JP2017161333A - Defect inspection device, defect inspection program, and defect inspection method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technique that determines the type of defect occurring in workpiece more accurately.SOLUTION: According to an embodiment, the present invention comprises: a first image acquisition unit 101 for acquiring a first captured image of a workpiece that is captured by a first imaging method; a second image acquisition unit 103 for acquiring a second captured image of the workpiece that is captured by a second imaging method; a first defect detection unit 102 for detecting a first defect in the workpiece on the basis of the first captured image and classifying the type of defect; a second defect detection unit 104 for detecting a second defect in the workpiece on the basis of the second captured image and classifying the type of defect; and a defect integration unit 107 for integrating the first defect and the second defect as an integrated defect when the position of the first defect in the workpiece and the position of the second defect match, and determining the type of integrated defect on the basis of the type of first defect and the type of second defect.SELECTED DRAWING: Figure 2

Description

  Embodiments described herein relate generally to a technique for inspecting a defect generated in a workpiece.

  Conventionally, an inspection for detecting a defect is performed on a workpiece conveyed on a production line. According to this inspection, a defect is detected by applying a predetermined algorithm to a captured image obtained by capturing a workpiece, and if a plurality of types of defects to be detected are assumed, the detected defect classification is determined. Made.

  In addition, as a technique for detecting various types of defects, image data obtained by imaging an inspection object is subjected to defect inspection by each of a fine defect inspection unit, a binarization inspection unit, and an unevenness inspection unit, and inspected. A defect inspection apparatus that comprehensively determines defects of an inspection object is known (Patent Document 1).

JP-A-8-145907

  However, according to the above-described defect inspection apparatus, when a plurality of different types of defects are imaged, if similar images are obtained, they are determined as the same type of defect, and the type of detected defect is determined. However, there was a problem that sometimes was not performed accurately.

  Embodiments of the present invention are made to solve the above-described problems, and an object of the present invention is to provide a technique for more accurately determining the type of a defect generated in a workpiece.

  In order to solve the above-described problem, an embodiment of the present invention provides a first image acquisition unit that acquires, as a first captured image, a captured image of a work imaged by a predetermined first imaging method, and the first imaging method. A second image acquisition unit that acquires a captured image of the workpiece captured by a different second imaging method as a second captured image, and detects a defect of the workpiece as a first defect based on the first captured image. A first defect detection unit for classifying the type of the first defect, and a second defect detection for classifying the type of the second defect by detecting the defect of the workpiece as the second defect based on the second captured image. When the position of the first defect and the position of the second defect in the workpiece coincide with each other, the first defect and the second defect are integrated as an integrated defect, and the type of the integrated defect is set as the first defect. Type of defect and type of second defect And a defect integrating unit for determining based on.

It is the schematic which shows the production line in which the defect inspection apparatus which concerns on 1st Embodiment was integrated. It is a block diagram which shows the function structure of a defect inspection apparatus. It is a figure which shows a defect classification table. It is a figure which shows the detection defect table which concerns on 1st Embodiment. It is a figure which shows the defect integration table which concerns on 1st Embodiment. It is a flowchart which shows the operation | movement of the whole process of a defect inspection apparatus. It is a flowchart which shows operation | movement of a defect integration process. FIG. 2 is a schematic diagram showing two defects to be integrated. It is the schematic which shows the integrated defect. It is a figure which shows the detected defect table with which the defect which concerns on 1st Embodiment was integrated. It is the schematic which shows the production line in which the defect inspection apparatus which concerns on 2nd Embodiment was integrated. It is a figure which shows the detection defect table which concerns on 2nd Embodiment. It is a figure which shows the defect integration table which concerns on 2nd Embodiment. It is a figure which shows the detected defect table with which the defect which concerns on 2nd Embodiment was integrated.

  Embodiments of the present invention will be described below with reference to the drawings.

(First embodiment)
First, a production line in which the defect inspection apparatus according to the first embodiment is incorporated will be described. FIG. 1 is a schematic diagram showing a production line in which the defect inspection apparatus according to the first embodiment is incorporated.

  As shown in FIG. 1, the production line 9 incorporating the defect inspection apparatus 10 according to the first embodiment conveys a workpiece having a certain width in one direction from a manufacturing process to an evaluation process, In the manufacturing process, workpieces are continuously produced in the transport direction, defect inspection is performed in the inspection process, and defect evaluation based on the defect inspection is performed in the evaluation process. In the first embodiment, a transparent or translucent sheet-like film made of polyethylene or the like as a raw material is manufactured and transported as a workpiece.

  In the inspection process, the production line 9 is attached to a plurality of transport rolls 91 for transporting continuously manufactured films in the manufacturing process, at least one transport roll 91, and processes the rotational displacement amount of the transport roll 91. The rotary encoder 91a for detecting the position of the film, the camera 92 for imaging the film surface, the illumination 93 for illuminating the imaging range by the camera 92 from the back side, the camera 94 for imaging the surface of the workpiece, and the imaging range by the camera 94 from the back side Illumination lighting 95 is provided.

  The camera 92 and the camera 94 are both line scan cameras, and the camera 92 and the camera 94 are different from each other in that the camera 92 is rotated and tilted around the optical axis. In the following description, the imaging method using the camera 92 is referred to as a streak inspection imaging method, and the imaging method using the camera 94 is referred to as a transmission imaging method. Here, the streak indicates a scratch on the sheet extending in the conveyance direction.

  The captured images captured by the cameras 92 and 94 are two-dimensional images used for sheet inspection by the defect inspection apparatus 10, and defect evaluation based on inspection results by the defect inspection apparatus 10 is performed in the evaluation process. According to this defect evaluation, it is determined as a non-defective product or a defective product at every predetermined position interval in the workpiece conveyance direction.

  The defect inspection apparatus 10 includes a CPU (Central Processing Unit) 11, a memory 12, a storage device 13, a camera 92, a camera 94, and an external interface (I / F) 14 that communicates with the rotary encoder 91 a as hardware. The CPU 11 and the memory 12 cooperate to execute various functions, and the storage device 13 stores a later-described defect classification table, detected defect table, and defect integration table as data used for processing executed by the various functions.

  Next, the functional configuration and various tables of the defect inspection apparatus will be described. FIG. 2 is a block diagram showing a functional configuration of the defect inspection apparatus. FIG. 3 is a diagram showing a defect classification table. FIG. 4 is a diagram illustrating a detected defect table according to the first embodiment. FIG. 5 is a diagram illustrating a defect integration table according to the first embodiment.

  The defect inspection apparatus 10 functions as a first image acquisition unit 101, a first defect detection unit 102, a second image acquisition unit 103, a second defect detection unit 104, a position calculation unit 105, a defect recording unit 106, and a defect integration unit. 107. The first image acquisition unit 101 acquires a captured image captured by the camera 92. The first defect detection unit 102 performs defect detection and classification on the captured image acquired by the first image acquisition unit 101 based on the defect classification table. The second image acquisition unit 103 acquires a captured image captured by the camera 94. The second defect detection unit 104 performs defect detection and classification on the captured image acquired by the second image acquisition unit 103 based on the defect classification table. The position calculation unit 105 acquires the position of the sheet detected by the rotary encoder 91a, and based on the imaging position of the rotary encoder 91a, the camera 92, and the camera 94 from the sheet position, the first defect detection unit on the sheet 102, the position of the defect detected by the second defect detection unit 104 is calculated. Here, the position of the defect is the coordinate of the vertex having the smallest coordinate value among the vertices of the rectangle surrounding the defect, where the Y-coordinate value is 0 at the front end in the sheet conveyance direction and the X-coordinate value is 0 at one end in the width direction. Shown as a value. The defect recording unit 106 associates the defects detected by the first defect detection unit 102 and the second defect detection unit 104 with the defect positions calculated by the position calculation unit 105 and records them in the detection defect table. The defect integration unit 107 integrates two defects detected by the first defect detection unit 102 and the second defect detection unit 104 as one defect based on the defect integration table.

  As shown in FIG. 3, the defect classification table includes four sections, “dark strong”, “dark weak”, and “light weak”, which are densities set relative to the formation that is the density of the normal portion of the sheet. “,“ Mighty ”, a combination of“ Small ”and“ Large ”indicating the area of a region corresponding to these categories, and a defect type are associated with each other. The four divisions based on the density of the captured image are “dark”, “dark”, “bright”, and “bright” in order of decreasing density, and the pixel density of the captured image corresponds to each of these categories. If the pixel is within the group, the pixel is classified into a corresponding category, and pixels in the same segment are labeled and determined as an area belonging to the corresponding segment. The areas of these sections are determined to be “small” when the area, that is, the number of pixels belonging to the area is equal to or smaller than a preset threshold value, and are determined to be “large” when larger than the threshold value.

  As shown in FIG. 4, the detected defect table includes a “product ID” that uniquely indicates a sheet that is a workpiece, and a “defect” that uniquely indicates a defect detected by the first defect detection unit 102 or the second defect detection unit 104. “ID”, “imaging method” indicating the imaging method of the captured image in which the defect is detected, “X coordinate value” indicating the defect position in the sheet width direction, and “defect position in the sheet conveyance direction” “Y coordinate value”, “width” indicating the size of the defect in the sheet width direction, “length” indicating the size of the defect in the sheet conveyance direction, and the defects classified based on the defect classification table This is associated with “defect type” indicating the type. Here, “X coordinate value” is 0 at one end in the width direction of the sheet, and “Y coordinate value” is 0 at the leading end in the sheet conveyance direction. The width of the defect is the size of the rectangle surrounding the defect in the X direction, and the length of the defect is the size of the rectangle in the Y direction. “X coordinate value”, “Y coordinate value”, “width” and “length” indicate the area occupied by defects on the sheet.

  As shown in FIG. 5, the defect integration table includes “defect type by streak inspection imaging” indicating the type of defect classified by the first defect detection unit 102, and defect type classified by the second defect detection unit 104. Is associated with “integrated defect type” indicating the type of defect corresponding to the combination of these two defect types. In FIG. The corresponding integrated defect type is indicated. This kind of integrated defect includes a “burn defect” including a streak that has a strong tail on a gel-like defect and a “drip defect” that is a wide range of dirt particles. According to this defect integration table, when “defect type by streak imaging” is dark strong / large and “defect type by transmission imaging” is dark strong / large, it is determined as “liquid dripping defect”. Except for the case of “defect”, when “defect type by streak imaging” is dark or dark, and “defect type by transmission imaging” is dark or dark, it is determined as “burn defect”.

  Next, the overall operation of the defect inspection apparatus will be described. FIG. 6 is a flowchart showing the overall processing operation of the defect inspection apparatus. Note that this entire operation is repeatedly executed every predetermined time.

  As shown in FIG. 6, first, the first image acquisition unit 101 acquires a captured image captured by the camera 92 as a first captured image (S101), and the first defect detection unit 102 based on the defect classification table. It is determined whether or not there is a defect in the first captured image, that is, whether or not there is an area with pixels corresponding to any one of “dark strong”, “dark weak”, “light weak”, and “light strong”. (S102).

  If there is a defect in the first captured image (S102, YES), the position calculation unit 105 calculates the position of the detected defect (S103), and the defect recording unit 106 detects the “product ID” of the sheet and the first defect detection. “Defect ID” of the defect detected by the unit 102, “Imaging method” of the captured image acquired by the first image acquisition unit 101, “X coordinate value” and “Y coordinate value” as the position of the defect, The “width” and “length” as the size of the defect and the “defect type” determined by the first defect detection unit 102 are associated with each other and added to the detected defect table (S104).

  Next, the second image acquisition unit 103 acquires a captured image captured by the camera 94 as a second captured image (S105), and the second defect detection unit 104 converts the second captured image into a second captured image based on the defect classification table. It is determined whether there is a defect (S106).

  If there is a defect in the second captured image (S106, YES), the position calculation unit 105 calculates the position of the detected defect (S107), and the defect recording unit 106 detects the “product ID” of the sheet and the second defect detection. The “defect ID” of the defect detected by the unit 104, the “imaging method” of the captured image acquired by the second image acquisition unit 103, the “X coordinate value” and the “Y coordinate value” of the defect, and the “defect“ The “width” and “length” and the “defect type” determined by the second defect detection unit 104 are associated with each other and added to the detected defect table (S108).

  Thereafter, the defect integration unit 107 executes defect integration processing described later (S109), and the first image acquisition unit 101 acquires the first captured image again (S101).

  In the process of step S106, when the second captured image has no defect (S106, NO), the defect integration unit 107 executes the defect integration process (S109).

  In the process of step S102, when the first captured image is not defective (S102, NO), the second image acquisition unit 103 acquires the captured image captured by the camera 94 as the second captured image (S105).

  Next, the operation of defect integration processing will be described. FIG. 7 is a flowchart showing the operation of defect integration processing. FIG. 8 is a schematic diagram showing two defects to be integrated. FIG. 9 is a schematic diagram showing integrated defects. FIG. 10 is a diagram illustrating a detected defect table in which defects according to the first embodiment are integrated.

  As shown in FIG. 7, first, the defect integration unit 107 determines whether there is an unselected defect among the defects recorded in the detected defect table (S201).

  When there is an unselected defect (S201, YES), the defect integration unit 107 determines a defect with the smallest defect ID among unselected defects, that is, a defect detected first among unselected defects. Select (S202). After the selection, the defect integration unit 107 determines whether or not there is a defect whose imaging method is different from the selected defect in the detected defect table and at least a part of which overlaps with the rectangular area of the selected defect (S203). ).

  When there is a defect that at least partially overlaps the rectangular area of the selected defect (S203, YES), the defect integration unit 107 determines the type of the selected defect and the type of defect that overlaps this defect in the defect integration table. The type of integrated defect associated with each combination is referred to, and the type of defect selected in the detected defect table is changed to the type of integrated defect referenced (S204).

Further, the defect integration unit 107 changes the position and size of the selected defect based on the position and size of the selected defect and the overlapping defect in the detected defect table (S205). It is deleted (S206), and it is determined again whether there is an unselected defect among the defects recorded in the detected defect table (S201).

  Here, the change of the position and size of the defect and the deletion of the overlapping defect will be described with reference to FIGS. As shown in FIG. 8, when a defect with a defect ID of 1 in the detected defect table shown in FIG. 4 is selected and a defect with a defect ID of 2 overlaps with this defect, as shown in FIG. For one defect, change the position and size of the defect to the minimum rectangular position and size that surrounds the two defects. At this time, in the detected defect table, as shown in FIG. 10, the “imaging method”, “X coordinate value”, “width”, “length”, and “defect type” are changed for the defect having the defect ID of 1. The defect with defect ID 2 is deleted. Note that the “imaging method” is blank.

  In step S203, if there is no defect that overlaps at least a part of the selected defect rectangular area (S203, NO), the defect integration unit 107 again selects an unselected defect from the defects recorded in the detected defect table. It is determined whether or not there is a defect (S201).

  In step S201, when there is no unselected defect (S201, NO), the defect integration unit 107 ends the defect integration process.

  As described above, according to the defect integration process, the defect type is determined based on the combination of the defect types detected and classified in the captured images captured by the different imaging methods, so that the defect can be detected with higher accuracy. The type can be determined. Further, by deleting only one of the defects whose defect areas overlap each other, it is possible to prevent the originally one defect from being handled as a plurality of defects.

(Second Embodiment)
Next, a second embodiment that is different from the first embodiment in the type of workpiece and the imaging method will be described. First, a production line incorporating the defect inspection apparatus according to the second embodiment will be described. FIG. 11 is a schematic view showing a production line in which the defect inspection apparatus according to the second embodiment is incorporated.

  In 2nd Embodiment, the metal sheet raw material which uses an alloy as a raw material is manufactured and conveyed as a workpiece | work. For this reason, in the inspection process, the production line 9a has a camera 92a that images the surface of the metal sheet material in order to inspect both surfaces of the non-permeable metal sheet material, and an illumination 93a that illuminates the imaging range of the camera 92a from the surface. It differs from the first embodiment in that it includes a camera 94a that images the back surface of the metal sheet material, and an illumination 95a that illuminates the imaging range of the camera 94a from the back surface. The camera 92a and the camera 94a are both line scan cameras. Hereinafter, the imaging method using the camera 92a is referred to as a front surface imaging method, and the imaging method using the camera 94a is referred to as a back surface imaging method. The hardware configuration and functional configuration of the defect inspection apparatus 10 are the same as those in the first embodiment.

  Next, a detected defect table and a defect integration table according to the second embodiment will be described. FIG. 12 is a diagram illustrating a detected defect table according to the second embodiment. FIG. 13 is a diagram illustrating a defect integration table according to the second embodiment. FIG. 14 is a diagram illustrating a detected defect table in which defects according to the second embodiment are integrated.

  In the second embodiment, since the type of workpiece and the imaging method in the inspection process are different, the detected defect table and the defect integration table stored in the storage device 13 of the defect inspection apparatus 10 are different. The defect classification table is the same as that in the first embodiment.

  As shown in FIG. 12, the fields in the detection defect table of the second embodiment are the same as those of the first embodiment, but the first embodiment is that the “imaging method” is set to front surface imaging or back surface imaging. Different from form. In the second embodiment, the captured image by the front surface imaging is acquired by the first image acquisition unit 101, and the captured image by the back surface imaging is acquired by the second image acquisition unit 103. Therefore, a defect whose “imaging method” is front surface imaging is a defect detected by the first defect detection unit 102, and a defect whose rear surface imaging is a defect detected by the second defect detection unit 104.

  Further, as shown in FIG. 13, the defect integration table of the second embodiment includes a “defect type by surface imaging” indicating the types of defects classified by the first defect detection unit 102, and a second defect detection unit 104. FIG. 13 associates “defect type by backside imaging” indicating the type of defect classified by the “integrated defect type” indicating the type of defect set for the combination of these two defect types. In FIG. 4, some combinations and types of integrated defects corresponding to these combinations are shown. The integrated defect types include depressions that are unevenness of metal sheet material due to impacts, etc., or “depressions / holes” that indicate through holes, and “depressions / holes (severity)” that indicate particularly large depressions or holes. . According to this defect integration table, when the “defect type by front surface imaging” is dark / large or bright / large and “defect type by back surface imaging” is dark / large or bright / large, Except when judged as “hole (severe)” and “depressed / hole (severe)”, “defect type by front imaging” is dark or bright regardless of size, and “defect by rear imaging” When the “type” is dark or bright regardless of the size, it is determined to be “concave / hole”.

  When the defect integration process based on the defect integration table shown in FIG. 13 is performed on the detected defect table shown in FIG. 12, as shown in FIG. Integrated as a “sink / hole (severe)” defect.

  As described above, by preparing various tables according to the type of workpiece and the imaging method, it is possible to determine the type of defect suitable for the type of workpiece and the imaging method.

  In the above-described embodiment, the defect detection program is described as being installed in advance in the above-described defect detection apparatus. However, the defect detection program in the present invention includes one stored in a storage medium. Here, the storage medium is a medium that is detachable from the defect detection device, such as a magnetic tape, a magnetic disk (such as a hard disk drive), an optical disk (such as a CD-ROM, a DVD disk), a magneto-optical disk (such as an MO), or a flash memory. Further, it refers to all media that can be read and executed by a computer as the above-described defect detection device, such as media that can be transmitted via a network.

  Although embodiments of the invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

  In the first and second embodiments, the defect type is determined for the combination of the defect classifications detected for the captured images obtained by the two different imaging methods, but three or more imaging methods are used. A defect type may be determined for each combination of defect classifications. In addition, although defect detection and classification are based on the density of the captured image, any information included in the captured image may be used for defect detection and classification. Moreover, the workpiece | work as a target which detects a defect is not restricted to the sheet-like member continuously produced with a fixed width | variety, What kind of shape may be sufficient. Moreover, although the 1st defect detection part and the 2nd defect detection part shall determine the classification | category of the detected defect based on the same defect classification table, it differs with a 1st defect detection part and a 2nd defect detection part. The defect classification may be determined based on the defect classification table.

DESCRIPTION OF SYMBOLS 10 Defect inspection apparatus, 101 1st image acquisition part, 102 1st defect detection part, 103 2nd image acquisition part, 104 2nd defect detection part, 107 Defect integration part

Claims (7)

A first image acquisition unit that acquires a captured image of a work imaged by a predetermined first imaging method as a first captured image;
A second image acquisition unit that acquires, as a second captured image, a captured image of the workpiece imaged by a second imaging method different from the first imaging method;
A first defect detector for detecting a defect of the workpiece as a first defect based on the first captured image and classifying the type of the first defect;
A second defect detector for detecting a defect of the workpiece as a second defect based on the second captured image and classifying the type of the second defect;
When the position of the first defect and the position of the second defect in the workpiece coincide with each other, the first defect and the second defect are integrated as an integrated defect, and the type of the integrated defect is set as the type of the first defect. And a defect integration unit that is determined based on the type of the second defect.   The defect integration unit integrates the first defect and the second defect when the first defect region and the second defect region partially overlap each other. Defect inspection equipment.   2. The defect integration unit, wherein the integrated defect type is a defect type set in advance for a combination of the first defect type and the second defect type. The defect inspection apparatus according to claim 2.   4. The type according to claim 1, wherein at least one of the first defect and the second defect is classified based on a preset concentration range. 5. Defect inspection equipment.   5. The defect inspection apparatus according to claim 4, wherein at least one of the first defect and the second defect is classified based on a size of a region belonging to the concentration range. Acquiring a captured image of a work imaged by a predetermined first imaging method as a first captured image;
Obtaining a captured image of the workpiece imaged by a second imaging method different from the first imaging method as a second captured image;
Detecting a defect of the workpiece as a first defect based on the first captured image and classifying the type of the first defect;
Detecting a defect of the workpiece as a second defect based on the second captured image and classifying the type of the second defect;
When the position of the first defect and the position of the second defect in the workpiece coincide with each other, the first defect and the second defect are integrated as an integrated defect, and the type of the integrated defect is set as the type of the first defect. And a defect inspection program for causing a computer to execute processing to be determined based on the type of the second defect. Computer
Acquiring a captured image of a work imaged by a predetermined first imaging method as a first captured image;
Obtaining a captured image of the workpiece imaged by a second imaging method different from the first imaging method as a second captured image;
Detecting a defect of the workpiece as a first defect based on the first captured image and classifying the type of the first defect;
Detecting a defect of the workpiece as a second defect based on the second captured image and classifying the type of the second defect;
When the position of the first defect and the position of the second defect in the workpiece coincide with each other, the first defect and the second defect are integrated as an integrated defect, and the type of the integrated defect is set as the type of the first defect. And a defect inspection method that is determined based on the type of the second defect.

Images