Method and device for detecting quality of inductive element, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a kind of quality detection method and device of inductive component, electronic equipment and storage medium.The method comprises: obtaining image to be measured;According to the position of the region of interest on template image, the position of the region of interest corresponding to the pad region of interest in image to be measured is determined, template image is inductive component image marked with the position information of region of interest, region of interest is the area where the pad part of interest is located, the pad region of interest includes the target pad part corresponding to the pad part of interest, region of interest and pad region of interest each include multiple sub-regions, each sub-region has corresponding detection standard;Determine the wire region where wire is located in pad region of interest;According to the distribution of wire region in each sub-region in multiple sub-regions and the detection standard corresponding to each sub-region, whether the position of wire on target pad part is qualified is determined.This scheme is stable and accurate, without complex parameter setting.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of semiconductor processing, and more particularly to a quality detection method of an inductance element, a quality detection device of an inductance element, an electronic device and a storage medium. BACKGROUND

[0002] Currently, people have higher and higher requirements for product quality. For manufacturers, how to improve the delivery quality of products and reduce end customer complaints has become an urgent demand. Because the forms of products are changing and the structures are complex and different, higher standards are required for product detection equipment.

[0003] Machine vision is a rapidly developing sunrise industry, and visual detection equipment has been widely used in various production links of manufacturing industry. The visual detection equipment uses a camera to collect images containing products and uses a visual detection algorithm to analyze and process the images, and then judges the product quality.

[0004] In recent years, the semiconductor industry in China has developed rapidly, and the demand for capacitor resistance inductance (LCT) elements has increased dramatically. The quality detection requirements are also getting higher and higher. Among them, the inductance element plays a role in blocking flow, voltage conversion, tuning, frequency division, etc. in different circuit systems, and its quality directly determines its performance.

[0005] The coil is an important part of the inductance element. The position detection of the coil part on the pad (hereinafter referred to as the wire or soldering wire) on the pad is also an important control index in the production process of the inductance element. For position detection, the relative position relationship of the target object (target soldering wire in the position detection of the soldering wire) relative to the reference is generally calculated to make a judgment. The conventional position detection usually needs to extract the edge of the product (inductance element in the position detection of the soldering wire) (such as extracting the entire pad area of the product) or edge fitting is performed on the edge of the product, and the position distance of the target soldering wire relative to the edge is judged. However, due to the irregular shape of the product pad area and some complex background interference (such as cover plate offset), whether edge fitting or extracting the pad area will cause certain misjudgment, and the efficiency is low, which is difficult to apply in high-speed demand. SUMMARY

[0006] The present application is proposed considering the above problems. The present application provides a quality detection method of an inductance element, an electronic device and a storage medium.

[0007] According to an aspect of the present application, a quality detection method of an inductor is provided, comprising: obtaining a to-be-detected image, the to-be-detected image containing a to-be-detected inductor; determining a position of a region of interest pad area corresponding to a region of interest in the to-be-detected image according to the region of interest on a template image, wherein the template image is an inductor image marked with position information of the region of interest, the region of interest is a region where a pad part of interest is located, the region of interest pad area contains a target pad part corresponding to the pad part of interest, the region of interest and the region of interest pad area each include a plurality of sub-regions, each sub-region has a corresponding detection standard, and the plurality of sub-regions in the region of interest pad area correspond one-to-one to the plurality of sub-regions in the region of interest; determining a wire region where a wire is located within the region of interest pad area; and determining whether a position of the wire on the target pad part is qualified according to a distribution of the wire region in each of the plurality of sub-regions in the region of interest pad area and the detection standard corresponding to each sub-region.

[0008] Exemplarily, the determining whether the position of the wire on the target pad part is qualified according to the distribution of the wire region in each of the plurality of sub-regions in the region of interest pad area and the detection standard corresponding to each sub-region includes: for any sub-region, intersecting the wire region with the sub-region; judging whether the position of the wire in the sub-region is qualified according to the intersection result and the detection standard corresponding to the sub-region to obtain a judgment result corresponding to the sub-region; and comprehensively determining whether the position of the wire on the target pad part is qualified according to the judgment results corresponding to the plurality of sub-regions in the region of interest pad area respectively.

[0009] Exemplarily, before the determining the wire region where the wire is located within the region of interest pad area, the method further comprises: obtaining images corresponding to a first color channel and a second color channel based on the to-be-detected image; subtracting a gray value of the image corresponding to the first color channel from a gray value of the image corresponding to the second color channel to obtain a difference image, wherein the first color channel and the second color channel satisfy the following condition: in an inductor image containing an inductor of a preset type, a gray value difference of a pad on the first color channel and the second color channel is less than a gray value difference of a wire on the first color channel and the second color channel, and the to-be-detected inductor belongs to the inductor of the preset type; determining a region with a gray value difference greater than a first preset gray threshold in the difference image as a target region; and determining the wire region where the wire is located within the region of interest pad area, including: determining an intersection of the region of interest pad area and the target region as the wire region.

[0010] Exemplarily, before the determining the region with the gray value difference greater than the first preset gray threshold in the difference image as the target region, the method further comprises: performing image stretching on the difference image.

[0011] Exemplarily, the first color channel and the second color channel further satisfy the following condition: on an inductance element image containing inductance elements of a preset type, a difference between the grayscale values of the solder pad on the first color channel and the second color channel is less than a second preset grayscale threshold.

[0012] Exemplarily, the plurality of sub-regions include one or more of a first sub-region, a second sub-region, a third sub-region, and a fourth sub-region, wherein the first sub-region is a region where a free end of the wire is expected to fall into; the second sub-region and the third sub-region are regions where the wire is not expected to fall into, respectively; and the fourth sub-region is a region where a connected end of the wire is expected to fall into.

[0013] Exemplarily, according to the distribution of the wire region in each of the plurality of sub-regions of the solder pad region of interest and the detection standard corresponding to each sub-region, it is determined whether the position of the wire on the target solder pad part is qualified, including: if the wire region falls into the first sub-region, it is determined that the judgment result corresponding to the first sub-region is qualified, otherwise it is determined that the judgment result corresponding to the first sub-region is unqualified; if the wire region falls into the second sub-region, it is determined that the judgment result corresponding to the second sub-region is unqualified, otherwise it is determined that the judgment result corresponding to the second sub-region is qualified; if the wire region falls into the third sub-region, it is determined that the judgment result corresponding to the third sub-region is unqualified, otherwise it is determined that the judgment result corresponding to the third sub-region is qualified; and if the wire region falls into the fourth sub-region and the length in the fourth sub-region is greater than a preset length threshold, it is determined that the judgment result corresponding to the fourth sub-region is qualified, otherwise it is determined that the judgment result corresponding to the fourth sub-region is unqualified.

[0014] Exemplarily, before determining the position of the solder pad region of interest corresponding to the region of interest in the to-be-detected image according to the region of interest on the template image, the method further includes: obtaining the template image; and determining the positions of a plurality of sub-regions in the region of interest on the template image based on region division information input by a user.

[0015] Exemplarily, the plurality of sub-regions include one or more of a first sub-region, a second sub-region, a third sub-region, and a fourth sub-region, wherein the first sub-region is a region where a free end of the wire is expected to fall into; the second sub-region and the third sub-region are regions where the wire is not expected to fall into, respectively; and the fourth sub-region is a region where a connected end of the wire is expected to fall into.

[0016] Exemplarily, the region division information includes edge information related to the first initial region, the second initial region and the third initial region respectively, and the position of the plurality of sub-regions in the region of interest on the template image is determined based on the user-input region division information, including: calculating a difference set between the region of interest and a region contained in the edge information to obtain a fourth sub-region; determining two target points on the edge of the fourth sub-region closest to two distal vertices of the region of interest respectively, the two distal vertices being two vertices on the region of interest located at the distal end along the extension direction of the wire; connecting the two distal vertices to the corresponding target points respectively to obtain two target edges; and dividing the region of interest into the first sub-region, the second sub-region, the third sub-region and the fourth sub-region through the two target edges and the edge of the fourth sub-region.

[0017] Exemplarily, the method further includes: receiving user-input edge adjustment information; and adjusting the position of a point on the edge of any of the plurality of sub-regions based on the edge adjustment information.

[0018] Exemplarily, the method further includes: receiving user-input position adjustment information; and adjusting the overall position of any of the plurality of sub-regions based on the position adjustment information.

[0019] According to another aspect of the present application, a quality detection device of an inductance element is provided, which is characterized by comprising: a first acquisition module configured to acquire a to-be-detected image, the to-be-detected image containing a to-be-detected inductance element; a first determination module configured to determine the position of a region of interest pad corresponding to a region of interest in the to-be-detected image according to the region of interest on a template image, wherein the template image is an inductance element image marked with position information of the region of interest, the region of interest is a region where a pad part of interest is located, the region of interest pad contains a target pad part corresponding to the pad part of interest, the region of interest and the region of interest pad each include a plurality of sub-regions, each sub-region has a corresponding detection standard, and the plurality of sub-regions in the region of interest pad correspond one-to-one to the plurality of sub-regions in the region of interest; a second determination module configured to determine a wire region where a wire is located within the region of interest pad; and a third determination module configured to determine whether the position of the wire on the target pad part is qualified according to the distribution of the wire region in each of the plurality of sub-regions in the region of interest pad and the corresponding detection standard of each sub-region.

[0020] According to another aspect of the present application, an electronic device is provided, which includes a processor and a memory, the memory having stored therein a computer program, and the processor executes the computer program to implement the quality detection method of the inductance element.

[0021] According to another aspect of the present application, there is also provided a storage medium storing computer programs / instructions which, when executed by a processor, implement the quality detection method of the inductive element.

[0022] The quality detection method of the inductive element, the electronic device and the storage medium according to the embodiments of the present application automatically determine the position of the region of interest pad area by using the template image marked with the region of interest, further determine the wire bonding area, and determine whether the position of the wire bonding is qualified by setting sub-areas with respective detection standards and judging the distribution of the wire bonding area in each sub-area. Therefore, the detection method can divide the sub-areas according to the actual situation, and thus is not affected by whether the shape of the pad area is regular, so that the detection scheme is stable and accurate, and each sub-area and its detection standard can be set in advance without complex parameter setting. In addition, the scheme does not involve edge finding or fitting, and is more efficient than the conventional position detection.

[0023] The above description is only a summary of the technical solutions of the present application. In order to enable one skilled in the art to better understand the technical means of the present application, the contents of the specification can be implemented, and in order to enable the above and other purposes, features and advantages of the present application to be more obvious and easy to understand, the specific embodiments of the present application are described below. BRIEF DESCRIPTION OF DRAWINGS

[0024] The above and other purposes, features and advantages of the present application will become more apparent from the following detailed description of the embodiments of the present application, taken in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification, together with the embodiments of the present application, to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0025] Figure 1 a schematic flowchart of a quality detection method of an inductive element according to one embodiment of the present application is shown;

[0026] Figure 2 a schematic diagram of an inductive element image according to one embodiment of the present application is shown;

[0027] Figure 3 a schematic diagram showing that the region of interest pad area includes four sub-areas according to one embodiment of the present application is shown;

[0028] Figure 4 a schematic diagram showing that the initial area is divided in the region of interest according to one embodiment of the present application is shown;

[0029] Figure 5A diagram showing a fourth sub-region obtained by dividing an initial region of a region of interest and a user according to an embodiment of the present application is shown;

[0030] Figure 6 A schematic block diagram of a quality detection device of an inductive element according to an embodiment of the present application is shown; and

[0031] Figure 7 A schematic block diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0032] In order to make the objectives, technical solutions and advantages of the present application more apparent, the following will describe example embodiments of the present application in detail with reference to the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present application.

[0033] In order to at least partially solve the above problems, an embodiment of the present application provides a quality detection method of an inductive element. Figure 1 A schematic flow chart of a quality detection method 100 of an inductive element according to an embodiment of the present application is shown. As shown in the figure, Figure 1 The method 100 can include a step S110, a step S120, a step S130 and a step S140.

[0034] The step S110 acquires a to-be-detected image, the to-be-detected image containing a to-be-detected inductive element.

[0035] Exemplarily, the to-be-detected image can be an image containing the to-be-detected inductive element. The to-be-detected inductive element can contain a coil, a solder pad and the like. The to-be-detected image can be a static image, or any video frame in a dynamic video. The to-be-detected image can be a raw image acquired by an image acquisition device (such as a separate camera or a camera of a mobile terminal, etc.) for the to-be-detected inductive element, or an image obtained after pre-processing (such as digitization, normalization, smoothing, etc.) of the raw image. It can be understood that the pre-processing of the raw image can include an operation of extracting a sub-image containing the to-be-detected inductive element from the raw image acquired by the image acquisition device to obtain the to-be-detected image. In an embodiment, the to-be-detected image can be a grayscale image or an RGB image, etc. Preferably, the to-be-detected image can be an RGB image.

[0036] Step S120: Determine the position of the pad region of interest in the image to be tested corresponding to the region of interest based on the region of interest on the template image. The template image is an image of an inductor component marked with the position information of the region of interest. The region of interest is the area where the pad of interest is located. The pad region of interest includes the target pad portion corresponding to the pad of interest. The region of interest and the pad region of interest each include multiple sub-regions. Each sub-region has a corresponding detection standard. The multiple sub-regions in the pad region of interest correspond one-to-one with the multiple sub-regions in the region of interest.

[0037] For example, the template image can be an image of an inductor component pre-marked with a region of interest (ROI). The inductor component in the template image is of the same type as the inductor component under test in the image under test. For example, an inductor component image may contain four pad regions, which may be located, for example, near the four corners of the inductor component image. Figure 2 A schematic diagram showing an inductor element image according to an embodiment of the present invention. See also Figure 2 The four pad areas are defined by four white boxes B1, B2, B3, and B4. Each pad area can be considered as containing a pad portion. For example, the user can pre-select the area containing the pad portion in the upper right corner (e.g., ...). Figure 2 As shown in Figure B3), the region of interest (ROI) is defined as the pad portion within this region. The inductor image after manually marking the ROI can then be used as a template image. Of course, the definition of the ROI can be set by the user as needed, and this invention does not impose any limitations on this. For the obtained image to be tested, the region in the image to be tested that corresponds to the ROI on the template image is the pad region of interest (PRI). This region may contain all or part of the pads in the inductor component under test, and these can be used as the target pad portion.

[0038] The position of the inductor element in the template image and the position of the inductor element in the image to be detected can be offset, i.e. the two can not be completely aligned. In order to accurately determine the pad region of interest, the offset between the inductor element in the template image and the inductor element to be detected in the image to be detected can be optionally determined, and the pad region of interest is adjusted based on the offset. Exemplarily, a second identification feature matching the first identification feature in the image to be detected can be determined based on the first identification feature in the template image. The first identification feature and the second identification feature can be the same feature on the inductor element, such as a partial contour of the inductor element. After determining the second identification feature, the offset between the image position of the first identification feature in the template image and the image position of the second identification feature in the image to be detected can be determined. Subsequently, based on the offset, the position of the pad region of interest in the template image can be adjusted. Subsequently, the region of the image to be detected at a second image position consistent with the first image position in the template image can be determined as the pad region of interest based on the first image position of the adjusted pad region of interest in the template image. Subsequently, defect detection can be performed in the pad region of interest. The above operation of adjusting the pad region of interest based on the offset to determine the pad region of interest is optional, and the pad region of interest can also be directly determined based on the initial unadjusted pad region of interest when needed.

[0039] The pad region of interest and the region of interest can each include a plurality of sub-regions. The plurality of sub-regions in the pad region of interest correspond one-to-one to the plurality of sub-regions in the region of interest, and have the same shape and size, and the plurality of sub-regions can correspond to respective detection criteria. The plurality of sub-regions in the pad region of interest are determined based on the plurality of sub-regions in the region of interest. The position of any sub-region in the pad region of interest is consistent with the position of the corresponding sub-region in the region of interest. For example, the region of interest can be evenly divided into 3 sub-regions along the extension direction of the wire. The sub-region where one end of the wire portion connected to the inductor element located outside the pad is determined as sub-region A, and sub-region B and sub-region C are sequentially determined in order. Exemplarily, the detection criteria for sub-region A and sub-region B can both be set as the wire falling into and being continuous. The detection criterion for sub-region C can be set as the length of the portion of the wire falling into the sub-region being greater than one fourth of the length of the entire wire. In addition, the detection criterion can limit the length of the wire in the sub-region, and can also limit the area occupied by the wire in the sub-region and other indicators.

[0040] In step S130, a wire region where the wire is located is determined in the pad region of interest.

[0041] Exemplarily, along the extension direction of the wire in the image to be detected, a wire region where the wire is located can be determined in the target pad portion in the pad region of interest.

[0042] Step S140, according to the distribution of the wire region in each of the plurality of sub-regions in the pad region of interest and the detection standard corresponding to each sub-region, determine whether the position of the wire on the target pad part is qualified.

[0043] Exemplarily, according to the determined wire region and the plurality of sub-regions in the region of interest, the position of the wire on the target pad part can be judged according to the detection standard corresponding to each sub-region, and then it can be determined whether the position of the wire on the target pad part is qualified, for example, it can be optionally determined whether the wire is missing, disconnected, multiple welding (appears in places where it should not appear) and other problems.

[0044] According to the quality detection method of the inductance element, the position of the pad region of interest is automatically determined by the template image marked with the region of interest, and the wire region is further determined, and the position of the wire is determined to be qualified by setting sub-regions with respective detection standards and judging the distribution of the wire region in each sub-region. The detection scheme is stable and accurate, and each sub-region and its detection standard can be set in advance without complex parameter setting. In addition, this scheme does not involve edge finding or fitting, and is more efficient than conventional position detection. Through experiments, using the above scheme, the detection of the wire at the four corners of the inductance element can be completed within a few milliseconds (depending on the performance difference of the processing unit), which has very high timeliness.

[0045] Exemplarily, according to the distribution of the wire region in each of the plurality of sub-regions in the pad region of interest and the detection standard corresponding to each sub-region, determine whether the position of the wire on the target pad part is qualified (step S140), which can include: for any sub-region, the wire region is intersected with the sub-region; according to the intersection result and the detection standard corresponding to the sub-region, determine whether the position of the wire in the sub-region is qualified, and obtain the judgment result corresponding to the sub-region; comprehensive judgment results corresponding to the plurality of sub-regions in the pad region of interest respectively, determine whether the position of the wire on the target pad part is qualified.

[0046] As described above, the detection standard of each sub-region can be set according to the requirements to determine whether the position of the wire on the target pad part contained in the pad region of interest is qualified. For any sub-region in the plurality of sub-regions in the region of interest, the judgment result corresponding to the sub-region can be obtained by the following steps.

[0047] For the sub-region A, the intersection of the determined wire region and the sub-region can be calculated. According to the calculated intersection, the length and continuity of the wire in the sub-region can be determined. If the wire in the sub-region A is continuous, it can be determined that the current detection result is qualified. In a similar manner, whether the wire region in other sub-regions meets the detection standard corresponding to each sub-region is judged in turn. Based on the judgment results of the three sub-regions, if the judgment results of the three sub-regions are all qualified, it can be determined that the position of the wire on the target pad part is qualified; otherwise, it is unqualified.

[0048] According to the above technical solution, the intersection of each sub-region and the wire region is calculated respectively, and whether the position of the wire in each sub-region is qualified is determined according to the intersection result and the detection standard corresponding to each sub-region, and then whether the position of the wire on the target pad part is qualified is determined. This determination method simply determines the distribution of the wire region in each sub-region by calculating the intersection, and then obtains the judgment result corresponding to each sub-region based on the intersection result. Moreover, since the sub-regions with their own detection standards are set, the sub-regions can be divided according to the actual situation, so that the influence of whether the shape of the pad region is regular can be avoided. This scheme is relatively simple to implement and is conducive to improving the speed of quality detection.

[0049] Exemplarily, before the wire region where the wire is located in the pad region of interest is determined (step S130), the method can further include: obtaining images corresponding to the first color channel and the second color channel based on the to-be-detected image; subtracting the gray value of the image corresponding to the first color channel from the gray value of the image corresponding to the second color channel to obtain a difference image, wherein the first color channel and the second color channel satisfy the following condition: the gray value difference of the pad on the first color channel and the second color channel is less than the gray value difference of the wire on the first color channel and the second color channel on an inductor image containing an inductor of a preset type, and the to-be-detected inductor belongs to the inductor of the preset type; determining a region with a gray value difference greater than a first preset gray threshold in the difference image as a target region; determining the wire region where the wire is located in the pad region of interest (step S130) can include: determining the intersection of the pad region of interest and the target region as the wire region.

[0050] In one embodiment, the image to be tested can be an RGB image, i.e. an image containing R, G, B three channels. According to the image to be tested, a single channel image corresponding to the first color channel and the second color channel can be obtained. The first color channel and the second color channel can be any two different channels of the R, G, B three channels. For example, the first color channel image can be an R channel image. The second channel image can be a G channel image. Subtracting the pixel value of each pixel in the R channel image (which is a gray value) from the pixel value of the pixel at the corresponding position in the G channel (which is also a gray value), a difference image can be obtained. It should be noted that the above operation of calculating the difference image is performed in the case that the gray value difference of the pad on the R channel and the G channel is less than the gray value difference of the wire on the R channel and the G channel. In many cases, the wire appears as a color close to yellow, and the pad appears as a color close to silver white. At this time, the brightness of the pad is relatively close on the R channel and the G channel, but the brightness of the wire is quite different, so the R channel can be subtracted from the G image, and the position of the pad in the finally obtained image will be darkened, and the wire on the pad will be highlighted, so that the pad and the wire can be better distinguished. However, the above is only an example, and other channel subtraction methods such as R channel minus B channel and B channel minus G channel can be used to highlight the wire according to the brightness performance of the pad and the wire in each channel in the specific application scenario. Of course, the first color channel and the second color channel are not limited to the color channels in the RGB color space, but can be any color channel in any color space, such as the color channel in the HSV space. In addition, the first color channel and the second color channel can belong to the same color space or belong to different color spaces, such as the R channel and the H channel.

[0051] The target region can contain the wire. The first preset gray threshold is a threshold for distinguishing the wire from other parts. The first preset gray threshold can be set in advance and can be set to any suitable value as needed. The first preset gray threshold can be any numerical value between 0 and 255. For example, the first preset gray threshold can be 180. It can be understood that the pixel value of the first pixel on the difference image is the difference (i.e. the gray value difference) between the pixel value of the second pixel on the image corresponding to the first color channel and the pixel value of the third pixel on the image corresponding to the second color channel. Among them, the position of the first pixel on the difference image, the position of the second pixel on the image corresponding to the first color channel, and the position of the third pixel on the image corresponding to the second color channel are consistent with each other. According to the difference image, the region where the pixel with a gray value difference greater than the first preset gray threshold (i.e. 180) is located can be determined as the target region. The region belonging to both the pad region of interest and the target region can be determined as the wire region.

[0052] It should be noted that the first color channel and the second color channel satisfying the condition that the difference between the grayscale values of the solder pad in the first color channel and the second color channel is less than the difference between the grayscale values of the solder wire in the first color channel and the second color channel can be determined in advance by theory and / or experiment, etc. In addition, as described above, the suitable first color channel and the second color channel corresponding to the solder pad and the solder wire can also change with different application scenarios. Therefore, for example, for a certain preset type of inductive element, the first color channel and the second color channel that can make the inductive element of this type appear the condition that the difference between the grayscale values of the solder pad in the first color channel and the second color channel is less than the difference between the grayscale values of the solder wire in the first color channel and the second color channel can be determined by theory and / or experiment, etc. When the quality detection is subsequently performed on the same type of inductive element (for example, the above-described inductive element to be detected), the prior knowledge about the first color channel and the second color channel can be used to identify the solder wire of the current inductive element, and thus the quality detection method 100 described herein can be implemented.

[0053] An exemplary determination manner of the first color channel and the second color channel is described below. For example, one or more inductance element images containing inductance elements of a preset type can be obtained in advance. For each inductance element image, the following operations can be performed. On the inductance element image, the positions of the pads and the bonding wires can be determined by manual labeling or target detection, etc. In addition, for the inductance element image, its single-channel images under a plurality of different preset color channels can also be extracted. The single-channel images can be grouped (for example, two by two combination), to obtain a plurality of image groups, wherein each image group contains two single-channel images. The gray value difference of the two single-channel images in each image group is obtained. Based on the difference value images corresponding to the plurality of image groups respectively and the previously determined positions of the pads and the bonding wires, the image group satisfying the following condition is determined: the gray value difference of the pads in the image group on the two color channels is less than the gray value difference of the bonding wires in the image group on the two color channels. One of the image groups satisfying the condition is determined as the target image group. The two color channels contained in the target image group are the first color channel and the second color channel. In the case where there are a plurality of image groups satisfying the condition, one of them can be randomly selected as the target image group, or the target image group can be selected according to a preset standard. For example, from the image groups satisfying the condition, the image group with the largest difference between the gray value difference of the pads in the image group on the two color channels and the gray value difference of the bonding wires in the image group on the two color channels can be selected as the target image group. In the case where there are a plurality of inductance element images, the target image group can also be determined by comprehensively considering the plurality of inductance element images. For example, from the target image groups corresponding to the plurality of inductance element images respectively, a new target image group can be determined in a similar manner as for a single inductance element image, for example, by random selection or selection based on the gray value difference, etc.

[0054] In the above technical solution, the difference value image is obtained based on the image corresponding to the first color channel and the image corresponding to the second color channel obtained from the image to be tested, and the bonding wire region is determined according to the target region and the pad region of interest in the difference value image. This method can better highlight the bonding wire by utilizing the brightness difference of the pads and the bonding wires on different color channels, which helps to more accurately determine the bonding wire region. In the case where there are complex interference (such as interference of black foreign matter, etc.) and inconsistent brightness difference of the coil, the algorithm for determining the bonding wire based on the gray value difference of the plurality of single-channel images can effectively eliminate the interference and accurately extract the bonding wire.

[0055] Exemplarily, before the region in the difference value image with a gray value difference greater than a first preset gray threshold is determined as the target region, the method can further include: performing image stretching on the difference value image.

[0056] In an embodiment, the difference image can be subjected to image stretching, i.e. gray scale stretching. Image stretching is mainly used to improve the contrast of the image, so that the wire further becomes more prominent and is better identified. For example, the pixel value of each pixel in the difference image can be multiplied by a certain coefficient to stretch the difference image. The certain coefficient can be any numerical value, for example 50. Alternatively, pixels with smaller pixel values in the difference image can also be divided by a certain coefficient, and pixels with larger pixel values can be multiplied by a certain coefficient. For example, pixels with pixel values less than or equal to 120 in the difference image are divided by a certain coefficient 50, and pixels with pixel values greater than 120 in the difference image are multiplied by a certain coefficient 50, thereby stretching the difference image.

[0057] According to the above technical solution, by performing gray scale stretching on the difference image, the light and dark contrast in the image can be further enhanced to further highlight the target region containing the wire, which helps to reduce the difficulty of subsequently determining the target region and improve the accuracy of determining the target region.

[0058] Exemplarily, the first color channel and the second color channel also satisfy the following condition: on the inductor element image containing the inductor element of the preset type, the difference between the gray scale values of the pads on the first color channel and the second color channel is less than a second preset gray scale threshold.

[0059] The determination manner of the first color channel and the second color channel satisfying the condition that the difference between the gray scale values of the pads on the first color channel and the second color channel is less than the second preset gray scale threshold is similar to the determination manner of the first color channel and the second color channel satisfying the condition that the difference between the gray scale values of the pads on the first color channel and the second color channel is less than the difference between the gray scale values of the wire on the first color channel and the second color channel, i.e. it can also be determined in advance by theoretical and / or experimental methods, etc.

[0060] In one embodiment, the user can set a second preset gray scale threshold according to the requirement. The second preset gray scale threshold can be used to determine the first color channel and the second color channel in different color channels. The second preset gray scale threshold can also be any value between 0 and 255. For example, the second preset gray scale threshold can be 100. Exemplarily, for the case that the inductance element image containing the inductance element of the preset type is an RGB image, the inductance element image can include three channels of R, G and B. The gray scale value difference of the pads in the R channel and the G channel, the R channel and the B channel and the G channel and the B channel is obtained respectively. Based on the obtained multiple gray scale value differences, the two color channels with the gray scale value difference less than the second preset gray scale threshold (i.e. 100) can be determined as the first color channel and the second color channel. For example, the difference between the gray scale values of the respective pixels of the pads corresponding to the R channel and the G channel is less than the second preset gray scale threshold, so the R channel can be determined as the first color channel and the G channel as the second color channel. It can be understood that if there are multiple gray scale value differences less than the second preset gray scale threshold, the two color channels corresponding to the smallest gray scale value difference can be optionally determined as the first color channel and the second color channel.

[0061] According to the above technical solution, the gray scale value difference of the pads on the first color channel and the second color channel is small, so that when the image corresponding to the two determined color channels is subtracted in gray scale value, the pads can be more easily filtered out, thereby further reducing the difficulty of determining the bonding wire.

[0062] Exemplarily, the multiple sub-regions can include one or more of a first sub-region, a second sub-region, a third sub-region and a fourth sub-region, wherein the first sub-region is a region where the free end of the bonding wire is expected to fall into; the second sub-region and the third sub-region are regions where the bonding wire is not expected to fall into; and the fourth sub-region is a region where the connecting end of the bonding wire is expected to fall into.

[0063] For the bonding wire, one end connected with the wire part outside the pad region of interest (mainly the wire part of the inductance element wound on the insulating tube) can be the connecting end of the bonding wire, and the other end away from the wire part outside the pad region of interest opposite to the connecting end of the bonding wire can be the free end.

[0064] Figure 3 A schematic diagram showing that the pad region of interest contains four sub-regions according to one embodiment of the present application is shown. As Figure 3As shown, the white line frame can represent the boundary between each sub-region. The image region contained in the largest rectangular frame 310 is the pad region of interest. The first sub-region 312 can represent the region where the free end of the wire is expected to fall. The second sub-region 314 and the third sub-region 318 are located on both sides of the wire and are regions where the wire is not expected to fall. The fourth sub-region 316 can represent the region where the connecting end of the wire is expected to fall.

[0065] The number of sub-regions on the pad region of interest and the size of each sub-region can be set as needed, and the present application does not limit this. The plurality of sub-regions can be arbitrarily divided as needed, which can include all of the above first sub-region, second sub-region, third sub-region and fourth sub-region, or only include part of the sub-regions. In the case where the plurality of sub-regions include one or more of the above four sub-regions, the plurality of sub-regions can also include other sub-regions different from the above four sub-regions.

[0066] According to the above technical solution, the sub-regions in the pad region of interest are divided in the above manner, and the distribution of the wire is limited in a more scientific manner.

[0067] Exemplarily, according to the distribution of the wire region in each of the plurality of sub-regions in the pad region of interest and the detection standard corresponding to each sub-region, determining whether the position of the wire on the target pad portion is qualified can include: if the wire region falls into the first sub-region, determining that the judgment result corresponding to the first sub-region is qualified, otherwise determining that the judgment result corresponding to the first sub-region is unqualified; if the wire region falls into the second sub-region, determining that the judgment result corresponding to the second sub-region is unqualified, otherwise determining that the judgment result corresponding to the second sub-region is qualified; if the wire region falls into the third sub-region, determining that the judgment result corresponding to the third sub-region is unqualified, otherwise determining that the judgment result corresponding to the third sub-region is qualified; if the wire region falls into the fourth sub-region and the length in the fourth sub-region is greater than a preset length threshold, determining that the judgment result corresponding to the fourth sub-region is qualified, otherwise determining that the judgment result corresponding to the fourth sub-region is unqualified.

[0068] Reference Figure 3For the first sub-region 312, the case that the wire bonding region falls into the first sub-region 312 can be judged as qualified. The case that the wire bonding region does not fall into the first sub-region 312 can be judged as unqualified. Exemplarily, the first sub-region 312 is set such that, in a normal state, the length and / or area of the wire bonding region of the inductor element that falls into the first sub-region accounts for one third or close to one third of the total length and / or area of the wire bonding region. Since the length of the wire bonding needs to be guaranteed, in the normal state, it is expected that the free end of the inductor element should be able to fall into the first sub-region 312, and if it does not, it can be judged that the wire bonding region in the current first sub-region 312 is unqualified. For the second sub-region 314 and the third sub-region 318, the case that the wire bonding region does not fall into the second sub-region 314 or the third sub-region 318 can be judged as qualified. The case that the wire bonding region falls into the second sub-region 314 or the third sub-region 318 can be judged as unqualified. Similarly to the first sub-region 312, in the normal state, it is expected that the inductor element should not fall into the second sub-region 314 or the third sub-region 318, and if it does, it can be judged that the wire bonding region contained in the current second sub-region 314 or the third sub-region 318 is unqualified. For the fourth sub-region 316, the user can pre-set a length threshold for the wire bonding region to fall into the fourth sub-region. For example, the pre-set length threshold can be 0.5 mm. The case that the wire bonding region falls into the fourth sub-region and the length of the wire bonding region in the fourth sub-region is greater than 0.5 mm can be judged as qualified. The case that the wire bonding region falls into the fourth sub-region but the length of the wire bonding region in the fourth sub-region is less than or equal to 0.5 mm, or the case that the wire bonding region does not fall into the fourth sub-region, can be judged as unqualified. By limiting the length of the wire bonding region in the fourth sub-region, the presence of problems such as wire bonding loss can be detected.

[0069] Alternatively, in addition to the pre-set length threshold, a pre-set area threshold or a pre-set continuity threshold can also be set. Exemplarily, the pre-set area threshold can represent a threshold corresponding to the ratio of the area of the wire bonding region in the fourth sub-region to the area of the total wire bonding region. The pre-set continuity threshold can represent a threshold corresponding to the ratio of the longest continuous part of the wire bonding region in the fourth sub-region to the total wire bonding region in the fourth sub-region.

[0070] According to the above technical solution, based on the falling and not falling of the wire bonding region in the multiple sub-regions in the pad region of interest and the length, it can be simply and intuitively judged whether the position of the wire bonding region in each sub-region is qualified.

[0071] Exemplarily, before determining the position of the pad region of interest corresponding to the region of interest in the to-be-measured image according to the region of interest on the template image, the method can further include: obtaining the template image; determining the positions of the multiple sub-regions in the region of interest on the template image based on the region division information input by the user.

[0072] In one embodiment, to determine the position of the pad region of interest corresponding to the region of interest in the image to be tested, a template image can be obtained first and the region of interest in the template image can be determined. The method of obtaining the template image is similar to the step S110 described above, and thus will not be described here for brevity. According to the obtained template image, the region of interest can be labeled by using a label box of any shape through manual labeling or automatic labeling by a computer.

[0073] For the obtained region of interest, the user can input region division information. The division information can be used to divide the region of interest into a plurality of sub-regions. For example, the region division information can include the area corresponding to each sub-region and the boundary points, etc. The plurality of sub-regions in the region of interest correspond one-to-one to the plurality of sub-regions in the pad region of interest.

[0074] According to the technical solution described above, the plurality of sub-regions can be divided in the region of interest of the template image based on the region division information input by the user. This division method allows the user to customize each sub-region, so that the divided sub-regions are more in line with the user's expectations, and thus the accuracy, reliability and user experience of the division are higher. In addition, the user can freely set the position of the sub-region according to the detection requirements, which can effectively avoid a large number of parameter adjustment processes.

[0075] Exemplarily, the plurality of sub-regions can include one or more of a first sub-region, a second sub-region, a third sub-region and a fourth sub-region, wherein the first sub-region is a region where the free end of the wire is expected to fall into; the second sub-region and the third sub-region are respectively regions where the wire is not expected to fall into; and the fourth sub-region is a region where the connecting end of the wire is expected to fall into.

[0076] The foregoing has been described in conjunction with Figure 3 The above four sub-regions have been described in detail, and thus will not be described here for brevity.

[0077] Exemplarily, the region division information includes edge information related to the first initial region, the second initial region and the third initial region respectively, and determining the positions of the plurality of sub-regions in the region of interest on the template image based on the region division information input by the user can include: calculating the difference set between the region of interest and the regions contained in the edge information to obtain a fourth sub-region; determining two target points on the edge of the fourth sub-region that are closest to two distal vertices of the region of interest respectively, the two distal vertices being two vertices on the region of interest that are located at the distal end along the extension direction of the wire; connecting the two distal vertices to the corresponding target points respectively to obtain two target edges; and dividing the region of interest into the first sub-region, the second sub-region, the third sub-region and the fourth sub-region through the two target edges and the edge of the fourth sub-region.

[0078] In one embodiment, the first initial region, the second initial region and the third initial region contained in the region division information can be artificially divided regions. Figure 4 A diagram illustrating division of initial regions in a region of interest according to one embodiment of the present application is shown. As shown in Figure 4 The user can simply divide the approximate positions of the first sub-region, the second sub-region and the third sub-region to obtain the first initial region 420, the second initial region 430 and the third initial region 440. The edges of these initial regions can be set relatively arbitrarily, and the shapes can be irregular and can exceed the edges of the region of interest 410 in the template image. The remaining part of the region of interest 410 obtained by subtracting the part of the first initial region, the part of the second initial region and the part of the third initial region contained in the region of interest from the region of interest 410 can be used as the fourth sub-region. Figure 5 A diagram illustrating obtaining of the fourth sub-region from the region of interest and the initial regions divided by the user according to one embodiment of the present application is shown. As shown in Figure 5 The fourth sub-region 510 can be obtained by the above subtraction method.

[0079] Subsequently, the distances from the two distal vertices of the region of interest to all points on the outer edges of the fourth sub-region can be calculated respectively, and the points corresponding to the minimum values of the distances are determined as the target points. As shown in Figure 3 The points A and B are respectively the two distal vertices of the region of interest along the extension direction of the wire. The points C and D are respectively the two target points on the edges of the fourth sub-region closest to the two distal vertices of the region of interest. After connecting the distal vertex A to the target point C and the distal vertex B to the target point D, the region of interest can be divided into four sub-regions, which are the first sub-region, the second sub-region, the third sub-region and the fourth sub-region. The four sub-regions divided by the connecting lines can be referred to the example of Figure 3 .

[0080] According to the above technical solution, the fourth sub-region is obtained by calculating the difference set between the region of interest and the region contained in the edge information of the initial region, and further other sub-regions are determined. This method allows the user to roughly divide the initial regions, and the system further automatically divides the complete multiple sub-regions according to the initial regions divided by the user. This solution has a lower requirement for the user's operation, a high degree of automation and a good user experience.

[0081] Exemplarily, the method 100 can further include receiving edge adjustment information input by the user, and adjusting the positions of the points on the edges of any of the multiple sub-regions based on the edge adjustment information.

[0082] In one embodiment, the edge adjustment information can include displacement information input by a user to control a node on the edge to move and / or a drag operation of the user on the node. For example, a plurality of nodes can be included in the edge contour of each sub-region, and the user can drag some of the plurality of nodes to adjust the edge contour of the sub-region. In addition, the user can also click to select the node to be adjusted, and input displacement information to be adjusted, and the system can automatically control the node to move a corresponding distance according to the displacement information.

[0083] According to the above technical solution, the position of any node on the edge of any sub-region can be flexibly adjusted, and the range contained in the sub-region is further adjusted. The method is simple to operate and easy to implement, and has a high degree of freedom for user operation.

[0084] Exemplarily, the method can further include: receiving position adjustment information input by a user; and adjusting the overall position of any sub-region of the plurality of sub-regions based on the position adjustment information.

[0085] In one embodiment, a plurality of sub-regions can be displayed in the user interface. The user can select a sub-region to be adjusted, and then drag the mouse to move the entire sub-region to an adjusted position. Based on the drag operation of the user, the overall position of one or more sub-regions can be adjusted. In another embodiment, the user can also select a sub-region to be adjusted by clicking the mouse, and then input displacement information for adjustment. For example, 0.2 mm to the right. Based on the adjustment information, the selected sub-region can be translated 0.2 mm to the right. The overall position of one or more sub-regions can also be adjusted by this method.

[0086] According to the above technical solution, the overall position of any sub-region of the plurality of sub-regions can be flexibly adjusted, and the range contained in the sub-region is further adjusted. The method is simple to operate and easy to implement, and has a high degree of freedom for user operation.

[0087] According to another aspect of the present application, a quality detection device of an inductive element is also provided. Figure 6 A schematic block diagram of a quality detection device 600 of an inductive element according to one embodiment of the present application is shown, as shown in the figure, the device 600 can include a first acquisition module 610, a first determination module 620, a second determination module 630 and a third determination module 640. Figure 6

[0088] The first acquisition module 610 is configured to acquire a to-be-tested image, and the to-be-tested image contains an inductive element.

[0089] ​The first determining module 620 is configured to determine a position of a region of interest pad area corresponding to the region of interest in the to-be-tested image according to the region of interest on the template image, where the template image is an inductor element image marked with position information of the region of interest, the region of interest is a region in which a pad part of interest is located, the region of interest pad area contains a target pad part corresponding to the pad part of interest, and the region of interest and the region of interest pad area each include a plurality of sub-regions, each of which has a corresponding detection criterion, and the plurality of sub-regions in the region of interest pad area correspond one-to-one to the plurality of sub-regions in the region of interest.

[0090] The second determining module 630 is configured to determine a wire region in which the wire is located within the region of interest pad area.

[0091] The third determining module 640 is configured to determine whether the position of the wire on the target pad part is qualified according to a distribution of the wire region in each of the plurality of sub-regions in the region of interest pad area and the corresponding detection criterion of each of the plurality of sub-regions.

[0092] For example, the third determining module 640 includes an intersection sub-module configured to, for any sub-region, perform an intersection operation between the wire region and the sub-region, a judgment sub-module configured to, for any sub-region, determine whether the position of the wire in the sub-region is qualified according to the intersection result and the corresponding detection criterion of the sub-region to obtain a judgment result corresponding to the sub-region, and a first determining sub-module configured to comprehensively determine whether the position of the wire on the target pad part is qualified according to the judgment results corresponding to the plurality of sub-regions in the region of interest pad area.

[0093] For example, the apparatus 600 further includes an obtaining module configured to obtain images corresponding to the first color channel and the second color channel based on the to-be-tested image before the second determining module 630 determines the wire region in which the wire is located within the region of interest pad area, a gray value subtraction module configured to perform a gray value subtraction operation between the image corresponding to the first color channel and the image corresponding to the second color channel to obtain a difference image, where the first color channel and the second color channel satisfy the following condition: in an inductor element image containing an inductor element of a preset type, a gray value difference of the pad on the first color channel and the second color channel is less than a gray value difference of the wire on the first color channel and the second color channel, and the to-be-tested inductor element belongs to the inductor element of the preset type, and a fourth determining module configured to determine a region in which a gray value difference is greater than a first preset gray threshold in the difference image as a target region, where the second determining module 630 includes a second determining sub-module configured to determine an intersection of the region of interest pad area and the target region as the wire region.

[0094] Exemplarily, the apparatus 600 further comprises a stretching module configured to perform image stretching on the difference image before the fourth determining module determines the region with the gray value difference greater than the first preset gray threshold in the difference image as the target region.

[0095] Exemplarily, the first color channel and the second color channel further satisfy the following condition: on the inductance element image containing the inductance element of the preset type, the gray value difference of the solder pad on the first color channel and the second color channel is less than a second preset gray threshold.

[0096] Exemplarily, the plurality of sub-regions comprises one or more of a first sub-region, a second sub-region, a third sub-region, and a fourth sub-region, wherein the first sub-region is a region where a free end of the bonding wire is expected to fall into; the second sub-region and the third sub-region are respectively regions where the bonding wire is not expected to fall into; and the fourth sub-region is a region where a connection end of the bonding wire is expected to fall into.

[0097] Exemplarily, the third determining module 640 comprises: a third determining submodule configured to determine that a judgment result corresponding to the first sub-region is qualified if the bonding wire region falls into the first sub-region, and otherwise determine that the judgment result corresponding to the first sub-region is unqualified; a fourth determining submodule configured to determine that a judgment result corresponding to the second sub-region is unqualified if the bonding wire region falls into the second sub-region, and otherwise determine that the judgment result corresponding to the second sub-region is qualified; a fifth determining submodule configured to determine that a judgment result corresponding to the third sub-region is unqualified if the bonding wire region falls into the third sub-region, and otherwise determine that the judgment result corresponding to the third sub-region is qualified; and a sixth determining submodule configured to determine that a judgment result corresponding to the fourth sub-region is qualified if the bonding wire region falls into the fourth sub-region and a length within the fourth sub-region is greater than a preset length threshold, and otherwise determine that the judgment result corresponding to the fourth sub-region is unqualified.

[0098] Exemplarily, the apparatus 600 further comprises a second obtaining module configured to obtain a template image before the first determining module 620 determines the position of the region of interest pad corresponding to the region of interest in the to-be-tested image according to the region of interest on the template image; and a fifth determining module configured to determine the positions of a plurality of sub-regions in the region of interest on the template image based on region division information input by a user.

[0099] Exemplarily, the plurality of sub-regions comprises one or more of a first sub-region, a second sub-region, a third sub-region, and a fourth sub-region, wherein the first sub-region is a region where a free end of the bonding wire is expected to fall into; the second sub-region and the third sub-region are respectively regions where the bonding wire is not expected to fall into; and the fourth sub-region is a region where a connection end of the bonding wire is expected to fall into.

[0100] For example, the region division information includes edge information related to the first initial region, the second initial region, and the third initial region, respectively. The fifth determining module includes: a calculation submodule, used to calculate the difference between the region of interest and the region contained in the edge information to obtain a fourth sub-region; a seventh determining submodule, used to determine the two target points on the edge of the fourth sub-region that are closest to the two far vertices of the region of interest, respectively, where the two far vertices are two vertices on the region of interest located at the far end along the extension direction of the welding line; a connecting submodule, used to connect the two far vertices to the corresponding target points respectively to obtain two target edges; and a dividing submodule, used to divide the region of interest into a first sub-region, a second sub-region, a third sub-region, and a fourth sub-region using the two target edges and the edge of the fourth sub-region.

[0101] For example, the device 600 further includes: a first receiving module for receiving edge adjustment information input by a user; and a first adjustment submodule for adjusting the position of a point on the edge of any sub-region in the plurality of sub-regions based on the edge adjustment information.

[0102] For example, the device 600 further includes: a second receiving module for receiving position adjustment information input by a user; and a second adjustment submodule for adjusting the overall position of any one of the multiple sub-regions based on the position adjustment information.

[0103] According to another aspect of the present invention, an electronic device is also provided. Figure 7 A schematic block diagram of an electronic device 700 according to an embodiment of the present invention is shown. Figure 7 As shown, the electronic device 700 may include a processor 710 and a memory 720. The memory 720 stores a computer program, and the processor 710 executes the computer program to implement the aforementioned inductor element quality detection method 100.

[0104] According to another aspect of the present invention, a storage medium is also provided. It stores a computer program / instructions, which, when executed by a processor, implement the aforementioned inductor element quality detection method 100. The storage medium may, for example, include a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0105] Those skilled in the art can understand the specific implementation schemes of the aforementioned inductor quality testing device, electronic device, and storage medium by reading the above description of the inductor quality testing method. For the sake of brevity, they will not be described in detail here.

[0106] Although example embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the example embodiments are only exemplary and are not intended to limit the scope of the present application. Those skilled in the art can make various changes and modifications of the example embodiments without departing from the scope and spirit of the present application. All such changes and modifications are intended to be within the scope of the present application as claimed.

[0107] Those skilled in the art can realize the units and algorithm steps with the examples described in connection with the embodiments disclosed herein can be realized in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the particular application and design constraints. Those skilled in the art can realize the described functions in a variety of ways using the techniques disclosed herein without departing from the scope and spirit of the present application.

[0108] It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of both hardware and software, and any combination thereof. In a unit claim, several elements can be presented with a comma between them. Such presentation is merely an epigrammatic and pedagogical device, used to more readily discern the components of a unit. Separate units can be listed with a comma separating them. Multiple, distinct components can be described as conjunctively encompassed by a single expression. These are an ongoing convenience, suitable for the sake of discourse, and are not dispositive. The use of the word "first" does not necessarily mean "second", and vice versa. Nor is the word "first" necessarily the aforementioned prior element(s) to which a given element does not relate. The use of the terms first and second does not imply any particular order. These terms can be understood to be used merely as names.

[0109] The above description is provided as an enabling teaching of the application and is not intended to limit the scope of the application. Within the scope of the appended claims, any changes or modifications in the examples described can be made. The scope of the application is therefore to be understood as not limited by the specific examples described above.

Claims

1. A method of quality detection of an inductive element, characterized by, The method comprises: obtaining a to-be-tested image, the to-be-tested image containing a to-be-tested inductor element; determining a position of a region of interest pad area in the to-be-tested image corresponding to a region of interest on a template image, wherein the template image is an inductor element image marked with position information of the region of interest, the region of interest is a region in which a pad part of interest is located, the region of interest pad area contains a target pad part corresponding to the pad part of interest, the region of interest and the region of interest pad area each include a plurality of sub-regions, each sub-region has a corresponding detection criterion, and the plurality of sub-regions in the region of interest pad area correspond one-to-one to the plurality of sub-regions in the region of interest; determining, in the region of interest pad area, a wire region in which a wire is located; determining, according to a distribution of the wire region in each of the plurality of sub-regions in the region of interest pad area and the corresponding detection criterion of each sub-region, whether a position of the wire on the target pad part is qualified.

2. The method of claim 1, wherein, The determining, according to the distribution of the wire region in each of the plurality of sub-regions in the region of interest pad area and the corresponding detection criterion of each sub-region, whether the position of the wire on the target pad part is qualified comprises: for any sub-region, intersecting the wire region with the sub-region; judging, according to an intersection result and the corresponding detection criterion of the sub-region, whether the position of the wire in the sub-region is qualified, to obtain a judgment result corresponding to the sub-region; integrating the judgment results corresponding to the plurality of sub-regions in the region of interest pad area respectively to determine whether the position of the wire on the target pad part is qualified.

3. The method of claim 1, wherein before the determining, in the region of interest pad area, the wire region in which the wire is located, the method further comprises: obtaining images corresponding to a first color channel and a second color channel based on the to-be-tested image; subtracting gray value of the image corresponding to the first color channel from gray value of the image corresponding to the second color channel to obtain a difference image, wherein the first color channel and the second color channel satisfy the following condition: in an inductor element image containing an inductor element of a preset type, a difference in gray value of a pad on the first color channel and the second color channel is less than a difference in gray value of a wire on the first color channel and the second color channel, and the to-be-tested inductor element belongs to the inductor element of the preset type; determining a region in which a difference in gray value is greater than a first preset gray threshold in the difference image as a target region; the determining, in the region of interest pad area, the wire region in which the wire is located comprises: determining an intersection of the region of interest pad area and the target region as the wire region.

4. The method of claim 3, wherein, Before the determining a region in which a difference in gray value is greater than a first preset gray threshold in the difference image as a target region, the method further comprises: performing image stretching on the difference image.

5. The method of claim 3, wherein, The first color channel and the second color channel also satisfy the following condition: on the inductance element image containing the inductance element of the preset type, the difference in grayscale values of the pads on the first color channel and the second color channel is less than a second preset grayscale threshold.

6. The method of any one of claims 1-5, wherein, The plurality of sub-regions include one or more of a first sub-region, a second sub-region, a third sub-region, and a fourth sub-region, wherein, The first sub-region is a region where a free end of the wire is expected to fall into; The second sub-region and the third sub-region are respectively regions where the wire is not expected to fall into; The fourth sub-region is a region where a connection end of the wire is expected to fall into.

7. The method of claim 6, wherein, The determining whether the position of the wire on the target pad part is qualified according to the distribution of the wire region in each of the plurality of sub-regions of the pad region of interest and the detection standard corresponding to each sub-region includes: If the wire region falls into the first sub-region, it is determined that the judgment result corresponding to the first sub-region is qualified, otherwise it is determined that the judgment result corresponding to the first sub-region is unqualified; If the wire region falls into the second sub-region, it is determined that the judgment result corresponding to the second sub-region is unqualified, otherwise it is determined that the judgment result corresponding to the second sub-region is qualified; If the wire region falls into the third sub-region, it is determined that the judgment result corresponding to the third sub-region is unqualified, otherwise it is determined that the judgment result corresponding to the third sub-region is qualified; If the wire region falls into the fourth sub-region and the length in the fourth sub-region is greater than a preset length threshold, it is determined that the judgment result corresponding to the fourth sub-region is qualified, otherwise it is determined that the judgment result corresponding to the fourth sub-region is unqualified.

8. The method of any one of claims 1-5, wherein, Before the determining the position of the pad region of interest corresponding to the region of interest in the to-be-detected image according to the region of interest on the template image, the method further includes: Obtaining the template image; Determining the positions of a plurality of sub-regions in the region of interest on the template image based on region division information input by a user.

9. The method of claim 8, wherein, The plurality of sub-regions include one or more of a first sub-region, a second sub-region, a third sub-region, and a fourth sub-region, wherein, The first sub-region is a region where a free end of the wire is expected to fall into; The second sub-region and the third sub-region are respectively regions where the wire is not expected to fall into; The fourth sub-region is a region where a connection end of the wire is expected to fall into.

10. The method of claim 9, wherein, The region division information includes edge information related to a first initial region, a second initial region, and a third initial region, respectively, and the determining the positions of a plurality of sub-regions in the region of interest on the template image based on the region division information input by a user includes: Calculating a difference set between the region of interest and a region contained in the edge information to obtain the fourth sub-region; Determining two target points on the edge of the fourth sub-region that are closest to two distal vertices of the region of interest, respectively, the two distal vertices being two vertices on the region of interest located at the distal end along the extension direction of the wire. connecting the two far-end vertices with the corresponding target points respectively to obtain two target edges; dividing the region of interest into the first sub-region, the second sub-region, the third sub-region and the fourth sub-region through the two target edges and the edge of the fourth sub-region.

11. The method of claim 8, wherein, The method further comprises: receiving edge adjustment information input by a user; adjusting the position of a point on the edge of any of the plurality of sub-regions based on the edge adjustment information.

12. The method of claim 8, wherein, The method further comprises: receiving position adjustment information input by a user; adjusting the overall position of any of the plurality of sub-regions based on the position adjustment information.

13. A mass detection device for an inductive element, characterized by comprise: a first acquisition module, configured to acquire a to-be-tested image, the to-be-tested image containing a to-be-tested inductance element; a first determination module, configured to determine the position of a region of interest pad area corresponding to a region of interest in the to-be-tested image according to the region of interest on a template image, wherein the template image is an inductance element image marked with position information of the region of interest, the region of interest is a region where a pad part of interest is located, the region of interest pad area contains a target pad part corresponding to the pad part of interest, the region of interest and the region of interest pad area each comprise a plurality of sub-regions, each sub-region has a corresponding detection standard, and the plurality of sub-regions in the region of interest pad area correspond one-to-one to the plurality of sub-regions in the region of interest; a second determination module, configured to determine a wire region where a wire is located within the region of interest pad area; a third determination module, configured to determine whether the position of the wire on the target pad part is qualified according to the distribution of the wire region in each of the plurality of sub-regions in the region of interest pad area and the detection standard corresponding to each sub-region.

14. An electronic device, comprising: comprise a processor and a memory, the memory storing a computer program, and the processor executes the computer program to implement the quality detection method of the inductance element according to any one of claims 1-12.

15. A storage medium, characterized by store a computer program / instruction, which, when executed by a processor, implements the quality detection method of the inductance element according to any one of claims 1-12.

Images