a large change amount” in this way, and performs alignment with the region of the reference image corresponding to the region. In this alignment, a portion having a specified luminance and a large luminance change (for example, an edge portion of a pad) is extracted from the extracted region, and a small region and a position of the reference image are extracted based on that portion. Match. Specifically, since the silk 81 generally has a large positional shift (see FIG. 6), a color (RGB) or luminance area excluding the silk is extracted, and the pixels of the extracted area are numbered vertically and horizontally. Inflating processing is performed for each pixel, and the inflated edge region (A4) as shown in FIG. 4 is extracted. On the other hand, for the corresponding region of the reference image, contour regions that have been inflated by the same method are extracted, and the position having the highest matching rate is cross-correlated while shifting in the vertical direction, the horizontal direction, and the rotational direction. calculate. Then, alignment in the vertical direction, the horizontal direction, and the rotation direction is performed from the position with the highest matching rate. These processes are performed independently only for the areas determined as “regions with a large amount of change”, and these processes are not performed for the areas determined as “regions with a small amount of change”.

Next, the third alignment means 33 performs an alignment process for an area determined as “an area with a small change amount”. The region determined to be the “region with a small amount of change” does not have a characteristic portion, and therefore cannot be aligned by the method such as the second alignment unit 32. Therefore, here, correction is performed using the position information corrected by the second alignment means 32. Specifically, if the region to be noticed is a “region with a small amount of change”, the closest “region with a large amount of change” is searched for, and correction information for the region (vertical correction, horizontal direction) And correction of the rotation direction). Then, the correction information is used to correct the area in the vertical direction, the horizontal direction, and the rotation direction. At this time, when using the correction information of one area having the largest change amount, the correction information of the area is used as it is, or when the correction information of the closest area and the next closest area is used, You may make it correct | amend using the average value of correction information. In FIG. 5, two “regions with a large amount of change” having different directions with respect to the region to be corrected are searched (regions surrounded by thick solid lines), and the vertical correction is performed based on the correction information of the regions. The correction in the horizontal direction and the correction in the rotation direction are performed.

The silk region detection means 6 first performs alignment for the entire image excluding the silk 81, and then the silk 81 region (that is, the region of the silk 81 that has been displaced, the upper diagram in FIG. 6) in the inspection object, The corresponding area of the silk 81 in the reference image (that is, the silk area before being displaced, the lower figure in FIG. 6) is detected, and the respective deviation amounts are detected. Specifically, first, the entire image excluding the silk 81 is aligned as described above, and then the image based on the luminance of the silk 81 is roughly aligned by the first alignment means 31. In addition, in the case of such rough alignment, alignment may be performed using a deviation amount that has already been calculated with a brightness other than the silk 81. Next, the image at the luminance of the silk 81 is divided into small rectangular areas by the second alignment means 32, and alignment is performed using an area having a large luminance change amount with the designated luminance (here, the luminance of the silk 81). . Then, the third alignment means 33 performs alignment of a rectangular area where the silk 81 does not exist with reference to the luminance of the silk 81. Here, the third alignment means 33 is used to align a rectangular area that does not include the silk 81, but the second alignment means 32 has a silk just outside the small rectangular area. When 81 exists, the silk 81 may enter inside the rectangular area depending on how the brightness of the silk 81 is taken. For this reason, alignment is also performed for a rectangular region that does not include the silk 81. And based on the brightness | luminance image of the silk 81 in this way, it aligns with the 3rd alignment means 33 from the 1st alignment means 31, and the vertical direction of the silk 81, a horizontal direction, The shift amount in the rotation direction is calculated, and the post-movement area and the original area of the silk 81 are detected. Here, for the sake of explanation, the area of the silk 81 that is displaced in the inspection object is referred to as a post-movement area, and the area of the silk 81 in the reference image of the silk 81 corresponding thereto is referred to as the original area. .

When inspecting the inspection object, the inspection means 7 determines whether each area aligned in this way is compared with the area of the reference image, and determines whether or not there are a plurality of defective pixels or a plurality of defective pixels in the area. The area that is being processed is output.

Here, when the area after the silk 81 is inspected is inspected by the first inspection means 71. In the first inspection means 71, for example, a luminance width corresponding to silk RGB luminance is stored in advance, and it is determined whether or not the pixel in the post-movement area is included in the luminance width. If the pixel in the post-movement area is not included in the luminance width, it is determined to be a “defective pixel”, and if the predetermined number of defective pixels are continuous, the area is determined as a defective location. Output as.

Further, in the other first inspection means 71, the quality of the silk 81 can be judged by comparing with the original area in the reference image. Specifically, when the movement amount of the silk 81 can be detected by cross-correlating the post-movement area and the original area, the pixel of the silk 81 in the inspection image is moved by the movement amount, and after the movement Whether or not there is a pixel having a luminance within a certain range from the luminance value of the pixel within a predetermined search distance in the reference image is determined with reference to the coordinates. When such a pixel exists, it is determined as a “good pixel”, and when such a pixel does not exist, it is determined as a “defective pixel”. Then, the same processing is performed for all the pixels, and when a predetermined number or more of defective pixels are continuous, the region is output as a “defective portion”.

On the other hand, since the base appears in the original area of the silk 81 that does not overlap with the post-movement area, it cannot be compared with the original area that is the area of the silk 81 in the reference image. Therefore, when the original area is inspected, the second inspection means 72 inspects it. In the second inspection unit 72, for example, the brightness of the resist or the base material is stored in advance, and it is determined whether or not the pixels of the original region are included within a predetermined brightness width in the brightness. Then, when the pixel of the original region in the inspection object is included in the luminance width, it is determined as “good pixel”, and when it is not included, it is determined as “defective pixel”. If a predetermined number or more of the defective pixels are continuous, the area is output as a “defective portion”.

The second inspection means 72 can also inspect based on luminance information around the original area. For example, the original area is inflated and the difference between the original areas is taken through to acquire an image around the original area. Then, the average luminance (RGB luminance) of the surrounding image is calculated, and when the pixels of the original area are included within a certain luminance width with respect to the average luminance, it is not included as “good pixel”. In this case, it is determined as “defective pixel”. When the predetermined number of defective pixels are continuous, the area can be output as a “defective location”.

Further, the areas other than the moved area and the original area of the silk 81 (that is, areas such as pads, wiring patterns, and resists) are different from the first inspection means 71 and the second inspection means 72. Inspection is performed by the third inspection means 73. In the third inspection means, for example, as shown in FIG. 6, the pixel value of the pixel within the predetermined search distance in the reference image with the position of the pixel of the aligned image as the reference (x, y) is used. From the above, it is determined whether or not there is a pixel having a luminance within a certain range. If such a pixel exists, it is determined as “good pixel”, and if such a pixel does not exist, “bad pixel” is determined. Judge that there is. Then, the same processing is performed for all the pixels, and when a predetermined number or more of defective pixels are continuous, the region is output as a “defective portion”. Here, the quality of each pixel is judged, but of course, areas such as pads, wiring patterns, and resists are extracted, and each area is inspected using its own inspection method and threshold. It may be.

Next, a method of aligning the inspection object in the automatic inspection apparatus 1 configured as described above will be described with reference to the flowchart of FIG.

First, when inspecting the printed circuit board 8 that is the inspection object, a case where the reference image is generated first will be described. When the reference image is generated, the printed circuit board 8 that is a non-defective inspection object is placed on the stage. The image acquisition means 2 acquires the image. At this time, an image of a stage for placing the printed circuit board 8 is acquired in advance, and an image consisting only of the printed circuit board 8 is acquired by taking a difference from the image of the stage (step S1).

Next, the acquired image is converted into a first resolution image having a low resolution, a reference image corresponding to the converted low resolution image is read out, and overall alignment is performed. In this alignment, the vertical cross-correlation is used to detect the vertical shift, the horizontal cross-correlation is used to detect the horizontal shift, and the image is rotated to rotate. The amount of deviation in the rotational direction is also detected by the cross-correlation of directions (when n = 1 in step S2). Then, based on these deviation amounts, the deviation of the image of the printed circuit board 8 as the inspection object is corrected (step S3).

Next, the image corrected at the first resolution is aligned at a second resolution that is relatively higher than the first resolution (step S4: No). Similarly, in the alignment at the second resolution, a reference image corresponding to the second resolution is read, and a vertical shift amount, a horizontal shift amount, and a rotational shift amount are detected by cross-correlation. (Step S2). Then, based on the detected deviation amount, the deviation amount of the image of the printed circuit board 8 as the inspection object is corrected (step S3).

Next, a division process is performed on the image of the inspection object aligned at the second resolution (step S5). Then, a luminance change amount indicating how much the luminance change of each pixel is in the area is obtained (step S6). When calculating this amount of change in luminance, the variance value of the luminance of each pixel in that region is obtained. If the variance value is equal to or greater than a predetermined threshold, it is determined that the region has a large amount of change, and on the contrary If the value is less than the predetermined threshold value, it is determined as “a region with a small amount of change” (step S7).

Next, an area determined to be the “region with a large amount of change” is extracted (step S7: Yes), and a portion with a large amount of change, such as an edge portion of the pad, is extracted from the region and inflated. (Steps S8 and S9). On the other hand, for the reference image corresponding to the region, the portion with a large amount of change is extracted and inflated, cross-correlation is performed for each image, and the degree of coincidence calculated by the cross-correlation is calculated. The amount of deviation is detected from the information of the high position (step S10), and the region of the inspection object is independently corrected (step S11).

On the other hand, when it is determined that the region is a region with a small amount of change (step S7: No), the closest region with a large amount of variation and the next region with a large amount of variation are extracted ( Step S13), the shift amounts in the vertical direction, the horizontal direction, and the rotation direction in each region are extracted. Then, the position of the region is corrected from the average value of the respective shift amounts (step S14).

Then, the same processing is performed on the plurality of printed circuit boards 8, and the luminance for each RGB is extracted for each pixel of the aligned image (step T1 in FIG. 8), and allowed for each pixel position. The brightness range to be determined is determined. When determining the luminance width, a dispersion value or standard deviation that is a variation in RGB luminance of pixels of the printed circuit board 8 that has read a plurality of sheets is obtained (step T2). The allowable range from the luminance is set large and stored as reference data for the pixel. When setting the permissible luminance width, the RGB luminance is converted into a polar coordinate system so that each luminance can be expressed by a distance r from the origin and an angle θ formed with a straight line passing through the origin (step T3). Then, the allowable luminance width is set by changing the distance r and the angle θ (step T4). If the allowable luminance width is set using the distance r and the angle θ in this way, the parameters are reduced and the hue (ratio of RGB luminance) is changed as compared with the case where the allowable luminance width is set in the orthogonal coordinate system. There is an advantage that only brightness and saturation can be changed without any change.

On the other hand, corresponding to the pixel, the search distance of the corresponding pixel of the printed circuit board 8 in the inspection object is stored as a table (step T5), and the pixel having the luminance within the allowable luminance width within the search distance from the position of the pixel. It is possible to check whether or not exists.

Next, processing in the case of inspecting the printed circuit board 8 to be inspected in a state where the reference image and the reference data are stored in this manner will be described with reference to FIGS.

In the case of inspecting the printed circuit board 8 to be inspected, similarly, the printed circuit board 8 is placed on the stage, and the image acquisition unit 2 acquires an image composed only of the printed circuit board 8. (Step S1).

Next, the acquired image is converted into an image of a first resolution which is a low resolution, and a reference image corresponding to the converted low resolution image is read out to cross-correlate in the vertical, horizontal and rotational directions. To correct the amount of deviation in each direction (steps S2 to S3). Similarly, the image corrected at the first resolution is aligned at a second resolution that is relatively higher than the first resolution (step S4, steps S2 to S3).

Next, the image of the inspection object aligned with such a rough image is divided (step S5), and the luminance change amount in the region is obtained to obtain “region with large change amount” and “change amount”. Are divided into “small regions” (steps S6 and S7).

Then, an area determined as “an area having a large change amount” is extracted (step S8), an area excluding silk color and luminance is extracted for the area, and the change amount of the pixel in the extracted area is extracted. A large portion is extracted and inflated (step S9), and a reference image corresponding to the region is also extracted for a portion with a large amount of change, inflated, and the amount of deviation is obtained by cross-correlating each image. Is detected (step S10). And the area | region of a test target object is correct | amended independently from the information of the position with the highest coincidence calculated by the cross correlation (step S11). For silk, an image corresponding to the brightness of the silk is extracted from the inspection image, and is aligned using the first alignment means 31 to the third alignment means 33 as in steps S1 to S11. The shift amount is calculated by comparing with the reference image, and the post-movement area and the original area are extracted based on the shift amount (step S12).

On the other hand, for the “region with a small amount of change”, the correction information of the “region with a large amount of change” in the vicinity is extracted, and the position of the “region with a small amount of change” is corrected based on the correction information (step S13, S14).

Next, after extracting the area and the original area after alignment and silk movement in this way, first, the post-movement area and the original area are inspected (step U1). When the post-movement area is inspected, as a first inspection method, it is determined whether or not the pixels in the post-movement area are configured with a luminance within a predetermined width of the silk (step U2), and the luminance within the predetermined width is determined. If it is configured, it is determined as “good pixel” (step U3), and if it is not configured, it is determined as “bad pixel” (step U4). If defective pixels are continuously present for a predetermined pixel or more, the region is output as a defective portion (step U5).

On the other hand, for the original area that does not overlap the post-movement area, as a second inspection method (step U6), it is determined whether or not the pixels in that area are included in the brightness within the predetermined width of the resist stored in advance. (Step U7), it is determined that the pixel is “good pixel” (step U8) if it is configured with a luminance within a predetermined width, and “bad pixel” if it is not configured (step U9). If defective pixels are continuously present for a predetermined pixel or more, the region is output as a defective portion (step U10).

Next, for the areas other than the moved area and the original area, as the third inspection method (step U11), the allowable luminance stored in advance from the position of the reference image corresponding to the position of each pixel of the inspection object. The width and the search distance are extracted (step U12), and it is checked whether or not there is a pixel having a luminance (luminance for each RGB) within the allowable luminance width within the search distance of the reference image (step U13). If such a pixel exists, it is determined as a “good pixel” (step U14), and if such a pixel does not exist, it is determined as a “defective pixel” (step U15). If a predetermined number or more of defective pixels are continuously present, a defective area is output (step U16).

As described above, according to the embodiment, the image acquisition unit 2 that acquires an image of the printed circuit board 8 that is the inspection target, the reference image storage unit 5 that stores the reference image, and the image acquisition unit 2 acquire the image. From the image and the reference image, a silk area detecting means 6 for detecting a silk area in the acquired image, and for the detected silk area, a first inspection means 71 for inspecting by a first inspection method, Since the area where the silk originated is provided with the second inspection means 71 for inspecting by the second inspection method, the area where the silk originated can also be inspected. The accuracy can be improved.

In addition, since the second inspection means 72 is configured to inspect depending on whether or not it is composed of pixels having a luminance within a predetermined luminance width with respect to the luminance of the resist or the base material, If inspection is performed based on the color of the substrate, it is possible to detect defects in the resist and the substrate.

In addition, when inspecting with the second inspection means, if the inspection is performed based on the brightness of the area around the area where the silk originated, the image is estimated from the surrounding area where the silk originated. Inspection accuracy can be improved.

Note that the present invention is not limited to the above-described embodiment, and can be implemented in various modes.

For example, in the above-described embodiment, the shift amount of the silk 81 is detected after the alignment is performed using the first alignment unit 31 to the third alignment unit 33. The displacement amount of the silk 81 may be roughly calculated by the displacement.

Furthermore, in the above embodiment, when the original area is inspected, the inspection is performed based on the color of the resist and the base material. However, when the wiring patterns exist on the left and right of the silk 81, the wiring pattern is A virtual region to be connected may be formed, and the virtual region may be inspected as a region where a resist is applied on the wiring pattern. In the case of forming such a virtual region, for example, a change point where the luminance changes at the outer edge of the silk 81 is detected, and a straight line or a curve connecting the change point and the change point is formed. Then, the inspection is performed by regarding the one of the straight line or the curve where the surrounding luminance is changing as the region constituted by the luminance.

Further, when inspecting the moved area of the silk 81 in the above embodiment, it is checked whether or not the pixels in the moved area are included in the luminance width corresponding to the RGB luminance of the silk, and the original area is inspected. In this case, it is determined whether or not the pixel of the original area is included within the predetermined luminance width of the resist or the base material, but the post-movement area and the original area can be inspected by other methods. . As a specific example, the center line of the silk 81 is extracted by thinning the silk 81, and the distance is calculated by comparing with the pixels of the center line of the silk 81 similarly thinned in the reference image. Based on this, a method for inspecting the post-movement area and the original area can be considered. In addition, as another method, the amount of displacement of the silk 81 is calculated by performing alignment using the first alignment unit 31 to the third alignment unit 33 and comparing with the reference image. Difference between images is performed. Then, by calculating the area of the portion where the difference is large, a method of inspecting the shift amount, the post-movement area, the original area, or the like can be used.

The present invention is used in the field of an automatic inspection device that inspects the formation state of a printed board, a liquid crystal substrate, a pattern or a character formed on the surface of an object.

DESCRIPTION OF SYMBOLS 1 ... Automatic inspection apparatus 2 ... Image acquisition means 3 ... Positioning means (31 1st positioning means, 32 2nd positioning means, 33 3rd positioning means)
4 ... Brightness change calculating means 5 ... Reference image storage means 6 ... Silk region detecting means 7 ... Inspection means 8 ... Printed circuit board 81 ... Silk

Claims

Image acquisition means for acquiring an image of a printed circuit board that is an inspection object;
Reference image storage means for storing a reference image;
A silk area detecting means for detecting a silk area in the image obtained by the image obtaining means;
A first inspection means for inspecting a silk area detected by the silk area detection means by a first inspection method;
A second inspection means for inspecting a silk area in a reference image by a second inspection method, other than the silk area detected by the silk area detection means;
Third inspection means for inspecting an area other than the area to be inspected by the first inspection means and the second inspection means by a third inspection method different from the first inspection method and the second inspection method; ,
An automatic inspection device characterized by comprising:
2. The automatic inspection according to claim 1, wherein the second inspection unit inspects whether or not the second inspection unit includes pixels having a luminance within a predetermined luminance width with respect to the luminance of the resist or the substrate. apparatus.
2. The automatic inspection apparatus according to claim 1, wherein the second inspection means performs an inspection based on the brightness of an area around the area where the silk was originally formed.
Obtaining an image of a printed circuit board that is an inspection object;
Detecting a silk region in the acquired image;
Inspecting the detected silk region with a first inspection method;
A step of inspecting a silk region in a reference image in a region other than the detected silk region by a second inspection method;
Inspecting a region other than the region to be inspected by the first inspection method and the second inspection method by a third inspection method different from the first inspection method and the second inspection method;
An automatic inspection method characterized by comprising:
5. The automatic inspection according to claim 4, wherein the second inspection method is configured to inspect whether or not a pixel having a luminance within a predetermined luminance width with respect to a luminance of a resist or a substrate is configured. Method.
5. The automatic inspection method according to claim 4, wherein the second inspection means performs an inspection based on a luminance of an area around the area where the silk is originally formed.