JP5390754B2 - Appearance inspection method and apparatus using image processing - Google Patents

Description

  The present invention relates to an appearance inspection method by image processing for determining whether or not a foreign matter attached to an article formed of a light-transmitting material is a removable foreign matter and an apparatus therefor.

  In general, as shown in FIG. 9, the foreign matter F1 that adheres to the surface of the article B and can be removed, and the foreign matter F2 that is embedded inside the article B and cannot be removed, as shown in FIG. There is a foreign matter F3 that is partially embedded in the article B and cannot be removed. In the following, the state in which the foreign matter F1 adheres to the surface of the article B and can be removed is “foreign matter adhesion”, the state in which the entire foreign matter F2 is embedded in the article B and cannot be removed is “foreign matter mixed”, and the foreign matter F3 A state in which a part is embedded in the article B and cannot be removed is referred to as “foreign matter partial mixing”. Foreign matter contamination and foreign matter partial contamination cannot be removed from the foreign matters F2 and F3, and the quality of the article B is impaired. Therefore, disposal as a defective product is required.

  On the other hand, in the case of foreign matter adhesion, the foreign matter F1 can be easily removed by a brush or air blow, so it is necessary to distinguish it from a defective product so that it is not mistaken for a defective product. If it is mistaken that foreign matter is adhering to foreign matter, a so-called useless spring is generated in which a non-defective product is judged as a defective product and disposed, and the yield decreases.

  As a method of determining the presence or absence of a foreign substance using a grayscale image obtained by imaging the appearance of the article B, a differential value of a pixel in an inspection region is obtained, and the difference between the average value of the differential value (average differential value) and an appropriate threshold value is determined. Is known, and when the average differential value is larger than a threshold value, it is determined that a foreign substance exists (see, for example, Patent Document 1).

In the technique described in Patent Document 1, the threshold value applied to the average differential value is set in two stages in order to distinguish the foreign object from the marking, and the foreign object exists when the average differential value is equal to or smaller than the smaller threshold value. If the average differential value is larger than the larger threshold value, it is determined that foreign matter is present. If the average differential value is between both threshold values, it is determined that either foreign matter or marking is present.
JP-A-4-350546

  When the technique described in Patent Document 1 is adopted, it is possible to determine whether or not a foreign object is attached to the article using information included in the captured gray image. However, in an article formed of a light-transmitting material, a portion embedded in the article is included in the image, so it is impossible to distinguish foreign matter contamination or foreign matter portion contamination from foreign matter adhesion. As a result, it is not possible to prevent a useless spring caused by misidentifying it as a defective product even though foreign matter can be easily removed.

  By the way, when a grayscale image as shown in FIGS. 10A to 10C is obtained corresponding to foreign matter adhesion, foreign matter contamination, and foreign matter partial mixing, respectively, in the differential image, FIGS. 11A to 11C are used. As shown, all have differential values. On the other hand, in an edge image obtained by extracting pixels having a differential value equal to or greater than an appropriate threshold value from the differential image, as shown in FIGS. Edges are detected both in the case of foreign matter and foreign matter. Therefore, it is difficult to distinguish between foreign matter adhesion and foreign matter part mixture even using an edge image.

  The present invention has been made in view of the above-mentioned reasons, and the object thereof is that an article formed of a light-transmitting material has the whole or part of the foreign matter embedded therein or the foreign matter adheres to the surface. It is an object of the present invention to provide an appearance inspection method by image processing and an apparatus thereof that make it possible to discriminate whether or not.

The invention of claim 1 is an appearance inspection method in which an article formed of a light-transmitting material is imaged by an imaging means, and foreign matter is discriminated using a grayscale image obtained by imaging, which is obtained by imaging. In a binary image obtained by binarizing a grayscale image, a connected area having a pixel value corresponding to a foreign object and having a pixel number equal to or more than a specified number is set as a candidate area where the foreign object exists, and the center of gravity of the candidate area is set as the center. In addition , when extracting an edge from a grayscale image , an area set to surround the candidate area based on the width dimension of the candidate area is used as an inspection area, and a differential image obtained by differentiating the grayscale image in the inspection area is generated. , first for extracting an edge from the first threshold value or more pixels is a differential value defined as contour lines of the foreign matter to be exposed on the surface of the interior embedded foreign substances and articles of the article are extracted together No Di extraction process, the differential image, the second threshold value or more differential value was Tadashi boss as contour lines of the foreign object contour of the foreign matter to be exposed on the surface of the article is embedded in the inside of the extracted article is not extracted And performing a second edge extraction process for extracting an edge from the pixel, and the threshold used for the first edge extraction process is smaller than the threshold used for the second edge extraction process, and the first edge It is characterized in that it is determined as a foreign object that can be removed when the change between the length of the edge extracted by the extraction process and the length of the edge extracted by the second edge extraction process is equal to or less than a specified determination threshold value.

The invention of claim 2 is an appearance inspection method in which an article formed of a light transmissive material is imaged by an imaging means, and foreign matter is discriminated using a grayscale image obtained by imaging, which is obtained by imaging. In a binary image obtained by binarizing a grayscale image, a connected area having a pixel value corresponding to a foreign object and having a pixel number equal to or more than a specified number is set as a candidate area where the foreign object exists, and the center of gravity of the candidate area is set as the center. In addition, when extracting an edge from a grayscale image, a differential image is generated by differentiating the grayscale image in the inspection area, with the area excluding the inner area set inside the candidate area based on the width dimension of the candidate area as the inspection area. In the differential image, an edge is extracted from a pixel having a differential value equal to or higher than a first threshold value so that a contour line between the foreign matter embedded in the article and the foreign substance exposed on the surface of the article is extracted together. Extraction In the differential image, in the first edge extraction process, the contour of the foreign matter exposed on the surface of the article is extracted, and the second threshold defined so as not to extract the contour of the foreign matter embedded in the article performed from a differential value of pixels and the second edge extraction process for extracting an edge, threshold used for the first edge extraction process is a value smaller than the threshold value used for the second edge extracting process, the It is characterized in that it is determined as a foreign object that can be removed when a change between the edge length extracted by the first edge extraction process and the edge length extracted by the second edge extraction process is equal to or less than a prescribed determination threshold value .

The invention of claim 3 is an appearance inspection method in which an article formed of a light transmissive material is imaged by an imaging means, and foreign matter is discriminated using a grayscale image obtained by imaging, which is obtained by imaging. In a binary image obtained by binarizing a grayscale image, a connected area having a pixel value corresponding to a foreign object and having a pixel number equal to or more than a specified number is set as a candidate area where the foreign object exists, and the center of gravity of the candidate area is set as the center. An area excluding the inner area set around the center of gravity of the candidate area from the outer area set to surround the candidate area based on the width dimension of the candidate area and set inside the candidate area based on the width dimension of the candidate area was a test査領zone, when extracting the edge from grayscale image to generate a differential image obtained by differentiating the grayscale image of the examination region, the differential image, dew on the surface of the interior embedded foreign substances and articles of the article A first edge extraction process for extracting an edge from a pixel having a differential value equal to or higher than a first threshold value so that a contour line with a foreign object to be extracted is extracted, and the differential image exposes the surface of the article. A second edge extraction process for extracting an edge from a pixel having a differential value equal to or greater than a second threshold value so that the outline of the foreign object is extracted and the outline of the foreign object embedded in the article is not extracted. And the threshold value used for the first edge extraction process is smaller than the threshold value used for the second edge extraction process, and the edge length extracted by the first edge extraction process and the second edge extraction process It is characterized in that it is determined as a foreign substance that can be removed when a change in the extracted edge length is equal to or less than a specified determination threshold value .

According to a fourth aspect of the present invention, there is provided an imaging means for imaging an article formed of a light-transmitting material, a binarizing means for generating a binary image obtained by binarizing a grayscale image obtained by imaging, and a binary Candidate area extraction means for extracting a connected area having pixels corresponding to a foreign substance and having a pixel value corresponding to a foreign substance among the pixels of the image as a candidate area where the foreign substance exists, and center of gravity of the candidate area And from the outer area set to surround the candidate area based on the width dimension of the candidate area, the inner area set around the center of gravity of the candidate area and set inside the candidate area based on the width dimension of the candidate area is excluded and inspection area setting means to the inspection area an area, a differentiating means for generating a differential image which the grayscale image obtained by differentiating in the examination region, Oite the differential image, inside the implanted foreign object and the surface of the article of the article With exposed foreign matter A first edge extraction means for extracting a first edge of the pixel is the threshold or more differential value defined as Guo lines are extracted together, Oite the differential image, a foreign matter is exposed to the surface of the article An edge is extracted from an image having a differential value equal to or larger than a second threshold value set to a value larger than the first threshold value so that a contour line is extracted and a contour line of a foreign substance embedded in the article is not extracted. A foreign substance that can be removed when a change between the edge length extracted by the first edge extracting means and the edge length extracted by the second edge extracting means is equal to or less than a prescribed determination threshold value; And determining means for determining.

According to the configuration common to the inventions of claim 1, claim 2, and claim 3 , in the differential image, the contour lines of the foreign matter embedded in the article and the foreign matter exposed on the surface of the article are extracted together. A first edge extraction process for extracting an edge from a pixel having a differential value equal to or greater than a first threshold value defined as defined above, and a contour line of a foreign substance exposed on the surface of the article in the differential image to extract the inside of the article because they provided a second edge extraction process that extracts an edge from implanted have been the second pixel is the threshold or more differential value contours were regulations boss so as not to be extracted of foreign matter, the first edge In the extraction process, an edge including most of the outline of the foreign object is extracted regardless of whether the entire foreign substance or a part of the foreign object is embedded in the article, or the foreign object part or the foreign object attached to the surface. Articles in the second edge extraction process Edges including contour foreign materials exposed to the surface are extracted.

  That is, by comparing the lengths of the edges detected by the first edge extraction process and the edges extracted by the second edge extraction process, the extent to which foreign matter is embedded in the article can be understood. When the foreign object is completely embedded in the article, the edge corresponding to the outline of the foreign object is not extracted in the second edge extraction process, and when the foreign object adheres without being embedded in the article, the first When the difference in edge length obtained between the edge extraction process and the second edge extraction process is small and a part of the foreign matter is embedded in the article, the first edge extraction process and the second edge extraction process Thus, the difference in edge length obtained by the above becomes large.

  By using these properties, it is possible to determine whether or not a foreign object is removable by image processing, and it is possible to prevent useless springs that are treated as defective when a removable foreign object is attached. Can result in improved yield.

In addition, since the first edge extraction process and the second edge extraction process employ a method of comparing the magnitude of the differential value with the threshold value when extracting an edge, only the threshold value is changed. The edge extraction process and the second edge extraction process can be easily realized by only changing the threshold value and without substantially changing the processing contents. For example, when the first edge extraction process and the second edge extraction process are processed with different contents, the increase in the program size is suppressed, and after the differential operation, only the magnitude of the threshold value is compared. Since the load is light, an increase in processing load can be suppressed.

In particular, according to the configuration of the first aspect of the present invention, in a binary image obtained by binarizing a grayscale image obtained by imaging, a connected image having a pixel value corresponding to a foreign object and having a prescribed number of pixels or more. Since the area is set as a candidate area where a foreign object exists, and the center area of the candidate area is set to surround the candidate area based on the width dimension of the candidate area, the inspection area is set as the inspection area. Based on this, the inspection area is set to a limited area that includes candidate areas, and the possibility of including edges due to uneven illuminance or outlines of articles when extracting edges related to foreign objects can be reduced, and edges related to foreign objects can be extracted. The accuracy to do becomes high. Moreover, since the inspection area is limited to a narrow range, the number of pixels to be processed is limited, resulting in a reduction in processing load and an increase in processing speed.

According to the configuration of the invention of claim 2, in the binary image obtained by binarizing the grayscale image obtained by imaging, the connected region including the pixel value corresponding to the foreign substance and the number of pixels equal to or more than the prescribed number is provided. Candidates with foreign objects are candidates for which foreign objects exist, and areas that exclude the inner area that is centered on the center of gravity of the candidate areas and that are set inside the candidate areas based on the width dimensions of the candidate areas are used as inspection areas. An area that is limited to exclude a part of the candidate area based on the area is set as the inspection area, and the possibility of including an edge due to the influence of the surface condition of the foreign object can be reduced when extracting the edge related to the foreign object. The accuracy of extracting the edge near the contour of the foreign object is increased. In other words, the noise generated inside the foreign object can be removed.

According to the configuration of the invention of claim 3, in the binary image obtained by binarizing the grayscale image obtained by imaging, a connected region including pixels having a pixel value corresponding to a foreign object and a prescribed number of pixels or more is provided. A candidate area in which a foreign object exists, centered on the center of gravity of the candidate area, and centered on the center of gravity of the candidate area from the outer area set to surround the candidate area based on the width dimension of the candidate area, and the width dimension of the candidate area Since the area excluding the inner area set inside the candidate area based on the inspection area is set as the inspection area, the inspection area is set to an area limited to the outline of the candidate area based on the candidate area where the foreign substance exists , and the foreign object When extracting edges related to illuminance, it is possible to reduce the possibility of inclusion of edges due to uneven illuminance or the outline of the article, etc. Tsu accuracy of extracting di increases. In addition, since the inspection area is limited to a narrower range than that of the invention of claim 3, the processing load is further reduced and the processing speed is improved.

According to the configuration of the invention of claim 4, as in the invention of claim 1, it is possible to determine the portion of the foreign matter exposed on the surface of the article and the portion embedded in the article. Therefore, it is possible to prevent a useless spring that is treated as a defective product when a removable foreign matter adheres to the article, leading to an improvement in yield. Further, since the first edge extracting means and the second edge extracting means are substantially the same processing and only the threshold values to be compared are different, the first edge extracting means and the second edge extracting means The configuration can be shared and the configuration is simplified. Furthermore, by obtaining a candidate area where a foreign object exists using a binary image and setting the inspection area so as to surround the candidate area around the center of gravity of the candidate area and based on the width dimension of the candidate area, Is limited to the vicinity of the contour of the candidate area, so that the possibility of including edges due to illuminance unevenness or the contour of an article when extracting edges related to foreign objects can be reduced, and the inner shape of foreign objects can be ignored. In addition, the accuracy of extracting edges related to foreign matters is increased, and the processing load is reduced because the number of pixels to be processed is reduced, leading to an improvement in processing speed.

  As shown in FIG. 1, the present embodiment includes a TV camera 11 as an imaging unit that images the article B, and an illumination device 12 that illuminates the article B. The illuminating device 12 desirably uses a shadowless lamp (ring illumination) so that no shadow is formed on the surface of the article B. The article B is made of a light-transmitting material, and is not limited to a transparent synthetic resin molded product, but may be an opaque colored synthetic resin molded product as long as the surface has light-transmitting properties. Included in article B. For example, a synthetic resin molded product colored white is included in the light transmissive material. In addition to the synthetic resin material, the technical idea of the present invention can be applied to any article B having light transmittance such as a glass material.

  A grayscale image (digital image having a lightness value as a pixel value) obtained by the TV camera 11 is input to the image processing apparatus 2. The image processing apparatus 2 includes an interface 29 for capturing an image and an image storage unit 20 for storing an image. The grayscale image from the TV camera 11 is temporarily stored in the image storage unit 20. The image storage means 20 is also used for storing each image generated by processing to be described later. The image processing apparatus 2 is an apparatus mainly composed of a computer, and enables the following processing by executing an appropriate program.

  A processing target area is set in a range in which the article B is included in the grayscale image stored in the image storage unit 20. The processing target area can be manually set by displaying a grayscale image on the screen of the monitor device, but in this embodiment, by binarizing the grayscale image with an appropriate threshold, The processing target area is automatically extracted as the area including the article B by the target area extracting means 21 for separating the item B.

  That is, since the brightness of the article B and the background is different, binarization is performed by setting an appropriate threshold value, and a connected area having pixel values on the article B side (here, pixels adjacent to each pixel in the binary image are foreign objects). If a set of pixels having a pixel value corresponding to F) is extracted and the number of pixels in each connected region is evaluated, it is possible to determine whether the item is an article B or not. Therefore, the pixels in the region that can be regarded as the article B are rectangular or circular so as to surround the article B from the maximum and minimum coordinate values in the horizontal direction (X direction) and the vertical direction (Y direction). A processing target area can be set.

  When the processing target area is determined, feature extraction is performed inside the processing target area to determine the possibility of the presence or absence of foreign matter. In addition, an area in which a foreign object may exist is set as a candidate area. When a candidate area exists, an inspection area is set so as to surround the candidate area.

  For feature extraction, binarization means 22 for generating a binary image obtained by binarizing a grayscale image with an appropriate threshold value, and a pixel having a pixel value different from the background (article B) from the binary image and defined Candidate area extraction means 23 for extracting a connected area consisting of a plurality of pixels as a candidate area is used. The threshold value set in the binarizing means 22 is set so that the presence range of the foreign matter can be extracted regardless of whether the foreign matter F is embedded in or attached to the article B.

  That is, the article B and the foreign matter F are distinguished from each other by using the difference in brightness in the grayscale image caused by the difference in reflectance and transmittance between the article B and the foreign matter F. In addition, since the foreign matter F has a certain size in the image, the number of pixels in the connected region is evaluated, and when the number of pixels is equal to or greater than a prescribed threshold, the candidate that the foreign matter F exists in the connected region. Consider it an area.

  The function of combining the binarizing means 22 and the candidate area extracting means 23 is the same as the function of the target area extracting means 21, and basically a threshold for generating a binary image and a threshold for the number of pixels in the connected area. Are different, and the configuration can be made common. In other words, a common subroutine may be used in the program, and only numerical values for condition determination may be passed to the subroutine as arguments.

  When the candidate area is extracted by the candidate area extracting means 23, the inside of the candidate area is set as the inspection area, and the differentiation means 25 generates a differential image obtained by differentiating the grayscale image in the inspection area. The image processing apparatus 2 includes a first edge extraction unit 26 that extracts, from the differential image, an edge including an outline of the foreign matter F exposed on the surface of the article B and the foreign matter F embedded in the article B; Second edge extraction means 27 for extracting, from the differential image, an edge that includes the outline of the foreign matter F exposed on the surface of the article B and does not contain the outline of the foreign substance F embedded in the article B; Prepare. The first edge extraction unit 26 and the second edge extraction unit 27 perform the above-described process by applying an appropriate threshold value to the pixel value of the differential image.

  Now, it is assumed that the differential image is obtained in the form as shown in FIG. In the illustrated example, the region Dm in the vicinity of the contour line of the foreign substance F is described in an elliptical shape, but in practice, the differential value changes around the region Dm described in an elliptical shape according to the state of the foreign object F. For example, when attention is paid to the vicinity of both ends in the major axis direction of the ellipse shown in the figure, the differential value differs depending on the foreign matter adhesion (solid line), foreign matter contamination (broken line), and foreign matter partial contamination (one-dot chain line) as shown in FIG. Show the distribution. The foreign matter part mixing indicates a state in which the foreign matter F is exposed on the surface of the article B at the left end portion of the drawing and the foreign matter F is embedded in the article B at the right end portion. In short, since a change in brightness is large at a portion exposed from the article B, a large differential value is obtained, and since a change in brightness is relatively small at a portion embedded in the article B, the differential value is also small.

  If this is utilized, as shown in FIG. 2B, by applying appropriate threshold values Tha and Thb to the differential value, the part exposed on the surface of the article B and the part embedded therein And can be separated. Here, the threshold value Tha and the threshold value Thb are set as Tha> Thb. The threshold value Thb is a pixel whose differential value exceeds the threshold value Thb, and the outline of the foreign matter F exposed on the surface of the article B and the inside of the article B. Are set so as to include both the outline of the foreign substance F embedded in the. In addition, the threshold value Tha includes the contour line of the foreign matter F exposed on the surface of the article B in the pixel whose differential value exceeds the threshold value Tha, and the contour line of the foreign matter F embedded in the article B. Set so that is not included.

  In the first edge extraction means 26, an edge is extracted by subjecting a pixel having a differential value exceeding the threshold Thb to a thinning process with a pixel width of 1 pixel width. In addition, the second edge extraction unit 27 extracts edges by performing a thinning process for setting the pixel width to one pixel width for the pixels whose differential value exceeds the threshold value Tha. In addition to the process of extracting the center line, a well-known technique can be employed for the thinning process.

  In order to compare edge lengths, which will be described later, out of the pixels on the edge obtained by the first edge extraction unit 26, pixels exceeding the threshold value Tha set in the second edge extraction unit 27 are extracted by the second edge extraction. It is desirable that the pixel is extracted by means 27. That is, it is desirable that the second edge extraction unit 27 extracts pixels on the edge within the range of pixels on the edge obtained by the first edge extraction unit 26.

  The first edge extraction unit 26 and the second edge extraction unit 27 have different thresholds applied to the differential image, but the other processes are the same, so that both the edge extraction units 26 and 27 are common. This can be realized by using the subroutine and giving an argument as a threshold value to the subroutine. That is, compared with a case where both edge extraction means 26 and 27 perform processing of different contents, an increase in the program size is suppressed, and the differential value obtained by the differentiation means 25 is compared with the threshold value to be thinned. Therefore, high-speed processing can be expected since increase in processing load can be suppressed.

  As described above, the first edge extracting unit 26 can extract the edge corresponding to the contour line of the foreign matter F regardless of whether or not it is embedded in the article B, and the second edge extracting unit 27. Then, it is possible to extract only the edge corresponding to the contour line of the foreign matter F exposed on the surface of the article B. Therefore, both edges are extracted by both edge extraction means 26 and 27 when foreign matter is attached, and edges are extracted by the first edge extraction means 26 when foreign matter is mixed, but no edge is extracted by the second edge extraction means 27. become.

  By the way, in the case of foreign matter part mixing, the edges are extracted by both edge extracting means 26 and 27 as in the case of foreign matter adhesion. However, in the case where the foreign matter part is mixed, a part of the foreign matter F is exposed on the surface of the article B and a part thereof is embedded in the article B. Therefore, the length of the edge extracted by the first edge extracting means 26 On the other hand, the length of the edge extracted by the second edge extracting means 27 is shortened.

  3 to 5, for each case of foreign matter adhesion, foreign matter contamination, and foreign matter partial contamination, a grayscale image (each diagram (a)), an inspection region Dp set by the inspection region extraction means 24 (each diagram (b)). ), An example of an edge image (each figure (c)) obtained by the second edge extraction means 26 and an edge image (each figure (d)) obtained by the first edge extraction means 26. In each of the drawings (c) and (d), the edge is a white pixel in an actual edge image, but for the convenience of the drawing, black and white are reversed and shown. In addition, if the size of the foreign matter F is the same, the inspection area Dp has almost the same size regardless of foreign matter adhesion, foreign matter contamination, or foreign matter partial contamination.

  In this embodiment, by using the above-described properties, foreign matter adhesion, foreign matter contamination, and foreign matter partial contamination are distinguished. That is, a determination unit that obtains a difference between the lengths of the edges extracted by the first edge extraction unit 26 and the second edge extraction unit 27 and discriminates foreign matter adhesion, foreign matter contamination, and foreign matter partial contamination according to the difference value. 28 is provided.

  In the case of foreign matter adhesion, since there is no significant change in the edge length obtained by the first edge extraction means 26 and the second edge extraction means 27, the determination means 28 sets an appropriate threshold for the difference. If the difference is equal to or less than the threshold value, it is determined that the foreign matter F is attached to the surface of the article B.

  In addition, when foreign matter is mixed, a large change occurs in the edge length obtained by the first edge extracting unit 26 and the second edge extracting unit 27. Therefore, the determining unit 28 sets an appropriate threshold for the difference. If the difference is equal to or greater than the threshold, it is determined that the entire foreign matter F is mixed with foreign matter embedded in the article B.

  Furthermore, an appropriate range between the foreign matter adhesion and the foreign matter contamination may be determined as foreign matter partial contamination. However, since both foreign matter contamination and foreign matter contamination are disposed as defective products in which the foreign matter F cannot be removed from the article B, the determination means 28 does not particularly distinguish foreign matter contamination from foreign matter contamination, and only whether or not foreign matter is attached. You may make it discriminate | determine.

  The operation of this embodiment is summarized in FIG. First, the grayscale image imaged by the TV camera 11 which is an imaging means is stored in the image storage means 20, and a process target area is set (S1). Next, the binarization means 22 and the inspection area extraction means 24 perform feature extraction (binarization) to extract candidate areas, and further, the inspection area so as to include the outline of the foreign substance F based on the candidate areas Dp is set (S2).

  When the inspection area Dp is determined, the differential value of the pixels in the inspection area Dp is obtained by the differentiating means 25, and the threshold values Tha and Thb are respectively set by the first edge extracting means 26 and the second edge extracting means 27 for the differential value. An edge is obtained by applying (S3 to S5).

  In the operation example shown in FIG. 6, the edge is extracted by the second edge extracting unit 27 before the edge is extracted by the first edge extracting unit 26, and the edge is not detected by the second edge extracting unit 27. (S4), it is determined that foreign matter is mixed without waiting for the edge extraction by the first edge extraction means 26 (S9). The fact that no edge is extracted means that there is no connected area consisting of pixels having pixel values as edges in the image, or the number of pixels included in the connected area is equal to or less than a prescribed threshold.

  If an edge is extracted by the second edge extracting means 27, the edge is extracted by the first edge extracting means 26 (S5), and the edge pixels obtained by the both edge extracting means 26, 27 are extracted. A difference in number is obtained, and this difference is compared with a prescribed threshold value (reference value) (S6). In step S6, if the difference is equal to or smaller than the reference value, it is determined that foreign matter is attached (S7), and if the difference exceeds the reference value, it is determined that foreign matter is mixed (S8).

  In the above-described operation example, the edge extraction by the second edge extraction unit 27 precedes the edge extraction by the first edge extraction unit 26, and only the result of the edge extraction by the second edge extraction unit 27 is a foreign object. Judgment of contamination is made, but after the edge extraction by the first edge extraction means 26 and the second edge extraction means 27 is performed, the difference in edge length is compared with an appropriate threshold value to determine the contamination. It is also possible to do. Further, when the determination unit 28 determines foreign matter adhesion, foreign matter contamination, and foreign matter partial contamination using the change in the edge length, it is also possible to use the edge length ratio instead of the edge length difference.

  By the way, the inspection area setting means 24 sets the inspection area Dp from the candidate area in the following procedure. That is, when the candidate area extraction unit 23 extracts the candidate area Ds as shown in FIG. 7A, the inspection area setting unit 24 obtains the position of the center of gravity G of the candidate area Ds as shown in FIG. 7B. . Further, as shown in FIG. 7C, an elliptical inspection region Dp set so as to surround the candidate region Ds around the position of the center of gravity G is set. In order for the inspection region Dp to surround the candidate region Ds, the width dimensions Lx, Ly (difference between the maximum value and the minimum value in each direction) in the horizontal direction (X direction) and the vertical direction (Y direction) of the candidate region Ds are set. Then, an elliptical inspection region Dp having a major axis and a minor axis respectively set to values obtained by adding prescribed margin values α and β to the horizontal and vertical width dimensions Lx and Ly, respectively, is set. Note that the inspection region Dp may be circular depending on the setting described above. In the illustrated example, a circular or elliptical inspection region Dp is set, but a region having another shape such as a rectangular shape may be set.

  By setting the inspection region Dp as described above, it is possible to set the inspection region Dp with the periphery of the candidate region Ds as a boundary so as to surround the candidate region Ds in which the foreign substance F exists. Therefore, it is possible to reduce the possibility of including edges due to noise such as illuminance unevenness and the contour line of the article B when extracting the edge related to the foreign matter F, and as a result, the accuracy of extracting the edge related to the foreign matter F is improved. Get higher. Further, since the inspection area Dp is limited, the number of pixels to be differentiated by the differentiating means 25 is limited, the processing load is reduced, and the processing speed is improved.

  In the example illustrated in FIG. 7, the inspection region Dp is set so as to surround the candidate region Ds, but the inspection region Dp may be set so as to exclude a part of the candidate region Ds. That is, the inspection area setting means 24 sets the inner area Dt included inside the candidate area Ds with the center of the center of the candidate area Ds as shown in FIG. 8, and excludes the inside of the inner area Dt from the inspection area Dp. It is.

  The inner region Dt may be an elliptical region having a major axis and a minor axis, respectively, obtained by subtracting prescribed exclusion values γ and δ from the horizontal dimensions Lx and Ly of the candidate area Ds in the horizontal and vertical directions. it can. In short, a region excluding the elliptical inner region Dt whose major axis or minor axis is Lx-γ in the horizontal direction and Ly-δ in the vertical direction is used as the inspection region Dp to be processed. The inspection area Dp may be circular. Also, the inspection area Dp having another shape such as a rectangular shape can be set.

  In this way, by excluding a partial area inside the candidate area Ds from the inspection area Dp, an edge caused by the shape inside the foreign substance F is prevented from being detected, and as a result, noise generated inside the foreign substance F is removed. can do. The inner region Dt can be set only when there is no large unevenness in the contour line of the candidate region Ds, and when the boundary of the inner region Dt does not intersect the contour line of the candidate region Ds. .

  In the above-described example, the example in which the inspection region Dp is set so as to surround the candidate region Ds and the example in which a partial region inside the candidate region Ds is excluded from the inspection region Dp are shown. Dp may be set. That is, the outer region is set so as to surround the candidate region Ds, and a part inside the candidate region Ds can be excluded, and the region surrounded by the outer region and the inner region Ds can be set as the inspection region Dp.

  In short, centering on the center of gravity of the candidate region Ds, Lx + α in the horizontal direction and Ly + β in the vertical direction from the elliptical outer region (inspection region Dp) having a major axis or a minor axis to Lx−γ in the horizontal direction and Ly in the vertical direction. A region excluding the elliptical inner region Dt whose major axis or minor axis is −δ is used as the inspection region Dp to be processed.

  As is clear from the processing procedure described above, the necessary information in the candidate area Ds is information related to the contour line of the candidate area Ds. Therefore, if only the pixels near the contour line are extracted, foreign matter adhesion, foreign matter contamination, and foreign matter partial contamination are included. Can be distinguished. Therefore, when the inspection area setting unit 24 sets the area between the outer area and the inner area Dt as the inspection area Dp, it is possible to perform the subsequent processing by focusing only on the vicinity of the contour line of the foreign substance F. The influence can be greatly reduced, and the processing load can be greatly reduced.

  As described above, since foreign matter adhesion, foreign matter partial contamination, and foreign matter contamination can be distinguished by image processing, the foreign matter adhesion in which the removable foreign matter F adheres to the article B is treated as a defective product. It is possible to prevent the useless spring, which leads to an improvement in yield. The inspection region Dp is desirably set with the candidate region Ds as a reference as described above, but a wider region can be used as the inspection region Dp as long as the candidate region Ds is included.

It is a block diagram which shows embodiment of this invention. It is principle explanatory drawing same as the above. It is operation | movement explanatory drawing which shows the example of an image in the case of foreign material adhesion in the same as the above. It is operation | movement explanatory drawing which shows the example of an image in the case of a foreign material mixing in the same as the above. It is operation | movement explanatory drawing which shows the example of an image in the case of foreign material part mixing in the same as the above. It is operation | movement explanatory drawing which shows the process sequence same as the above. It is a figure which shows the example of a setting of the inspection area | region in the same as the above. It is a figure which shows the other example of a setting of the test | inspection area | region in the same as the above. It is a figure which shows the relationship between an article | item and a foreign material. It is a figure which shows the example of a grayscale image. It is a figure which shows the example of a differential image. It is a figure which shows the example of an edge image.

Explanation of symbols

11 TV camera (imaging means)
DESCRIPTION OF SYMBOLS 12 Illuminating device 20 Image storage means 21 Target area extraction means 22 Binarization means 23 Candidate area extraction means 24 Inspection area setting means 25 Differentiation means 26 First edge extraction means 27 Second edge extraction means 28 Determination means B Article Dp Inspection area Ds Candidate area Dt Inner area F Foreign object G Center of gravity

Claims (4)

An appearance inspection method in which an article formed of a light-transmitting material is imaged by an imaging means, and foreign matter is discriminated using a grayscale image obtained by imaging, and the grayscale image obtained by imaging is binarized In a binary image, a connected region having a pixel value corresponding to a foreign substance and having a pixel number equal to or greater than a specified number of pixels is set as a candidate region where the foreign matter exists, and the center of gravity of the candidate region is set as the center and the width of the candidate region is set. In order to extract edges from a grayscale image , an area set to surround the candidate area based on the candidate area is generated, and a differential image obtained by differentiating the grayscale image in the inspection area is generated and embedded in the article in the differential image. a first edge extraction process for extracting an edge from the pixel is been first threshold value or more differential value defined as foreign matter and outline of the foreign matter to be exposed on the surface of the article are extracted together, fine In the image, the edge from the second threshold value or more pixels is a differential value contours inside embedded foreign object contour line is extracted article foreign material exposed was regulations boss so that they are not extracted to the surface of the article The second edge extraction process to be extracted, and the threshold value used for the first edge extraction process is smaller than the threshold value used for the second edge extraction process, and the edge extracted by the first edge extraction process A visual inspection method based on image processing, wherein a foreign substance is determined to be removable when a change between the length of the edge and the length of the edge extracted by the second edge extraction processing is equal to or less than a prescribed determination threshold value. An appearance inspection method in which an article formed of a light-transmitting material is imaged by an imaging means, and foreign matter is discriminated using a grayscale image obtained by imaging, and the grayscale image obtained by imaging is binarized In a binary image, a connected region having a pixel value corresponding to a foreign substance and having a pixel number equal to or greater than a specified number of pixels is set as a candidate region where the foreign matter exists, and the center of gravity of the candidate region is set as the center and the width of the candidate region is set. Based on the region excluding the inner region set based on the candidate region based on the inspection region, and extracting the edge from the grayscale image, a differential image obtained by differentiating the grayscale image in the inspection region is generated. A first edge for extracting an edge from a pixel having a differential value equal to or greater than a first threshold value so that a contour line between the foreign matter embedded therein and the foreign matter exposed on the surface of the article is extracted together. The differential value is equal to or greater than a second threshold value that is defined so that the contour line of the foreign matter exposed on the surface of the article is extracted and the contour line of the foreign matter embedded in the article is not extracted in the extraction process and the differential image. A second edge extraction process for extracting an edge from the pixel, and the threshold used for the first edge extraction process is smaller than the threshold used for the second edge extraction process, and the first edge extraction process An appearance inspection method using image processing, wherein a foreign substance is determined to be removable when a change between the edge length extracted by the second edge extraction processing and the edge length extracted by the second edge extraction processing is equal to or less than a predetermined determination threshold value . An appearance inspection method in which an article formed of a light-transmitting material is imaged by an imaging means, and foreign matter is discriminated using a grayscale image obtained by imaging, and the grayscale image obtained by imaging is binarized In a binary image, a connected region having a pixel value corresponding to a foreign substance and having a pixel number equal to or greater than a specified number of pixels is set as a candidate region where the foreign matter exists, and the center of gravity of the candidate region is set as the center and the width of the candidate region is set. Based on the outer area set to surround the candidate area based on the center of gravity of the candidate area and excluding the inner area set inside the candidate area based on the width dimension of the candidate area, the gray area image When extracting an edge from the image, a differential image obtained by differentiating the grayscale image in the inspection area is generated, and in the differential image, the contour between the foreign matter embedded in the article and the foreign substance exposed on the surface of the article A first edge extraction process for extracting edges from pixels having a differential value equal to or greater than a first threshold value that is defined so as to be extracted, and a contour line of foreign matter exposed on the surface of the article is extracted in the differential image Second edge extraction processing for extracting an edge from a pixel having a differential value equal to or greater than a second threshold value so that the contour line of the foreign matter embedded in the article is not extracted, and the first edge The threshold value used for the extraction process is smaller than the threshold value used for the second edge extraction process, and the edge length extracted by the first edge extraction process and the edge length extracted by the second edge extraction process are A visual inspection method by image processing , characterized in that a foreign substance is determined to be removable when the change in the value is equal to or less than a prescribed determination threshold value . Imaging means for imaging an article formed of a light transmissive material, binarization means for generating a binary image obtained by binarizing a grayscale image obtained by imaging, and foreign matter among the pixels of the binary image Candidate area extracting means for extracting a connected area having a pixel value corresponding to the number of pixels equal to or more than a prescribed number as a candidate area where a foreign substance exists, and a width dimension of the candidate area centered on the center of gravity of the candidate area The inspection area is an area that is centered on the center of gravity of the candidate area from the outer area that is set to surround the candidate area based on the image and that excludes the inner area that is set inside the candidate area based on the width dimension of the candidate area. The area setting means, the differentiation means for generating a differential image obtained by differentiating the grayscale image in the inspection area, and the contour line between the foreign matter embedded in the article and the foreign substance exposed on the surface of the article are combined. Extract A first edge extracting means for extracting an edge from a pixel having a differential value equal to or greater than a first threshold value, and a differential image, wherein a contour line of a foreign substance exposed on the surface of the article is extracted in the article. A second edge extracting means for extracting an edge from an image having a differential value equal to or larger than a second threshold value set to a value larger than the first threshold value so that an outline of the embedded foreign matter is not extracted; Determining means for determining that the foreign matter can be removed when a change between the edge length extracted by the edge extracting means and the edge length extracted by the second edge extracting means is equal to or less than a predetermined determination threshold value. A visual inspection device using image processing as a feature.

Images