JP2006098093A - Substrate inspection device, substrate inspection method, inspection logic forming device of substrate inspection device and inspection logic forming method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a technique which enables the judgment of the quality of a solder fillet in a high-density mounting substrate with high-precision. <P>SOLUTION: The substrate inspection device is constituted so that a first pixel region of a bluish color is first extracted from an inspection image according to a first logic to judge whether the characteristic quantity possessed by the first pixel region satisfies a first judge condition. Next, a second pixel region of a reddish color is extracted from the inspection image according to a second logic by the substrate inspection device to judge whether the characteristic quantity possessed by the second pixel region satisfies a second judge condition. When both of the judge results of the first and second logics are real, a part to be inspected is judged to be a good product. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a technique for automatically generating inspection logic used in a substrate inspection apparatus.

  Conventionally, there has been proposed a board inspection apparatus for inspecting the mounting quality of a printed circuit board on which a large number of electronic components are mounted. In this type of printed circuit board, “the shape of the solder pile when the electrode part of the electronic component and the land are soldered” is called a solder fillet. However, depending on the wetting of the electrode part of the electronic component, a solder fillet is formed. In some cases, the electronic component and the solder fillet are not in contact with each other. Therefore, in order to inspect the soldering quality, it is necessary to accurately grasp the shape of the solder fillet made of a free curve.

  However, in the conventional board inspection apparatus, since monochrome (single color) single illumination is used as a light source, it is difficult to perform image analysis of the three-dimensional shape of the solder fillet. Therefore, the quality of soldering cannot be determined, and the board inspection apparatus cannot be used practically.

  In order to solve such a problem, the present applicant has proposed a substrate inspection apparatus of the type shown in FIG. 13 (see Patent Document 1). This method is called the three-color light source color highlight method (or simply the color highlight method), and is a technology that obtains the three-dimensional shape of the solder fillet as a pseudo-color image by illuminating the inspection object with light sources of multiple colors. is there.

  It is said that the practical use of automatic inspection of printed circuit boards is practically after the advent of this color highlighting technology. In particular, at the present time when electronic components are miniaturized, it is difficult to visually determine the solder fillet shape, and it can be said that board inspection cannot be realized without a color highlight type substrate inspection apparatus.

  As shown in FIG. 13, the color highlight type substrate inspection apparatus images a light projecting unit 105 that irradiates the inspection target 107 on the substrate 110 with the three primary color lights at different incident angles and the reflected light from the inspection target 107. An imaging unit 106. The light projecting unit 105 includes three annular light sources 111, 112, and 113 that have different diameters and that simultaneously emit red light, green light, and blue light based on a control signal from the control processing unit. Yes. The light sources 111, 112, and 113 are arranged in directions corresponding to different elevation angles when viewed from the inspection target 107 while being centered on the position directly above the inspection target 107.

  When the inspection target (solder fillet) 107 is irradiated by the light projecting unit 105 having such a configuration, light of a color corresponding to the inclination of the surface of the inspection target 107 enters the imaging unit 106. Therefore, as shown in FIG. 14, when the soldering of the electronic component is good / when the component is missing / when the solder is insufficient, the color pattern of the captured image depends on the shape of the solder fillet. A clear difference appears. This facilitates image analysis of the three-dimensional shape of the solder fillet, and makes it possible to accurately determine the presence / absence of electronic components and the quality of soldering.

In the color highlight type substrate inspection system, color parameters (color conditions) representing “the color of a good product that should be” and “the color of a defective product that should be” are set in advance, and the corresponding color parameter is selected from the inspection image. The color area to be extracted is extracted, and the quality is determined based on various feature amounts (for example, area and length) of the extracted area. Therefore, prior to the actual inspection, it is necessary to set the color parameters used for the inspection, the types of feature amounts, the determination conditions (for example, threshold values) for separating good products from defective products, and the like. The color parameters, feature amounts, and determination conditions are collectively referred to as inspection logic or inspection parameters, and setting and adjusting the inspection logic is generally referred to as teaching.

  In order to improve the inspection accuracy, it is important to set the color parameter so that a significant and clear difference appears between the feature quantity indicated by the non-defective product and the feature quantity indicated by the defective product. That is, it can be said that the quality of teaching of color parameters directly affects the inspection accuracy.

Therefore, as shown in FIG. 15, the present applicant has proposed a tool for supporting the setting of color parameters in the color highlight method (see Patent Document 2). In this tool, it is possible to set the upper limit value and the lower limit value of each of the hue ratios ROP, GOP, BOP and lightness data BRT of red, green, and blue as color parameters. The input screen of FIG. 15 is provided with a color parameter setting unit 127 for inputting color parameter setting values, and a setting range display unit 128 for displaying the color range extracted by each set color parameter. ing. The setting range display section 128 displays a hue diagram 134 showing all colors obtained under a predetermined brightness. When the operator sets the upper limit value and lower limit value of each color parameter, Displays a confirmation area 135 surrounding the color extracted by the set color parameter. When the binarization display button 129 is pressed, the extraction result based on the current color parameter is displayed as a binary image. According to this tool, the operator can track the color parameters until an appropriate extraction result is obtained while viewing the confirmation area 135 and the binary image.
Japanese Patent Laid-Open No. 2-78937 JP 9-145633 A

  The board inspection apparatus has an advantage that a plurality of inspection items can be inspected at high speed and accurately at once for the mounting quality of the printed board. However, in actual operation of the board inspection device, the over logic that teaches each inspection logic according to the individual inspection object, does not miss the defective product, and determines that the non-defective product is a defective product is an allowable value ( Judgment accuracy must be sufficiently increased until the value can be kept below the value assumed in advance.

  However, in the color highlight type substrate inspection apparatus, although advanced substrate inspection that can withstand practical use is possible, teaching to suppress oversight and overdetection of defective products to a target value is difficult. Even if the color parameter setting support tool described above is used, it is inevitable that the setting of a color parameter will depend on the experience and intuition of the operator. In addition, no matter how good the operator is, the adjustment must be repeated on a trial and error basis, which is inefficient and requires a lot of labor and adjustment time.

  In recent years, high-density mounting has progressed, and the distance between components has been narrowed. However, this has caused the following problems. For example, as shown in FIG. 16, when a large component 141 is present near the component to be inspected 140, light from the light source 113 having the largest incident angle (small elevation angle) among the three light sources 111, 112, and 113 (this example) The blue light is blocked by the component 141. Then, since the blue light does not hit the inspection target component 140, a color pattern that accurately reflects the solder fillet shape cannot be obtained.

In the upper part of FIG. 17, the shape (side view) of the solder fillet for each of the defective products (insufficient solder), non-defective products (those with blocked blue light), non-defective products (those without light shielding), and defective products (excessive solder). The color pattern (upper view) obtained by imaging each solder fillet is shown in the middle row. Normally, blue-colored areas tend to be large for good solder fillets, and blue-colored areas tend to be small for defective solder fillets, so only the blue-colored pixel areas are extracted as shown below. By comparing the size (area, length, etc.) of the pixel region, it is possible to determine whether the solder fillet is good or bad. However, in a solder fillet where blue light is blocked, even if it is a non-defective product, the blue-colored pixel area becomes very small and it is difficult to distinguish it from a defective product.

  FIG. 18 is a histogram of the areas of the blue color pixel regions of the non-defective product and the defective product. It can be seen that the frequency distribution of non-defective products blocked by blue light overlaps with the frequency distribution of defective products. In any inspection, the outflow of defective products is never allowed. Therefore, when it is difficult to separate defective products from non-defective products, the threshold is set as shown in FIG. 18 to allow the occurrence of over-detection. I must. However, this leads to frequent overdetection, which increases the loss cost of discarding a non-defective product as a defective product, and necessitates a re-inspection of the defective product by visual inspection.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a technique capable of accurately determining the quality of a solder fillet on a high-density mounting board.

  A further object of the present invention is to provide a technique capable of automatically generating parameters used in solder fillet inspection on a high-density mounting board.

  The board inspection apparatus according to the present invention performs solder fillet pass / fail judgment by the board inspection method described below.

  First, light of a plurality of colors is irradiated at different incident angles onto the inspection target component on the substrate by the light projecting means, and the reflected light is imaged by the imaging means to obtain an inspection image. The incident angle is an angle formed between light and the normal line of the substrate (the optical axis of the image pickup means), and the incident angle is smaller as the light from the light source has a larger elevation angle as viewed from the substrate (component). A color pattern corresponding to the inclination angle of the solder fillet appears in the solder portion of the inspection image.

  The board inspection apparatus has a storage unit for storing inspection logic. Specifically, the storage unit is good with respect to the first color condition for extracting the pixel including the color component of the light having the largest incident angle and the first feature amount of the pixel area that satisfies the first color condition. The first logic including the first determination condition set to a value that allows the overdetection of the defect and the oversight of the defective product to be permitted, and the second for extracting the pixel including the color component of the light having the smallest incident angle. Regarding the second feature amount of the pixel region that satisfies the color condition and the second color condition, the second feature condition includes a second determination condition that is set to a value that excludes overlooking of defective products that can be missed by the first logic. 2 logics are stored.

  When performing the solder fillet inspection, the first logic and the second logic are read from the storage unit.

  First, the first inspection means of the board inspection apparatus extracts a first pixel area satisfying the first color condition from the solder portion of the inspection image according to the first logic, and the first pixel area has the first pixel area. It is determined whether one feature amount satisfies the first determination condition.

Here, since the first color condition is to extract pixels including a color component of light having the largest incident angle, the first pixel region is large (wide) for non-defective products and small (narrow) for defective products. There is a tendency. Therefore, an amount representing the size of the pixel region may be employed as the first feature amount. For example, it is preferable that the number of lines having a number of pixels greater than or equal to a predetermined width among the lines constituting the first pixel region is the first feature amount. This feature amount can be said to reflect the size of the cluster of pixel regions. Further, the area (number of pixels) of the first pixel region may be used as the first feature amount.

  In a high-density mounting substrate, light having the largest incident angle may be blocked by other components. In that case, a correct color pattern cannot be obtained, and even if the product is a non-defective product, the first pixel area becomes as small as a defective product. However, since the first determination condition is set to a value that eliminates overdetection of a non-defective product, the determination result is always true for a non-defective product. Note that a defective product having a first pixel area having the same size as that of a non-defective product that is blocked by light having the largest incident angle is overlooked in the first logic (the determination result is true).

  Next, the second inspection means of the substrate inspection apparatus extracts a second pixel region that satisfies the second color condition from the solder portion of the inspection image according to the second logic, and the second pixel region has the second pixel region. It is determined whether the two feature amounts satisfy the second determination condition.

  Here, since the second color condition is to extract pixels including the color component of light having the smallest incident angle, the second pixel region is small (narrow) for non-defective products and large (wide) for defective products. There is a tendency. Accordingly, the second feature amount may be an amount that represents the size of the pixel region, similarly to the first feature amount. Note that there are various forms of solder defects such as no solder, insufficient solder, excessive solder, and the appearance of the second pixel region varies. Therefore, it is preferable to adopt the area (number of pixels) of the second pixel region as the second feature amount in that the same value can be obtained regardless of whether the constituent pixels of the second pixel region are solid or discrete. . Further, when the area is used, there is an advantage that the generation of the inspection logic (second determination condition) is simplified.

  The size of the second pixel region is not affected at all even if the light having the largest incident angle is blocked by other components. Therefore, it is possible to find a significant and clear difference in the second feature amount between a defective product that is overlooked by the first logic and a non-defective product that is blocked by light having the largest incident angle. In other words, it is possible to set the second determination condition to a value that excludes defective products that can be overlooked by the first logic, and if this second determination condition is used, at least a component that is determined to be non-defective in the first logic You can remove the defective products that you missed.

  Then, the determination means of the board inspection apparatus determines that the inspection target component is a non-defective product when the determination results of the first logic and the second logic are both true. As a result, even if the light having the largest incident angle is blocked by other parts, the non-defective product is determined to be non-defective and the oversight of the defective product is eliminated. An accurate pass / fail judgment can be realized.

  The inspection logic composed of the first logic and the second logic is automatically generated by the inspection logic generation device of the present invention. The inspection logic generation device includes an image acquisition unit, a first pixel region extraction unit, a first feature amount histogram generation unit, a first determination condition determination unit, a specific defective product image selection unit, a second pixel region extraction unit, and a second feature amount. A histogram generation unit, a second determination condition determination unit, and an inspection logic generation unit are included, and these functions are realized by a program of the information processing apparatus.

  In the inspection logic generation device of the present invention, first, the image acquisition means captures a plurality of non-defective images obtained by imaging components with good soldering and a plurality of defects obtained by imaging components with poor soldering. Acquire non-defective images.

Then, the first pixel region extracting means extracts the first pixel region from each of the non-defective product image and the defective product image using the first color condition for extracting the pixel including the color component of the light having the largest incident angle. The first feature quantity histogram generating means creates a first feature quantity histogram for the first feature quantity of each first pixel region, and the first determination condition determining means uses the first feature quantity histogram in the first feature quantity histogram. The first determination condition is determined so as to include all the frequency distributions of the non-defective images. As a result, it is possible to generate the first determination condition having a value that eliminates the overdetection of the non-defective product and allows the oversight of the defective product.

  Here, when “the number of lines having the number of pixels greater than or equal to a predetermined width among the lines constituting the first pixel region” is adopted as the first feature amount, the “width” and “number of lines” are determined by the following procedure. It is recommended to search for an optimal solution of “threshold value”.

  First, the first determination condition determining means arbitrarily sets the line width. Then, the first feature amount histogram generating unit is configured to create a first feature amount histogram for the number of lines having the number of pixels equal to or larger than the width in the first pixel region of each of the good product image and the defective product image, and the non-defective product image A threshold value is set smaller than the lower limit of the frequency distribution, and the degree of separation between the good product image and the defective product image based on the threshold value is calculated.

  The first determination condition determining means determines the width that maximizes the degree of separation by repeating the above-described series of search processes while changing the set value of “width”, and determines the determined “width” and “the width” The threshold value at “is used as the first determination condition. Thereby, the optimal solution of the first determination condition can be automatically obtained.

  As the degree of separation between the non-defective product image and the defective product image, various amounts can be adopted, but it is preferably an amount calculated based on the number of defective product images having a frequency exceeding the threshold value. If such a degree of separation is employed, the number of defective products that are missed by the first logic can be reduced, leading to an improvement in final determination accuracy. For example, the number of defective images having a frequency exceeding the threshold value may be simply adopted as the separation degree, or a function of the number may be used as the separation degree. In addition, the distance between the lower limit of the frequency distribution of good images and the upper limit of the frequency distribution of defective images below the threshold, the peak value of the frequency distribution of non-defective images, and the peak of the frequency distribution of defective images It is also preferable to consider the distance between the values.

  When the first determination condition is determined, the specific defective product image selection unit selects, as the specific defective product image, a frequency satisfying the first determination condition from the defective product images. That is, the specific defective product image corresponds to a defective product that can be overlooked in the first logic.

  Subsequently, the second pixel region extracting means uses the second color condition for extracting the pixel including the color component of the light having the smallest incident angle, and uses the second color condition to extract the second from each of the good product image and the specific defective product image. The pixel area is extracted, the second feature quantity histogram generating means creates a second feature quantity histogram for the second feature quantity of each second pixel area, and the second determination condition determining means is the second feature quantity. Based on the frequency distribution of the histogram, a second determination condition for separating the second feature quantity of the non-defective product image from the second feature quantity of the specific defective product image is determined. In this way, by limiting the teacher image serving as the reference for the second determination condition to the non-defective image and the specific defective product image, a value that eliminates the oversight of the defective product (specific defective product) that can be overlooked in the first logic. A second determination condition can be generated.

  Here, when the area of the second pixel region is adopted as the second feature amount, the above-described search process is not necessary, and the determination process of the second determination condition is simplified. As the second feature amount, “the number of lines having a pixel number equal to or larger than a predetermined width among the lines constituting the second pixel region” is adopted, and the “width” and “ It is also possible to search for the optimal solution of the “threshold number”.

  When the first and second determination conditions are determined, the inspection logic generation unit extracts a pixel area that satisfies the first color condition from an inspection image obtained by imaging the inspection target component, and the pixel area has First logic that determines whether or not the first feature amount satisfies the first determination condition, and a pixel region that satisfies the second color condition is extracted from the inspection image, and the second feature amount of the pixel region is The second logic for determining whether or not the second determination condition is satisfied, and when both the determination results of the first logic and the second logic are true, the inspection logic for determining the inspection target component as a non-defective product is generated. This inspection logic is passed to the board inspection apparatus and used for solder fillet inspection.

  The present invention can be understood as a substrate inspection method or inspection logic generation method of a substrate inspection apparatus including at least a part of the above processing, or a program for realizing such a method. The present invention can also be understood as a substrate inspection apparatus having at least a part of the means for performing the above-described processing or an inspection logic generation apparatus of the substrate inspection apparatus. Each of the above means and processes can be combined with each other as much as possible to constitute the present invention.

  According to the board inspection apparatus of the present invention, it is possible to determine the quality of the solder fillet on the high-density mounting board with high accuracy. Further, according to the inspection logic generation device of the present invention, parameters used in the substrate inspection device, in particular, inspection logic used in solder fillet inspection on a high-density mounting substrate can be automatically generated, and teaching work can be reduced. Teaching can be automated.

  Exemplary embodiments of the present invention will be described in detail below with reference to the drawings.

(Configuration of board inspection system)
FIG. 1 shows a hardware configuration of a board inspection system according to an embodiment of the present invention.

  The substrate inspection system includes a substrate inspection apparatus 1 that executes a substrate inspection process, and an inspection logic generation apparatus 2 that automatically generates inspection logic (parameters) used in the substrate inspection process of the substrate inspection apparatus 1. The board inspection apparatus 1 and the inspection logic generation apparatus 2 can exchange electronic data such as images and parameters via a wired or wireless network, or a recording medium such as an MO or a DVD. In the present embodiment, the board inspection apparatus 1 and the inspection logic generation apparatus 2 are configured separately, but the function of the inspection logic generation apparatus can be incorporated into the board inspection apparatus main body to be integrated.

(Configuration of board inspection equipment)
The board inspection apparatus 1 is an apparatus for automatically inspecting the mounting quality (soldering state, etc.) of the mounting component 21 on the board 20 by a color highlight method. The substrate inspection apparatus 1 generally includes an X stage 22, a Y stage 23, a light projecting unit 24, an imaging unit 25, and a control processing unit 26.

  Each of the X stage 22 and the Y stage 23 includes a motor (not shown) that operates based on a control signal from the control processing unit 26. By driving these motors, the X stage 22 moves the light projecting unit 24 and the imaging unit 25 in the X axis direction, and the Y stage 23 moves the conveyor 27 that supports the substrate 20 in the Y axis direction.

The light projecting unit 24 includes three annular light sources 28, 29, and 30 that have different diameters and that simultaneously emit red light, green light, and blue light based on a control signal from the control processing unit 26. . The light sources 28, 29, and 30 are arranged in directions corresponding to different elevation angles when centered on the position directly above the observation position and viewed from the observation position. With this arrangement, the light projecting unit 24 is connected to the substrate 20.
The upper mounting component 21 is irradiated with light of a plurality of colors (three colors of R, G, and B in this embodiment) at different incident angles.

  The imaging unit 25 is a color camera, and is positioned downward at a position directly above the observation position. As a result, the reflected light on the substrate surface is imaged by the imaging unit 25, converted into color signals R, G, and B of the three primary colors and supplied to the control processing unit 26.

  The control processing unit 26 includes an A / D conversion unit 33, an image processing unit 34, an inspection logic storage unit 35, a determination unit 36, an imaging controller 31, an XY stage controller 37, a memory 38, a control unit (CPU) 39, and a storage unit 32. , An input unit 40, a display unit 41, a printer 42, a communication I / F 43, and the like.

  The A / D conversion unit 33 is a circuit that receives the color signals R, G, and B from the imaging unit 25 and converts them into digital signals. The digital grayscale image data for each hue is transferred to the image data storage area in the memory 38.

  The imaging controller 31 is a circuit including an interface for connecting the control unit 39 to the light projecting unit 24 and the image capturing unit 25, and the light amount of each light source 28, 29, 30 of the light projecting unit 24 based on the output of the control unit 39. And control such as maintaining the mutual balance of the hue light outputs of the imaging unit 25 is performed.

  The XY stage controller 37 is a circuit including an interface for connecting the control unit 39 to the X stage 22 and the Y stage 23, and controls driving of the X stage 22 and the Y stage 23 based on the output of the control unit 39.

  The inspection logic storage unit 35 is a storage unit that stores inspection logic used for substrate inspection processing. The board inspection apparatus 1 can perform a plurality of types of inspection processes such as a fillet inspection for inspecting a solder shape and a lack inspection for inspecting a missing part. The inspection logic is prepared for each type of inspection, and includes color parameters (color conditions) for extracting a predetermined color pattern (pixel area) from the image, types of feature values extracted from the color pattern, Consists of pass / fail judgment conditions related to the feature amount.

  The image processing unit 34 performs a process of extracting a region satisfying the color parameter from an image obtained by imaging the component 21 on the substrate 20 and a process of calculating a predetermined feature amount from the extracted region. It is. The determination unit 36 is a circuit that receives the feature amount calculated by the image processing unit 34 and executes processing for determining whether the component mounting state is good or not based on whether or not the feature amount satisfies a predetermined determination condition.

  The input unit 40 includes a keyboard, a mouse, and the like necessary for inputting operation information and data related to the substrate 20. The input data is supplied to the control unit 39. The communication I / F 43 is for transmitting and receiving data to and from the inspection logic generation device 2 and other external devices.

  The control unit (CPU) 39 is a circuit that executes various arithmetic processes and control processes. The storage unit 32 is a storage device composed of a hard disk and a memory, and stores the CAD information of the substrate, the determination result of the substrate inspection process, and the like in addition to the program executed by the control unit 39.

FIG. 2 shows a functional configuration of the substrate inspection apparatus 1. The board inspection apparatus 1 includes an instruction information reception function 10, a board carry-in function 11, a CAD information reading function 12, a stage operation function 13, an imaging function 14, an inspection logic reading function 15, an inspection function 16, a determination result writing function 17, and a board. An unloading function 18 is provided. The inspection function 16 includes a solder region extraction function 16a, a first inspection function 16b, a second inspection function 16c, and a determination function 16d. These functions are realized by the control unit 39 controlling the hardware according to a program stored in the storage unit 32. In addition, a CAD information storage unit 32 a that stores CAD information and a determination result storage unit 32 b that stores determination results are provided inside the storage unit 32.

(Board inspection processing)
Next, substrate inspection processing in the substrate inspection apparatus 1 will be described. Here, a solder fillet inspection corresponding to a high-density mounting substrate will be described as an example of the substrate inspection processing. The solder fillet inspection is a process for determining whether or not the shape of the solder fillet is good.

  As shown in FIG. 3A, in a good solder fillet, a wide inclined surface like a mountain skirt is formed from the component 21 to the land on the substrate 20. On the other hand, when the solder shortage occurs, the area of the inclined surface is reduced. Conversely, when the solder is excessive, the solder fillet is raised on the land.

  When these solder fillets are imaged by the board inspection apparatus 1, images (color patterns) as shown in FIG. 3B are obtained. Since the red, green, and blue irradiation lights are incident on the solder fillet at different angles, the hue of the reflected light that is incident on the imaging unit 25 changes according to the inclination of the solder fillet. That is, the reflected light of the blue light having the shallowest incident angle is dominant in the steep portion, whereas the reflected light of the red light is dominant in the portion having almost no inclination.

  Therefore, normally, a non-defective solder fillet has a large blue-colored pixel area and a small red-colored pixel area, whereas a defective solder fillet has a small blue-colored pixel area and a red-colored pixel area. The pixel area becomes large. However, in a solder fillet in which blue light is blocked by other parts, even if it is a non-defective product, the blue-color pixel area becomes as small as a defective product (the red-color pixel area is not affected).

  In the fillet inspection according to the present embodiment, using such a tendency of the color pattern, a first logic that performs pass / fail determination based on the size of the blue region, and a second logic that performs pass / fail determination based on the size of the red region, By combining, fillet inspection compatible with high-density mounting is realized. Hereinafter, the flow of fillet inspection processing will be described in detail with reference to the flowchart of FIG.

  The instruction information receiving function 10 is in a waiting state until instruction information for instructing execution of substrate inspection is input (step S100; NO, step S101). When instruction information is input from an external device by operating the input unit 40 or via the communication I / F 43, the instruction information receiving function 10 receives the instruction information, the board carry-in function 11, the CAD information reading function 12, and the inspection logic. The data is sent to the reading function 15 (step S100; YES). The instruction information includes information (model number, etc.) of the board to be inspected.

  The inspection logic reading function 15 reads the inspection logic corresponding to the model number of the board from the inspection logic storage unit 35 (step S102). Here, the inspection logic for the fillet inspection is read.

The inspection logic of this embodiment is composed of a first logic and a second logic. The first logic includes a first color parameter (first color condition) for extracting a pixel including a light color component having the largest incident angle (that is, a blue color pixel), a width and a threshold value. A first determination condition is included. The second logic includes a second color parameter (second color condition) for extracting a pixel (that is, a red color pixel) including a light color component having the smallest incident angle, and a threshold value. Is included.

  Based on the instruction information, the board carry-in function 11 carries the board 20 to be inspected from the printed board carry-in section onto the conveyor 27 (step S103), and the CAD information reading function 12 receives the CAD information corresponding to the model number of the board. Read from the CAD information storage unit 32a (step S104).

  Next, the stage operation function 13 obtains information such as the dimensions, shape, and component arrangement of the substrate 20 from the read CAD information, and the plurality of components 21 mounted on the substrate 20 are sequentially observed positions (imaging positions). The X stage 22 and the Y stage 23 are operated via the XY stage controller 37 (step S105).

  On the other hand, the imaging function 14 causes the three light sources 28, 29, and 30 of the light projecting unit 24 to emit light via the imaging controller 31, and simultaneously irradiates red, green, and blue light onto the substrate 20. In addition, the imaging function 14 controls the imaging unit 25 via the imaging controller 31, and images the component 21 on the substrate 20 in synchronization with the operation of the stages 22 and 23 (step S106). The captured image is taken into the memory 38.

  In the inspection function 16, the solder area extraction function 16a extracts the solder area from the captured image by the image processing unit 34 (step S107). The extraction of the solder region can be automatically performed by template matching, for example.

  Subsequently, the first inspection function 16b extracts a first pixel area that satisfies the first color parameter from the extracted solder area according to the first logic (step S108). The first color parameter used here is composed of four values: a lower limit and an upper limit of blue saturation, and a lower limit and an upper limit of lightness. The first inspection function 16b converts pixels included in the color range defined by the first color parameter into white pixels and other pixels into black pixels by binarization processing. FIG. 3C shows the solder area after binarization. By binarizing with the first color parameter, it can be seen that only the first pixel area of the blue color in the solder area is extracted as a white pixel.

  Next, the first inspection function 16b extracts the feature amount of the first pixel region (white pixel region) in the image processing unit 34 (step S109). Here, as shown in FIG. 5, a line having the number of pixels equal to or greater than the width defined by the first determination condition (hereinafter referred to as “defined width”) among the lines constituting the first pixel region as the feature amount. (Hereinafter referred to as “specified width line number”). In the example of FIG. 5, feature quantities “4” are extracted from the first pixel area of the non-defective product, and “1” is extracted from the first pixel area of the defective product. This feature amount reflects the size of a cluster of pixel areas, and is suitable for distinguishing a blue color area in a non-defective image. In order to make the explanation easy to understand, an image of 10 × 10 pixels is illustrated in FIG. 5, but an image of about several tens × several tens to several hundreds × hundreds tens is used in an actual inspection.

  Next, the first inspection function 16b passes the specified width line number of the first pixel region to the determination unit 36, and the determination unit 36 includes the specified width line number of the first pixel region and the threshold included in the first determination condition. The value is compared (step S110). When the specified number of lines exceeds the threshold value, it is determined as “true”, and when it is equal to or less than the threshold value, it is determined as “false”. For example, if the threshold value is “3”, the determination result is “true” for the non-defective product in FIG. 5 and “false” for the defective product.

In the present embodiment, the specified width and threshold value of the first determination condition are preset to values that eliminate overdetection of non-defective products and allow oversight of defective products (a specific setting method will be described later). ). Technical common sense is that the judgment condition used for inspection is set to a value that allows overdetection of non-defective products and excludes oversight of defective products, but in the present embodiment, the opposite setting is used. ing. As a result, as shown in FIG. 3D, the determination result of the first logic is always “true” if it is a non-defective product regardless of the presence or absence of light shielding. Since the second defective product from the left has the first pixel area having the same size as the non-defective product with light shielding, the determination result is “true” and the defective product is overlooked. In order to eliminate this missed defective product, the image determined as “true” by the first logic is applied to the second logic (step S110; YES).

  The second inspection function 16c extracts a second pixel area that satisfies the second color parameter from the solder area according to the second logic (step S111). The second color parameter used here is composed of four values, a lower limit and an upper limit of red saturation and a lower limit and an upper limit of lightness. The second inspection function 16c converts the pixels included in the color range defined by the second color parameter into white pixels and the other pixels into black pixels by binarization processing. FIG. 3E shows the solder area after binarization. By binarizing with the second color parameter, it can be seen that only the second pixel area of the red color in the solder area is extracted as a white pixel.

  Next, in the second inspection function 16c, the image processing unit 34 extracts the feature amount of the second pixel area (white pixel area) (step S112). Here, the area value (number of pixels) of the second pixel region is calculated as the feature amount. Then, the second inspection function 16c passes the area value to the determination unit 36, and the determination unit 36 compares the area value of the second pixel region with the threshold value included in the second determination condition (step S113). When the area value is equal to or smaller than the threshold value, it is determined as “true”, and when it exceeds the threshold value, it is determined as “false”.

  In the present embodiment, the threshold value of the second determination condition is set in advance to a value that excludes overlooking of defective products that can be overlooked in the first logic (a specific setting method will be described later). As a result, as shown in FIG. 3F, the determination result is “true” for a non-defective product, and the determination result is “false” for a defective product that is missed by the first logic.

  The determination function 16d determines that the component to be inspected is “non-defective” when the determination results of the first logic and the second logic are both “true”, and “decision” when at least one of the determination results is “false”. It is determined as “defective product” (steps S114 and S115). The broken line in FIG. 3 represents an object to be determined as “good”.

  The determination result writing function 17 writes the determination result together with the location ID (information for specifying a part) in the determination result storage unit 32b (step S116).

  When all the components on the board 20 have been inspected, the board carry-out function 18 carries out the board 20 by the printed board carrying section, and the board inspection process is terminated (step S117).

  According to the board inspection processing described above, since the three-dimensional shape of the solder fillet can be accurately grasped by the color pattern appearing in the two-dimensional image, it is possible to accurately determine the quality of the solder mounting quality. Moreover, even if the blue light is blocked by other parts, the non-defective product is judged as a non-defective product and the oversight of the defective product is eliminated. can do.

  Next, a method for generating the above-described inspection logic will be described. In the present embodiment, the inspection logic is automatically generated by the inspection logic generation device 2.

(Configuration of inspection logic generator)
As shown in FIG. 1, the inspection logic generation device 2 is a general-purpose device including a CPU, a memory, a hard disk, an I / O control unit, a communication I / F, a display unit, an information input unit (keyboard and mouse), etc. as basic hardware. Computer (information processing apparatus).

  FIG. 6 shows a functional configuration of the inspection logic generation device 2. The inspection logic generation device 2 includes an instruction information reception function 50, a teacher image information reading function 51, an image acquisition function 52, a distribution function 53, a first pixel area extraction function 54, a first feature quantity extraction function 55, and a first feature quantity. Histogram generation function 56, first determination condition determination function 57, specific defective product image selection function 58, second image region extraction function 59, second feature quantity extraction function 60, second feature quantity histogram generation function 61, second determination condition A determination function 62, an inspection logic generation function 63, and an inspection logic writing function 64 are provided. These functions are realized by a program stored in a memory or a hard disk being read and executed by a CPU.

  In addition, a teacher image information DB 65 that stores teacher image information used for teaching is provided in the hard disk. The teacher image information includes an image of the mounted component imaged by the board inspection apparatus 1 and teacher information (teaching data) indicating whether the image should be detected (non-defective product) or excluded (defective product). In order to increase the reliability of teaching, it is preferable to prepare dozens to thousands of teacher image information for each of the non-defective product and the defective product.

(Inspection logic generation process)
The flow of the inspection logic generation process will be described along the flowcharts of FIGS. 7A and 7B.

  The instruction information receiving function 50 is in a waiting state until instruction information for instructing automatic generation of inspection logic is input (step S200; NO, step S201). When the instruction information is input from the information input unit, the instruction information receiving function 50 transmits the instruction information to the teacher image information reading function 51 (step S200; YES). This instruction information includes information for specifying teacher image information to be subjected to inspection logic generation, the type of inspection logic, and the like.

  The teacher image information reading function 51 reads teacher image information corresponding to the examination logic to be created from the teacher image information DB 65 in accordance with the instruction information (step S202). The teacher image information includes a non-defective image (an image with a good solder fillet) and a defective image (an image with a defective solder fillet). The non-defective image includes an image of a component in which blue light is blocked by another component and an image of a component that is correctly irradiated with blue light. Teacher information is given to these images.

  When the teacher image information is read, the image acquisition function 52 extracts a solder area from the image to which the teacher information is added (step S203). As shown in FIG. 8, the image acquisition function 52 has a template composed of a land window 70 and a component main body window 71, and enlarges / reduces the template, or relative to the land window 70 and the component main body window 71. The windows 70 and 71 are aligned with the land area 72 and the part 73 in the image while shifting the position. For example, a method such as template matching may be used for matching the windows. Thereby, the land area 72 is specified for each of the non-defective product image and the defective product image. And the area | region except the overlap part with the component main body window 71 from the land window 70 is extracted as a solder area | region (refer the shaded part of FIG. 8).

  Next, the distribution function 53 distributes the extracted solder area into a non-defective product image and a defective product image based on the teacher information (step S204). See FIG. 3B for examples of non-defective images and defective images.

(1) First Determination Condition Determination Process The first pixel area extraction function 54 binarizes all solder areas of the non-defective product image and the defective product image using the preset first color parameters (step S205). The first color parameter is composed of four values: a lower limit and an upper limit of blue saturation, and a lower limit and an upper limit of lightness. The value of the first color parameter may be set so as to include the entire blue color, or may be automatically calculated from the pixel color tendency of each of the non-defective product image and the defective product image. In this binarization process, blue color pixels included in the color range defined by the first color parameter are converted into white pixels, and other pixels are converted into black pixels. The white pixel area after binarization is called a first pixel area.

  As shown in FIG. 3C, in principle, the first pixel region is very large in a non-defective image, and the first pixel region is extremely small in a defective image. Therefore, when such a binarized image is used, it becomes easy to quantitatively calculate a feature amount for identifying a non-defective product or a defective product. Examples of the feature amount include the area of the first pixel region, the area ratio, the center of gravity, the length, the maximum width, the shape, and the like. Here, as described above, the specified width line number is selected as the feature amount.

  However, as the specified width is set, the number of specified width lines changes, and the degree of separation between non-defective products and defective products also changes. Therefore, in the present embodiment, the specified width is set to a temporary value, a first feature amount histogram is created for the specified number of lines in the first pixel area of each of the good image and the defective image, and the lower limit of the frequency distribution of the good image By setting a threshold value to a smaller value and calculating the degree of separation between the non-defective product image and the defective product image based on the threshold value, the optimum specified width that maximizes the degree of separation is repeated. decide.

  Specifically, first, the first feature quantity extraction function 55 calculates the width (number of white pixels) for each line for the first pixel areas of the non-defective image and the defective image (step S206). As shown in FIG. 9, many non-defective images have many wide lines and few defective images. In addition, it can be seen that in a non-defective image with light shielding, the light shielding portion is a black pixel, so that wide lines are reduced.

  Next, the first feature quantity extraction function 55 sets an initial value of the specified width (step S207). Here, the search is performed for the specified width of 10% to 90% of the land width, and the initial value is set to 10% of the land width (the value of the specified width is also a ratio (%) to the land width). It may be a format converted into the number of pixels).

  The first feature quantity extraction function 55 calculates the number of lines having a width equal to or greater than the specified width (number of specified width lines) for each first pixel region (step S208). The first feature amount histogram generation function 56 creates a first feature amount histogram relating to the number of defined width lines of each first pixel region (step S209). FIG. 10 shows an example of the first feature amount histogram. The black portion in the figure represents the frequency distribution (defective product distribution) of the non-defective image, and the white portion represents the frequency distribution (defective product distribution) of the defective product image. It can be seen that the non-defective image with light shielding has a smaller number of specified width lines than the non-defective image with no light shielding, so that a part of the non-defective product distribution overlaps the defective product distribution.

The first determination condition determination function 57 determines a threshold value that includes all of the frequency distributions of the non-defective images (including both with and without light shielding) in the first feature amount histogram (step S210). In this embodiment, a threshold value is set between the lower limit value of the non-defective product distribution and the upper limit value of a portion obtained by excluding the overlap of the non-defective product distribution with the non-defective product distribution (hereinafter referred to as “non-overlapping distribution”). For example, as shown in FIG. 10, when the non-overlapping distribution and the non-defective distribution are continuous (there is no interval), the upper limit value of the non-overlapping distribution (a value smaller than the lower limit value of the non-defective distribution) is set as the threshold value. That's fine. When the non-overlapping distribution and the non-defective product distribution are separated (there is an interval) (see the middle part of FIG. 11), an intermediate value between the upper limit value of the non-overlapping distribution and the lower limit value of the non-defective product distribution is used as a threshold value. Alternatively, preferably, a threshold value may be set at an appropriate position between the two distributions based on the variance of the non-overlapping distribution and the variance of the non-defective distribution. In addition, as long as the threshold value is set to a value smaller than the lower limit value of the non-defective product distribution, another threshold value determination algorithm may be adopted.

  Then, the first determination condition determination function 57 calculates the separation degree between the non-defective product image and the defective product image based on the threshold value (step S211). Here, simply, “the number of defective images whose frequency exceeds the threshold value” is defined as the degree of separation. That is, the smaller the number of defective products that are missed by this threshold value, the better the degree of separation. The calculated degree of separation is stored in the memory together with the specified width and threshold value.

A degree of separation other than this definition may be adopted. For example, the distance between the upper limit of the non-overlapping distribution and the lower limit of the non-defective distribution, the variance of the non-overlapping distribution (or defective product distribution) and the non-defective product distribution, and the peak value of the non-overlapping distribution (or defective product distribution) It is also preferable to consider the distance between the peak value of the non-defective product distribution and the like. Further, when the distance is X and the number of misses is Y, the degree of separation E may be defined by the following functional expression.
E = αX + βY
E = αX / Y
Where α and β are coefficients.

  Thereafter, as shown in FIG. 11, the prescribed widths are sequentially updated by the first feature amount extraction function 55 (step S213), and the threshold value and the degree of separation in each prescribed width are calculated and stored in the memory. (Steps S208 to S212; NO). When the maximum value of the specified width is reached (90% of the land width in this example), the search process is terminated (step S212; YES). Then, the degree of separation at each prescribed width stored in the memory is compared to select the prescribed width having the maximum degree of separation, and the prescribed width and the threshold value in the prescribed width are determined as the first determination condition. (Step S214). With the above processing, the first determination condition that eliminates the overdetection of the non-defective product and permits the oversight of the defective product is obtained.

(2) Determination Process of Second Determination Condition When the first determination condition is confirmed, the specific defective product image selection function 58 has a frequency that satisfies the first determination condition (exceeds a threshold value) from the defective product images. An image is selected as a specific defective product image (step S215). That is, the specific defective product image corresponds to a defective product that can be overlooked in the first logic (see FIG. 10).

  The second pixel area extraction function 59 binarizes all the solder areas of the non-defective image and the specific defective product image using the preset second color parameter (step S216). The second color parameter is composed of four values: a lower limit and an upper limit of red saturation, and a lower limit and an upper limit of lightness. The value of the second color parameter may be set so as to include the entire red color, or may be automatically calculated from the pixel color tendency of each of the non-defective product image and the specific defective product image. In this binarization processing, red color pixels included in the color range defined by the second color parameter are converted into white pixels, and other pixels are converted into black pixels. The white pixel area after binarization is called a second pixel area.

  As shown in FIG. 3E, in principle, the second pixel region is very small in a non-defective image, and the second pixel region is extremely large in a defective image. Therefore, when such a binarized image is used, it becomes easy to quantitatively calculate a feature amount for identifying a non-defective product or a defective product. The feature amount includes the area, area ratio, center of gravity, length, maximum width, shape, and the like of the second pixel region. Here, the area (area value) is selected as the feature amount. Since the area value is a single parameter, the threshold value (judgment condition) determination process is simplified, unlike a composite parameter (width, number of lines) such as the specified number of lines.

Specifically, the second feature quantity extraction function 60 calculates the area (number of pixels) for the second pixel area of each of the non-defective product image and the specific defective product image (step S217), and the second feature quantity histogram generation function 61 Then, a second feature amount histogram relating to the area value of each second pixel region is created (step S218). FIG. 12 shows an example of a second feature amount histogram of a good product image and a specific defective product image. When a good product image and a specific defective product image are compared, it can be seen that a clear difference appears in the area value of the red color pixel.

  Next, the second determination condition determination function 62 calculates a threshold value for optimally separating the area value of the non-defective product image from the area value of the specific defective product image based on the frequency distribution of the second feature amount histogram. (Step S219). This threshold value is the second determination condition.

  Various methods for optimally separating the two peaks appearing in the feature amount histogram have been proposed, and any method may be adopted here. For example, Otsu's discriminant analysis method may be used, or a point separated by 3σ from the edge of a non-defective image peak may be determined as a threshold based on experience. In addition, a threshold determination algorithm similar to that in the case of the first determination condition may be adopted (however, in determining the threshold value of the second determination condition, a threshold value is set so as to eliminate oversight of a specific defective product). Should be set).

  When the first determination condition and the second determination condition are determined by the above process, the inspection logic generation function 63 generates the first logic from the first color parameter and the first determination condition (specified width and threshold), and the first logic The second logic is generated from the two-color parameters and the second determination condition (threshold value), and these are further combined. If both the determination results of the first logic and the second logic are true, the inspection target part is determined to be a non-defective product. Inspection logic for the solder fillet to be generated is generated (step S220). Then, the inspection logic writing function 64 writes the inspection logic in the inspection logic storage unit 35 of the substrate inspection apparatus 1 (step S221).

  According to the present embodiment described above, since the inspection logic used in the solder fillet inspection is automatically generated, the time and load required for teaching can be greatly reduced. Moreover, according to this inspection logic, it is possible to determine the quality of the solder fillet on the high-density mounting board with high accuracy. Note that the reliability of the color parameter and the threshold value is improved as the number of teacher image information to be given first increases.

<Modification>
The above-described embodiment is merely an example of the present invention. The scope of the present invention is not limited to the above embodiment, and various modifications can be made within the scope of the technical idea.

  For example, in the above embodiment, color parameters including the lower limit and upper limit of saturation and the lower limit and upper limit of brightness are used, but the type and value of the color parameter are selected by the color pattern of the component image captured by the board inspection apparatus. It may be determined according to the tendency of. Further, the color parameter is not limited to a rectangle, and a circle, a polygon, a free curve figure, or the like may be used, or a multidimensional shape may be used.

  In addition, as a feature amount extracted from the first pixel region and the second pixel region, an area ratio, a length, a maximum width, a center of gravity, and the like can be preferably employed. The area ratio is the occupation ratio of the binarized area in the land window. For example, if a component is soldered with a deviation from the land area, the area of the solder area increases and the area ratio changes. If this is regarded as a feature amount, it is effective for inspection of component displacement. The length is the length in the vertical direction or the horizontal direction of the white pixel region, and the maximum length is the maximum value among the lengths of the white pixel region. The center of gravity is a relative position of the center of gravity of the white pixel region with respect to the land window.

Any feature amount may be used as long as it can accurately determine pass / fail, and it is also preferable to combine a plurality of types of feature amounts to improve accuracy. It is also possible to extract a plurality of types of feature amounts in the inspection logic generation process, and to adopt a feature amount that best separates non-defective products and defective products among them. In the above embodiment, the feature amount histogram is used to determine the determination condition. However, if the type of feature amount is different, an area ratio histogram, a length histogram, a maximum width histogram, a centroid histogram, or the like is used in accordance with the feature amount. Become. For example, if an area ratio histogram is used instead of the area value histogram, the pass / fail judgment is executed based on the pixel occupation rate binarized by the color parameter in the land window. Even when the size becomes smaller or larger, determination processing that is not affected by the size of the land window is possible.

The figure which shows the hardware constitutions of the board | substrate inspection system which concerns on embodiment of this invention. The figure which shows the function structure of a board | substrate inspection apparatus. The figure which shows the relationship of the determination result of the shape of a solder fillet, a color pattern, a binarized image, and inspection logic. The flowchart which shows the flow of a board | substrate inspection process. The figure explaining the regulation width and the regulation width line number. The figure which shows the function structure of a test | inspection logic production | generation apparatus. The flowchart which shows the flow of a test | inspection logic production | generation process. The flowchart which shows the flow of a test | inspection logic production | generation process. The figure which shows the extraction process of a solder area | region. The figure which shows the feature-value of a 1st pixel area. The figure which shows the 1st feature-value histogram. The figure which shows the search process of a 1st determination condition. The figure which shows the determination process of 2nd determination conditions. The figure which shows the structure of the board | substrate inspection apparatus of a color highlight system. The figure which shows an example of the color pattern which appears in a captured image. The figure which shows the setting support tool of a color parameter. The figure which shows the problem resulting from high-density mounting. The figure which shows the relationship between the shape of a solder fillet, a color pattern, and a binarized image. The figure which shows the area histogram of the pixel area of the blue color of each good product and inferior goods.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Board | substrate inspection apparatus 2 Inspection logic production | generation apparatus 10 Instruction information reception function 11 Board | substrate carrying-in function 12 CAD information reading function 13 Stage operation function 14 Imaging function 15 Inspection logic reading function 16 Inspection function 16a Solder area extraction function 16b 1st inspection function 16c 1st 2 Inspection Function 16d Judgment Function 17 Judgment Result Writing Function 18 Board Unloading Function 20 Board 21 Mounted Parts 22 X Stage 23 Y Stage 24 Projecting Unit 25 Imaging Unit 26 Control Processing Unit 27 Conveyor 28 Red Light Source 29 Green Light Source 30 Blue Light Source 31 Imaging controller 32 storage unit 32a CAD information storage unit 32b determination result storage unit 33 A / D conversion unit 34 image processing unit 35 inspection logic storage unit 36 determination unit 37 XY stage controller 38 memory 39 control unit 40 input unit 41 display unit 42 printer 50 Instruction information reception function 51 Teacher image information reading function 52 Image acquisition function 53 Distribution function 54 First pixel area extraction function 55 First feature quantity extraction function 56 First feature quantity histogram generation function 57 First determination condition determination function 58 Specification Defective product image selection function 59 Second image region extraction function 60 Second feature quantity extraction function 61 Second feature quantity histogram generation function 62 Second determination condition determination function 63 Inspection logic generation function 64 Inspection logic writing function 65 Teacher image information DB
70 Land window 71 Parts window 72 Land area 73 Parts

Claims (14)

The light projecting means irradiates the inspection target parts on the substrate with light of a plurality of colors at different incident angles,
The imaging means captures the reflected light to obtain an inspection image,
With respect to the first color condition for extracting the pixel including the color component of the light having the largest incident angle and the first feature amount of the pixel area satisfying the first color condition, overdetection of non-defective products is eliminated and is not detected. The first logic including the first determination condition set to an allowable value for overlooking the non-defective product is read from the storage unit,
According to the first logic, a first pixel area that satisfies the first color condition is extracted from a solder portion of the inspection image, and a first feature amount of the first pixel area satisfies the first determination condition. Determine whether
Regarding the second color condition for extracting the pixel including the color component of the light having the smallest incident angle and the second feature amount possessed by the pixel area satisfying the second color condition, the second logic condition may be overlooked by the first logic. A second logic including a second determination condition set to a value that eliminates oversight of non-defective products is read from the storage unit;
According to the second logic, a second pixel area that satisfies the second color condition is extracted from a solder portion of the inspection image, and a second feature amount of the second pixel area satisfies the second determination condition. Determine whether
A substrate inspection method by a substrate inspection apparatus that determines that the inspection target component is a non-defective product when both of the determination results of the first logic and the second logic are true. 2. The substrate inspection method according to claim 1, wherein the first feature amount is the number of lines having a number of pixels greater than or equal to a predetermined width among lines constituting the first pixel region. The substrate inspection method according to claim 1, wherein the second feature amount is an area of the second pixel region. Automatic inspection logic used in board inspection equipment that inspects the mounting state of components based on images obtained by irradiating mounting colors on the board with multiple colors at different angles of incidence and imaging the reflected light A method of generating,
Information processing device
Acquire a plurality of non-defective images obtained by imaging the parts with good soldering and a plurality of defective images obtained by imaging the parts with poor soldering,
Extracting a first pixel region from each of the non-defective product image and the defective product image using a first color condition for extracting a pixel including a color component of light having the largest incident angle;
Creating a first feature amount histogram for the first feature amount of each first pixel region;
Determining a first determination condition so as to include all of the frequency distribution of the non-defective image in the first feature amount histogram;
A frequency that satisfies the first determination condition is selected from the defective images as a specific defective image,
Extracting a second pixel region from each of the non-defective product image and the specific defective product image using a second color condition for extracting a pixel including a color component of light having the smallest incident angle,
Create a second feature amount histogram for the second feature amount of each second pixel region,
Based on the frequency distribution of the second feature amount histogram, a second determination condition is determined so as to separate the second feature amount of the non-defective product image from the second feature amount of the specific defective product image,
A pixel region that satisfies the first color condition is extracted from an inspection image obtained by imaging the inspection target component, and a first feature amount of the pixel region is determined to satisfy the first determination condition. 1 logic and a second logic for extracting a pixel region that satisfies the second color condition from the inspection image and determining whether a second feature amount of the pixel region satisfies the second determination condition, An inspection logic generation method for a substrate inspection apparatus, which generates inspection logic for determining that a component to be inspected is a non-defective product when both the determination results of the first logic and the second logic are true. The inspection logic generation method of the substrate inspection apparatus according to claim 4, wherein the first feature amount is the number of lines having a number of pixels equal to or larger than a predetermined width among lines constituting the first pixel region. Information processing device
The width of the line is set, the first feature amount histogram is created for the number of lines having the number of pixels equal to or larger than the width in the first pixel area of each of the good product image and the defective product image, and the frequency distribution of the good product image is By setting a threshold value to a value smaller than the lower limit, and repeating the search process for calculating the separation degree of the non-defective product image and the defective product image based on the threshold value, a width that maximizes the separation degree is determined,
6. The inspection logic generation method for a substrate inspection apparatus according to claim 5, wherein the determined width and a threshold value in the width are set as the first determination condition. The inspection logic generation method for a substrate inspection apparatus according to claim 6, wherein the separation degree is calculated based on the number of defective product images whose frequency exceeds the threshold value. The inspection logic generation method of the substrate inspection apparatus according to claim 4, wherein the second feature amount is an area of the second pixel region. A light projecting means for irradiating a plurality of colors of light at different angles of incidence on a component to be inspected on a substrate;
Imaging means for imaging the reflected light to obtain an inspection image;
With respect to the first color condition for extracting the pixel including the color component of the light having the largest incident angle, and the first feature amount of the pixel area that satisfies the first color condition, overdetection of non-defective products is eliminated and A first logic including a first determination condition set to an allowable value for overlooking a defective product, a second color condition for extracting a pixel including a color component of light having the smallest incident angle, and the first A storage unit that stores a second logic including a second determination condition that is set to a value that eliminates oversight of a defective product that can be overlooked in the first logic with respect to a second feature amount of a pixel region that satisfies a two-color condition When,
According to the first logic, a first pixel area that satisfies the first color condition is extracted from a solder portion of the inspection image, and a first feature amount of the first pixel area satisfies the first determination condition. First inspection means for determining whether or not
According to the second logic, a second pixel area that satisfies the second color condition is extracted from a solder portion of the inspection image, and a second feature amount of the second pixel area satisfies the second determination condition. Second inspection means for executing second logic for determining whether or not
A determination means for determining that the inspection target part is a non-defective product when both of the determination results of the first logic and the second logic are true;
A board inspection apparatus comprising: Automatic inspection logic used in board inspection equipment that inspects the mounting state of components based on images obtained by irradiating mounting colors on the board with multiple colors at different angles of incidence and imaging the reflected light A device for generating,
Image acquisition means for acquiring a plurality of non-defective images obtained by imaging good soldering parts and a plurality of defective images obtained by imaging non-soldering parts;
First pixel region extraction means for extracting a first pixel region from each of the non-defective product image and the defective product image using a first color condition for extracting a pixel including a color component of light having the largest incident angle;
First feature quantity histogram generating means for creating a first feature quantity histogram for the first feature quantity of each first pixel region;
First determination condition determining means for determining a first determination condition so as to include all of the frequency distribution of the non-defective image in the first feature amount histogram;
Specific defective product image selection means for selecting, as the specific defective product image, a frequency satisfying the first determination condition from the defective product images;
Second pixel region extraction means for extracting a second pixel region from each of the non-defective product image and the specific defective product image using a second color condition for extracting a pixel including a light color component having the smallest incident angle. When,
Second feature amount histogram generating means for creating a second feature amount histogram for the second feature amount of each second pixel region;
Second determination condition determining means for determining a second determination condition so as to separate the second feature quantity of the non-defective product image from the second feature quantity of the specific defective product image based on the frequency distribution of the second feature quantity histogram. When,
A pixel region that satisfies the first color condition is extracted from an inspection image obtained by imaging the inspection target component, and a first feature amount of the pixel region is determined to satisfy the first determination condition. 1 logic and a second logic for extracting a pixel region that satisfies the second color condition from the inspection image and determining whether a second feature amount of the pixel region satisfies the second determination condition, Inspection logic generating means for generating inspection logic for determining that the inspection target component is a non-defective product when both of the determination results of the first logic and the second logic are true;
An inspection logic generation device for a substrate inspection device comprising: The inspection logic generation device of a substrate inspection device according to claim 10, wherein the first feature amount is the number of lines having a number of pixels equal to or larger than a predetermined width among lines constituting the first pixel region. The first determination condition determining means is:
The width of the line is set, and the first feature amount histogram generating means is configured to create a first feature amount histogram for the number of lines having the number of pixels equal to or larger than the width in the first pixel region of each of the good product image and the defective product image. By setting the threshold value to a value smaller than the lower limit of the frequency distribution of the non-defective image and repeating the search process for calculating the separation degree between the good image and the defective image based on the threshold value, the degree of separation is maximized. To determine the width
12. The inspection logic generation device of a substrate inspection device according to claim 11, wherein the determined width and a threshold value in the width are set as the first determination condition. 13. The inspection logic generation device for a substrate inspection device according to claim 12, wherein the degree of separation is calculated based on the number of defective product images whose frequency exceeds the threshold value. The inspection logic generation device of a substrate inspection device according to claim 10, wherein the second feature amount is an area of the second pixel region.

Images