JP2006078300A - Flaw detection method of object by color image of the object - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To enhance the reliability of the flaw detection processing of a target of inspection. <P>SOLUTION: A color image that has been photographed as target of inspection is acquired. The specific region in the color image and the region adjacent to the periphery of the specific region are acquired. The size of a masked region, including the specific region, is altered corresponding to the color of the acquired adjacent region. Then, predetermined flaw detection processing is performed on regions other than the masked region. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a technique for detecting a defect of an inspection object using a color image.

  A printed circuit board for constituting an electronic circuit is provided with through holes for conduction between layers and insertion of components, and board holes for cutting and positioning of the printed circuit board. In such a printed circuit board, the thickness of the resist around the through hole varies greatly, and the color on the image obtained by photographing the printed circuit board may change. Therefore, when a printed circuit board is inspected by an image inspection apparatus, a region corresponding to a hole and a portion having a constant width around the hole is generally excluded from the inspection target in an image obtained by photographing the printed circuit board. (A region excluded from the inspection target is generally called a “mask region”).

Japanese Patent No. 2500961 Japanese Unexamined Patent Publication No. Hei 6-2878739 JP 11-316193 A JP 2002-259667 A

  However, if a region corresponding to a hole and a portion having a constant width around the hole is uniformly used as a mask region, a defect existing around the substrate hole that is not a through hole may not be detected. On the other hand, if only the area corresponding to the hole is used as a mask area, even a printed circuit board without a defect is mistakenly recognized as having a defect due to a color change that can be tolerated due to variations in resist thickness around the through hole. There is a risk. That is, there is a problem that when a color image obtained by imaging a printed circuit board is analyzed to detect a defect, the presence or absence of a defect is erroneously recognized.

  The above-described problem is not limited to the inspection by the image inspection apparatus for the printed circuit board, and is generally a problem common to the inspection using the color image of the inspection object.

  The present invention has been made to solve the above-described conventional problems, and it is an object of the present invention to improve the reliability of defect detection processing for an inspection object.

  In order to achieve at least a part of the above object, the method of the present invention is a method for detecting a defect of the inspection object using a color image obtained by photographing the inspection object, and (a) the color image Obtaining a specific area, (b) obtaining an adjacent area around the specific area, (c) setting a mask area including the specific area, and (d) the color image. And a step of performing a predetermined defect detection process for a region other than the mask region, wherein the size of the mask region is changed according to the color of the adjacent region.

  According to this configuration, since the size of the mask area is changed according to the color of the adjacent area, the reliability of the defect detection process for the inspection object can be improved.

  The mask area includes the specific area and a special processing area including the periphery of the specific area, and the method further includes a special processing area different from the predetermined defect detection processing for the special processing area. It is good also as a thing provided with the process of performing defect processing.

  According to this configuration, it is possible to detect a defect that appears in the mask region.

  The step (b) includes (b1) a step of acquiring a boundary region around the specific region, and (b2) when the color of the boundary region satisfies a predetermined condition, including the boundary region, from the boundary region And (b3) setting the size of the mask region to a predetermined size when the color of the boundary region does not satisfy the predetermined condition. It is good.

  According to this configuration, since the size of the mask area is changed according to the color of the adjacent area when the color of the boundary area does not satisfy a predetermined condition, the image processing amount of the adjacent area can be reduced.

  The predetermined condition is a condition that a pixel in a predetermined first color range exists in the boundary region, and the step (c) includes a second color in which the color of the pixel in the adjacent region is a predetermined color. A step of enlarging the mask area when outside the range may be included as compared with the case of being within the second color range.

  According to this configuration, the size of the mask region can be set more appropriately.

  The inspection object may be a printed board, and the specific area may be an area corresponding to a hole provided in the printed board.

  According to this configuration, the reliability of the defect detection process for the printed circuit board can be improved.

  Note that the present invention can be realized in various modes. For example, a defect detection method and apparatus for an inspection object, an image inspection method and apparatus using the detection result, and various methods or apparatuses thereof. The present invention can be realized in the form of a computer program for realizing the function, a recording medium recording the computer program, a data signal including the computer program and embodied in a carrier wave, and the like.

Next, the best mode for carrying out the present invention will be described in the following order based on examples.
A. First embodiment:
B. Second embodiment:
C. Variations:

A. First embodiment:
FIG. 1 is an explanatory diagram showing a configuration of a printed circuit board inspection apparatus 100 as an embodiment of the present invention. The printed circuit board inspection apparatus 100 includes a light source 20 for illuminating the printed circuit board PCB, an imaging unit 30 that captures an image of the printed circuit board PCB, and a computer 40 that controls the entire apparatus. An external storage device 50 that stores various data and computer programs is connected to the computer 40.

  The computer 40 has functions of an image acquisition unit 210, a hole region acquisition unit 220, an adjacent region acquisition unit 230, a special processing region setting unit 240, a special processing region inspection unit 250, and a non-mask region inspection unit 260. have. The functions of these units are realized by the computer 40 executing computer programs stored in the external storage device 50.

  FIG. 2 is an explanatory diagram showing a state of the printed circuit board PCB which is an inspection object. The printed circuit board PCB is provided with five through holes TH1 to TH5 and a substrate hole HL used for cutting the printed circuit board PCB. The surface of the printed circuit board PCB includes a silk print region RSG in which white characters are silk-printed on the substrate base, a gold plated region RGP on which gold plating is applied, a substrate base region RSB in which the substrate base is exposed, and a substrate base. It includes a base resist region RBR coated with a resist and a pattern resist region RPR coated with a resist on a copper wiring pattern. Of the region where the resist is applied on the copper wiring pattern, the periphery of the through hole TH5 is a thin resist region RTR with a thin resist.

  Generally, in the printed circuit board PCB, depending on the resist coating process, the thickness of the resist around the through hole becomes unstable, and the thickness of the peripheral resist may be different for each through hole. Therefore, even in the case of a printed circuit board PCB having no defect, an area where the resist is thin may occur around the through hole as shown in FIG. Therefore, the allowable range of the resist thickness around the through hole is set wider than that of the other region where the resist is applied, and the presence of a thin resist region such as the thin resist region RTR is allowed. It should be noted that the thin resist region RTR has a different color as will be described later due to variations in the thickness of the resist even if the printed circuit board has no defect. That is, the thin resist region RTR adjacent to the through hole is a region having a wider color tolerance range than other regions.

  FIG. 3 is a flowchart showing a procedure for detecting a defect of the printed circuit board PCB in the first embodiment. In step S100, the image acquisition unit 210 (FIG. 1) acquires a color image of the printed circuit board PCB from the imaging unit 30.

  In step S100, the image acquisition unit 210 executes a smoothing process (blurring process) on the acquired color image as necessary. In the smoothing process, various smoothing filters such as a median filter, a Gaussian filter, and a moving average can be used. By performing this smoothing process, unique pixels existing in the image data can be removed, so that image data with less dust (noise component) can be obtained. In addition, when the processing after step S200 is executed for an image acquired in advance, image data is read from the external storage device 50 (FIG. 1) in step S100.

  FIG. 4A is an explanatory diagram showing a state of a color image IM obtained by photographing the printed circuit board PCB (FIG. 2). The color image IM includes a black region BK, a white region WH, a gold region GL, a brown region BR, a dark green region GD, and a light green region GB. In the present specification, these image areas BK, WH, GL, BR, GD, and GB are collectively referred to as “color areas”.

  On the color image IM, the through holes TH1 to TH5 and the substrate hole HL are represented by a black region BK because the hole is formed in the substrate. The silk printing region RSG, the gold plating region RGP, and the substrate base region RSB are represented by a white region WH, a gold region GL, and a brown region BR, respectively, according to the color of the surface material. The base resist region RBR is represented by a dark green region GD since a green resist is applied to a brown substrate base, and the pattern resist region RPR is a base because a copper-colored copper wiring pattern is formed under the resist. It is represented by a bright green region GB having a luminance higher than that of the resist region RBR. The thin resist region RTR with a thin resist on the pattern is represented by a gold region GL because the color of the copper wiring appears.

  In the color image obtained by photographing the actual printed circuit board PCB, the boundary between the gold region GL corresponding to the thin resist region RTR and the bright green region GB corresponding to the surrounding pattern resist region RPR is clearly separated. Although not shown in FIG. 4A, for convenience of illustration, the golden region GL and the light green region GB are depicted as being separated as different color regions.

  In step S200 of FIG. 3, the hole area acquisition unit 220 acquires a hole area representing a hole provided in the printed circuit board PCB by extracting the black area BK in the color image IM. The black area BK can be extracted as an area where the luminance value of each pixel constituting the color image IM is equal to or less than a predetermined luminance threshold. The predetermined luminance threshold value used for extraction of the black region BK can be set by, for example, histogram analysis for luminance values.

  In this embodiment, the black area BK is extracted based on the luminance value of each pixel, but the black area BK can be extracted by other methods. The extraction of the black region BK is also performed by dividing the color image IM into a plurality of predetermined representative color regions including black, and extracting a region in which the representative color is black among the divided regions. be able to. The area division of the color image IM is, for example, a distance index value representing a distance in a predetermined color space between the color of each pixel of the color image IM and a plurality of representative colors, and the area of the representative color that minimizes the distance index value. This can be done by classifying each pixel. As this distance index value, for example, the Euclidean distance when the RGB color space is regarded as a three-dimensional Euclidean space, or the color difference ΔE in the L * a * b * space can be used. The area dividing method of the color image IM may be an area dividing method for classifying each pixel into a plurality of representative colors. For example, the area dividing method may be performed by the methods disclosed in Patent Document 3 and Patent Document 4 described above. it can.

  In this embodiment, the hole area is acquired by extracting the black area BK in the color image IM. However, the image area corresponding to the hole provided in the printed circuit board PCB is acquired by another method. Also good. For example, it is possible to acquire a hole region from the position and size of a hole included in design data (CAD data) used to form a through hole or a substrate hole. It is also possible to take an image of the printed circuit board PCB illuminated from the opposite surface of the imaging unit 30 and set a region where the brightness of the taken image is high as a hole region.

  FIG. 4B is an explanatory diagram showing the arrangement of hole regions acquired in step S200. As shown in FIG. 4B, by extracting the black region BK from the color image IM, the image regions SR1 to SR5 corresponding to the through holes TH1 to TH5 and the image region SR6 corresponding to the substrate hole HL are obtained. To be acquired. Each of the image regions SR1 to SR6 acquired in this way becomes a hole region.

  In step S300 of FIG. 3, the adjacent region acquisition unit 230 acquires adjacent regions adjacent to the hole regions SR1 to SR6. The adjacent area acquisition unit 230 performs an enlargement process for enlarging the hole areas SR1 to SR6 acquired in step S200 with a predetermined enlargement width (for example, 5 pixels). The area enlarged by the enlargement process becomes an adjacent area. As the enlargement width, in addition to a predetermined set value, a specified value input by the user, a set value calculated based on CAD data, or the like can be used. Moreover, it is good also as what sets an expansion width separately for every hole area | region.

  As the hole area enlargement process, any process can be applied as long as the area generated by the enlargement process includes the hole area and the generated area can be made larger than the hole area. As such processing, for example, when any of the eight neighborhoods of each pixel belongs to the hole region, the expansion processing for setting the pixel to belong to the hole region, or this expansion processing is performed by n (n is 1 or more N-stage expansion processing can be used. It is also possible to use a process of acquiring the contour of the hole region and enlarging the contour.

  FIG. 4C is an explanatory diagram showing a state of acquiring an adjacent region. The adjacent region acquisition unit 230 performs the enlargement process on the hole region SR1, and thereby the region ER1 is generated. The region (region ER1-region SR1) enlarged by this enlargement process becomes the adjacent region NR1 of the hole region SR1. Similarly, the areas NR2 to NR6 obtained by removing the hole areas SR2 to SR6 from the areas ER2 to ER6 generated by the enlargement process of the hole areas SR2 to SR6, that is, the areas NR2 to NR6 enlarged by the enlargement process are the hole areas SR2 to SR6. It becomes an adjacent area of SR6.

  In step S400 of FIG. 3, the special processing area setting unit 240 determines whether or not to set a special processing area for performing a special defect detection process according to the color of the pixel included in each adjacent area. Specifically, when a pixel of a predetermined color (in this embodiment, gold) exists in a region adjacent to a certain hole region, a special processing region is set around the hole region.

  FIG. 5 is an explanatory diagram showing how the special processing area is set. FIG. 5A shows a color image IM obtained by photographing the printed circuit board PCB (FIG. 2). Note that FIG. 5A and FIG. 4A are the same. FIG. 5B shows the arrangement of adjacent regions NR1 to NR6 and the color region to which these regions NR1 to NR6 belong. FIG. 5C shows the arrangement of the special processing areas PR2, PR3, PR5 set in step S400. In addition, the broken line drawn in FIG.5 (b) and FIG.5 (c) represents the boundary of the color area | region shown to Fig.5 (a).

  As shown in FIG. 5B, since the adjacent region NR1 of the hole region SR1 is included in the dark green region GD, there are no gold pixels in the adjacent region NR1. Therefore, no special processing area is set in the hole area SR1. On the other hand, the adjacent region NR2 of the hole region SR2 is included in the gold region GL. Therefore, a gold pixel exists in the adjacent region NR2, and a special processing region PR2 is set in the hole region SR2 (FIG. 5C). Similarly, special processing regions PR3 and PR5 are set in the hole regions SR3 and SR5 where the gold pixels exist in the adjacent regions NR3 and NR5. On the other hand, since there are no gold pixels in the adjacent regions NR4 and SR6, no special processing region is set in the hole regions SR4 and SR6.

  The special processing area is set by the enlargement process of the hole area in the same manner as the adjacent area. In the example of FIG. 5C, the special process area setting unit 240 performs the enlargement process of the hole area SR2. Then, the region PR2 enlarged by the enlargement process is set as a special processing region corresponding to the hole region SR2. The same applies to the other hole regions SR3 and SR5.

  In FIG. 5C, the special processing regions PR2, PR3, and PR5 are drawn larger than the adjacent regions NR2, NR3, and NR5, but the size relationship between the special processing regions and the adjacent regions can be arbitrarily set.

  In step S500 of FIG. 3, the special processing area inspection unit 250 detects a defect in each special processing area. Specifically, it is determined whether or not the color of the pixel in the special processing area is included in the allowable color range. If the color of all the pixels in the special processing area is within the allowable range, it is determined that the special processing area has no defect, and there is a pixel with a color outside the allowable range in the special processing area. Is determined to have a defect in the special processing area.

  FIG. 6 is an explanatory diagram showing a state of defect detection processing on the printed circuit board PCB having no defect in the special processing region. FIG. 6A shows the state of the special processing area of the printed circuit board PCB. FIG. 6B shows the color distribution of each pixel in the special processing region PR5 of the printed circuit board PCB. In FIG. 6B, for the convenience of illustration, the point representing the color of each pixel in a two-dimensional color space (hereinafter also referred to as “RB color space”) composed of two color components of an R component and a B component. Is drawn with black circles.

  As shown in FIG. 6A, in the printed circuit board PCB, the two special processing regions PR2 and PR3 corresponding to the two hole regions SR2 and SR3 are both included in the gold region GL. On the other hand, the special processing region PR5 corresponding to the hole region SR5 extends over two color regions, the gold region GL and the light green region GB. As described above, the boundary between these two color regions GL and GB is not clear in the color image obtained by photographing the actual printed circuit board PCB, so the pixel color in the special processing region PR5 is continuous from gold to light green. Changes. Therefore, as shown in FIG. 6B, a point representing the color of the pixel in the special processing region PR5 is a partial range XR (hereinafter referred to as RB color space) that spans the range representing green and the range representing gold. , Also called “real color range XR”).

  As shown in FIG. 6, when the colors of all the pixels in the special processing region PR5 belong to the actual color range XR, the special processing region inspection unit 250 determines that the special processing region PR5 has no defect. With respect to the other special processing regions PR2 and PR3, whether or not there is a defect is determined based on whether or not the color of the pixel in the special processing region is included in the actual color range set for each special processing region.

  In this embodiment, whether or not the color of each pixel in the special processing region PR5 belongs to the actual color range XR is generated in advance prior to the inspection of each substrate and stored in the external storage device 50. This is determined by referring to the uptable LUT. Here, the lookup table LUT is a value indicating whether or not an individual color belongs to the actual color range XR when an RGB value (also referred to as an “input point”) representing an individual color in the RGB color space is input. (For example, 1 if it belongs to the actual color range XR, 0 if it does not belong).

  The lookup table LUT is generated based on the color of each pixel in the special processing area of the master image (hereinafter also referred to as “real color”) using a master image that is a color image obtained by photographing a printed circuit board without defects. Is done. Specifically, the lookup table LUT generates a lookup table that outputs 0 for all input points, and changes the output value corresponding to the color of each pixel in the special processing area of the master image to 1. It is generated by doing. In this way, by rewriting the output value of the lookup table, the color range where the output value is 1 becomes the actual color range XR. After generation of the lookup table LUT, for each input point of the lookup table LUT, if any of the output values near the input point is 1, the output value corresponding to the input point is changed to 1. It is preferable to perform an expansion process. By performing this expansion process, it is possible to include in the actual color range XR colors that can exist on the printed circuit board PCB having no defect and that do not appear in the special processing area of the master image.

  The lookup table LUT in this embodiment outputs a value (real color flag) indicating whether or not the individual color belongs to the actual color range, but the output value of the lookup table is that the individual color is actual. Any value can be used as long as it can be determined whether or not it belongs to the color range. For example, it is also possible to use a value generated from a value (color number) indicating which color in the color space represents an area representing an individual color and an actual color flag as an output value of the lookup table.

  In this embodiment, it is determined by referring to the look-up table LUT whether or not the color of the pixel in the special processing area is included in the allowable color range, but other methods are used. Is also possible. For example, if an upper limit value and a lower limit value are set for each RGB component, and each RGB component value of the pixel in the special processing area is between the upper limit value and the lower limit value, the color of the pixel is acceptable. It is good also as what judges that it is the range.

  FIG. 7 is an explanatory diagram showing a state of defect detection processing in the printed circuit board PCB having a defect in the special processing region. As in FIG. 6, FIG. 7A shows the state of the special processing region of the printed circuit board PCB, and FIG. 7B shows the color distribution of each pixel in the special processing region PR5 of the printed circuit board PCB. Yes.

  In the example shown in FIG. 7A, there are two image areas DF1 and DF2 (also referred to as “defect image areas”) representing two defects in the special processing area PR5. These defect image areas DF1 and DF2 have colors different from those appearing in the special processing area PR5 of the printed circuit board PCB having no defect, as represented by the black triangle and the black square in FIG. 7B, respectively. is doing. As described above, in the printed circuit board PCB having a defect in the special processing region, the special processing region PR5 is represented by black triangles and black squares in addition to pixels of colors belonging to the actual color range XR represented by black circles. The pixel has a color that does not belong to the actual color range XR. Therefore, the special processing region inspection unit 250 determines that the special processing region PR5 is defective.

  In step S600 of FIG. 3, the non-mask area inspection unit 260 removes the special processing area and the hole area (these areas are collectively referred to as “mask area”) from the color image IM (the non-mask area). ) To detect the defects inside. Specifically, for example, an area outside the mask is divided into areas, and the presence / absence of a defect in the printed circuit board PCB is determined based on the position and shape of the representative color area on the area division result. In the area outside the mask, a special processing area having a wide color tolerance range is removed from the color image IM, so that it is possible to detect defects with high reliability by dividing the area.

  FIG. 8 is an explanatory diagram showing the result of performing the defect processing detection process on the printed circuit board PCB having no defect. In the comparative example in which no special processing region is set, as shown in FIG. 8A, the color of the thin resist region RTR becomes the gold region GL by dividing the region. Therefore, it is determined that the area where the resist that is originally green is applied is gold, and the thin resist area RTR is detected as a defect. On the other hand, in this embodiment, since a special defect detection process is performed for the thin resist region RTR, the thin resist region RTR is not detected as a defect.

  As described above, in this embodiment, an adjacent area is provided around the hole area, and the mask area including the hole area is enlarged when the specific color is included in the adjacent area. The possibility that the thin resist region RTR to be erroneously recognized as a defect can be reduced. Further, since the special processing area is provided around the hole area and the defect in the special processing area is detected, the defect existing around the hole area can be detected.

B. Second embodiment:
FIG. 9 is a flowchart showing a procedure for detecting a defect of the printed circuit board PCB in the second embodiment. The flowchart of FIG. 9 differs from the flowchart shown in FIG. 3 in that two steps S310 and S320 are added between steps S200 and S300. Others are the same as FIG.

  In step S310, the adjacent region acquisition unit 230 (FIG. 1) acquires the boundary region by the hole region enlargement process. In step S320, whether or not it is necessary to determine the setting of the special processing area using the adjacent area is determined according to the color of the boundary area.

  FIG. 10 is an explanatory diagram showing a state of setting an adjacent area using a boundary area. FIG. 10A shows the arrangement of the color areas in the vicinity of the two hole areas SR1 and SR3. The adjacent area acquisition unit 230 (FIG. 1) acquires the boundary areas TR1 and TR3 by the enlargement process of the hole areas SR1 and SR3. Then, when pixels of a predetermined color (for example, gold) exist in the boundary regions TR1 and TR3, it is determined that a special processing region needs to be set, and adjacent regions are set around the hole regions SR1 and SR3. The The same processing is performed for the other hole regions.

  FIG. 10B shows an arrangement of adjacent areas set using the boundary areas TR1 and TR3. In the example of FIG. 10, since no gold pixel exists in the boundary region TR1 (included in the dark green region GD), no adjacent region is set in the hole region SR1. On the other hand, since a gold pixel exists in the boundary region TR3 (included in the gold region GL), the adjacent region NR3 is set in the hole region SR3. As shown in FIG. 10B, the adjacent region NR3 is set to be larger than the boundary region TR3.

  As described above, in the second embodiment, the necessity for determining the setting of the special processing area is determined according to the color of the boundary area, and the special processing using the adjacent area only for the hole area that needs to be determined for the special processing area. By determining the presence / absence of area setting, the image processing amount of the adjacent area can be reduced.

C. Variations:
In addition, this invention is not restricted to the said Example and embodiment, It can implement in a various aspect in the range which does not deviate from the summary, For example, the following deformation | transformation is also possible.

C1. Modification 1:
In each of the above embodiments, the special processing area is set around the hole area, but a specific area other than the hole area can be extracted and the special processing area can be set around the specific area. In this case, the specific area can be acquired by extracting a specific color area generated by area division of the color image IM, acquiring the position and shape of the specific area from the CAD data, or the like. As the specific area, it is preferable to select an area having a predetermined color (for example, black) in the color image.

C2. Modification 2:
In each of the above embodiments, the necessity of the special processing area is determined depending on whether or not a pixel of a specific color is included in the adjacent area. In general, the necessity of the special processing area is determined according to the color of the adjacent area. Can be determined. Specifically, the special processing area can be set when the color of each pixel in the adjacent area in the predetermined color space is outside the predetermined color distribution range. Further, the special processing area may be set when the adjacent area extends over two or more representative color areas of a plurality of predetermined representative color areas. Here, the “representative color area” is an area on the image corresponding to each representative color generated from a color image by area division using a plurality of representative colors. In this case, whether or not the adjacent region extends over two or more representative color regions can be determined by performing region division of the color image in advance and determining whether or not the number of representative color regions included in the adjacent region is two or more. .

C3. Modification 3:
In each of the above embodiments, the special processing region inspection unit 250 (FIG. 1) performs the defect detection processing in the special processing region in step S500 of FIG. 3, but the defect detection processing in the special processing region is omitted. May be. That is, the mask area including the special processing area and the hole area is not subjected to the defect detection process, and the area outside the mask area is subjected to the defect detection process.

C4. Modification 4:
In each of the above embodiments, the mask area (= hole area + special processing area) is set according to the necessity of the special processing area determined for each hole area, but in general, according to the color of the adjacent area. It is sufficient if the size of the mask area can be changed. In this case, it is preferable that the mask area is set to be large when a pixel of a specific color is included in the adjacent area, and is set to be small when a pixel of a specific color is not included in the adjacent area.

C5. Modification 5:
In each of the embodiments described above, the special processing area is set using the hole area, but an area that satisfies a predetermined condition may be set as the special processing area regardless of the hole area. The region that satisfies the predetermined condition can be, for example, a region having a predetermined position or shape, or a region having a predetermined color around the hole region, such as a gold plating region RGP of the printed circuit board PCB.

C6. Modification 6:
The setting of the special processing area and the detection of the defect in the special processing area according to the present invention are not limited to the printed circuit board, but are arbitrary having image areas having different color tolerance ranges on the color image obtained by photographing the inspection object. It can be applied to defect detection of objects. For example, the present invention can be applied to defect detection of these inspection objects using color images obtained by photographing inspection objects such as semiconductor wafers with patterns and mechanical parts having complicated shapes.

BRIEF DESCRIPTION OF THE DRAWINGS Explanatory drawing which shows the structure of the printed circuit board inspection apparatus 100 as one Example of this invention. Explanatory drawing which shows the state of the surface of printed circuit board PCB. The flowchart which shows the procedure of the defect detection process of the printed circuit board PCB in 1st Example. Explanatory drawing which shows the mode of acquisition of an adjacent area | region. Explanatory drawing which shows the mode of the setting of a special process area | region. Explanatory drawing which shows the mode of the defect detection process in the printed circuit board without a defect in a special process area | region. Explanatory drawing which shows the mode of the defect detection process in the printed circuit board with a defect in a special process area | region. Explanatory drawing which shows the result of having performed the defect process detection process about the printed circuit board PCB without a defect. The flowchart which shows the procedure of the defect detection process of the printed circuit board PCB in 2nd Example. Explanatory drawing which shows the mode of the setting of the adjacent area | region using a boundary area | region.

Explanation of symbols

DESCRIPTION OF SYMBOLS 20 ... Light source 30 ... Imaging part 40 ... Computer 50 ... External storage device 100 ... Printed circuit board inspection apparatus 210 ... Image acquisition part 220 ... Hole area acquisition part 230 ... Adjacent area acquisition part 240 ... Special process area setting part 250 ... Special process area Inspection part 260 ... Outside mask area inspection part PCB ... Printed circuit board

Claims (6)

A method for detecting defects in the inspection object using a color image obtained by photographing the inspection object,
(A) obtaining a specific region in the color image;
(B) obtaining an adjacent region around the specific region;
(C) setting a mask region including the specific region;
(D) performing a predetermined defect detection process on an area other than the mask area in the color image;
With
The size of the mask area is changed according to the color of the adjacent area. The method of claim 1, comprising:
The mask area includes the specific area and a special processing area including the periphery of the specific area,
The method further includes a step of performing a special defect process different from the predetermined defect detection process for the special process region. The method according to claim 1 or 2, comprising:
The step (b)
(B1) obtaining a boundary region around the specific region;
(B2) obtaining the adjacent region that includes the boundary region and is larger than the boundary region when the color of the boundary region satisfies a predetermined condition;
(B3) a step of setting the size of the mask region to a predetermined size when the color of the boundary region does not satisfy the predetermined condition;
Including a method. The method of claim 3, comprising:
The predetermined condition is a condition that a pixel of a predetermined first color range exists in the boundary region,
The step (c) includes a step of enlarging the mask region when the color of a pixel in the adjacent region is outside a predetermined second color range than in the case of the second color range. Method. A method according to any one of claims 1 to 4, comprising
The method in which the inspection object is a printed circuit board, and the specific area is an area corresponding to a hole provided in the printed circuit board. An apparatus for detecting defects in the inspection object using a color image obtained by photographing the inspection object,
A specific area acquisition unit for acquiring a specific area in the color image;
An adjacent area acquisition unit for acquiring an adjacent area around the specific area;
A mask area setting unit for setting a mask area including the specific area;
An inspection area outside the mask area that performs a predetermined defect detection process for an area other than the mask area in the color image;
With
The apparatus, wherein a size of the mask area is changed according to a color of the adjacent area.

Images