CN117291940A

CN117291940A - Method for dividing image of thin film capacitor electrode and electronic equipment

Info

Publication number: CN117291940A
Application number: CN202311047166.4A
Authority: CN
Inventors: 张元�; 杨再学; 陈皓天; 陈斌
Original assignee: Harbin Institute of Technology; Chongqing Research Institute of Harbin Institute of Technology
Current assignee: Harbin Institute of Technology; Chongqing Research Institute of Harbin Institute of Technology
Priority date: 2023-08-18
Filing date: 2023-08-18
Publication date: 2023-12-26

Abstract

The application provides a thin film capacitor electrode image segmentation method and electronic equipment. The method comprises the following steps: compressing an original image obtained by shooting a base film according to a preset compression ratio to obtain a compressed first image; performing open operation processing on the first image to obtain a second image; performing binarization processing on the second image to obtain a third image; performing edge segmentation on the third image through a preset double-threshold processing strategy to obtain an edge segmentation graph of the electrode plate in the third image; determining the corner coordinates of each electrode slice from a third image with an edge segmentation map; determining the corresponding angular point coordinates of each electrode slice in the original image according to the preset compression ratio and the angular point coordinates of each electrode slice; and dividing the original image to obtain a graph area of each electrode slice based on the corresponding angular point coordinates in the original image and the preset size of the electrode slice. Therefore, the accuracy and the efficiency of dividing the independent electrode slice areas from the original image are improved.

Description

Method for dividing image of thin film capacitor electrode and electronic equipment

Technical Field

The invention relates to the technical field of computer image processing, in particular to a thin film capacitor electrode image segmentation method and electronic equipment.

Background

In the field of image segmentation processing, the requirements of different scenes on segmentation algorithms are different, so that it is difficult to adapt one segmentation algorithm to all scenes for segmentation, and particularly under the requirements of high efficiency and high accuracy, the difficulty is multiplied in balance. In the manufacturing process of the thin film capacitor, it is generally required to detect the electrode sheet (or the internal electrode) of the thin film capacitor to ensure the quality of the electrode sheet. The electrode pads are typically printed on a flexible substrate, i.e., a substrate is printed with a plurality of electrode pads. The base film formed by the flexible film material is easy to deform, and the number of electrode plates is huge and reaches hundreds of thousands or even more complex scenes, at present, whether template matching or projection or other modes are adopted, and due to the characteristics of huge and dense segmentation number, easy deformation and deflection of the flexible material, and the like, the two indexes of high segmentation efficiency and high segmentation accuracy are difficult to meet simultaneously.

Disclosure of Invention

In view of the above, an object of the embodiments of the present application is to provide a method for dividing a thin film capacitor electrode image and an electronic device, which are beneficial to improving efficiency and accuracy of dividing an independent electrode sheet region from an image.

In order to achieve the technical purpose, the technical scheme adopted by the application is as follows:

in a first aspect, an embodiment of the present application provides a method for dividing a thin film capacitor electrode image, where the method includes:

acquiring an original image obtained by shooting a base film, wherein the base film comprises a plurality of electrode plates which are used for manufacturing a thin film capacitor and are arranged in an array;

compressing the original image according to a preset compression ratio to obtain a compressed first image;

performing open operation processing on the first image to obtain a second image;

performing binarization processing on the second image to obtain a third image;

performing edge segmentation on the third image through a preset double-threshold processing strategy to obtain an edge segmentation graph of the electrode slice in the third image;

determining corner coordinates of each electrode slice from the third image with the edge segmentation map;

determining the corresponding angular point coordinates of each electrode plate in the original image according to the preset compression ratio and the angular point coordinates of each electrode plate;

and dividing the original image to obtain a region of each electrode slice based on the corresponding angular point coordinates in the original image and the preset size of the electrode slice.

With reference to the first aspect, in some optional embodiments, performing edge segmentation on the third image by using a preset dual-threshold processing policy to obtain an edge segmentation map of the electrode slice in the third image, where the edge segmentation map includes:

determining the gradient amplitude and gradient direction of each pixel point in the third image;

marking the pixel points with gradient amplitude values larger than a first preset threshold value as first-class pixel points representing strong edges;

marking the pixel points with gradient amplitude values larger than a second preset threshold value and smaller than or equal to the first preset threshold value as second class pixel points representing weak edges, wherein the second preset threshold value is smaller than the first preset threshold value;

marking the pixel points with the gradient amplitude smaller than or equal to the second preset threshold value as third-class pixel points representing non-edges;

and obtaining an edge segmentation map of the electrode slice in the third image according to the first type pixel point, the second type pixel point and the third type pixel point through a preset edge tracking strategy.

With reference to the first aspect, in some optional embodiments, according to the first type of pixel point, the second type of pixel point, and the third type of pixel point, by using a preset edge tracking policy, an edge segmentation map of an electrode slice in the third image is obtained, including:

adding the first type pixel points in the first image to an edge result;

updating the second type pixel points adjacent to the first type pixel points into new first type pixel points, and adding the new first type pixel points into the edge result;

repeating the steps to update the second type pixel points adjacent to the first type pixel points into new first type pixel points, and adding the new first type pixel points into the edge result until all the second type pixel points are traversed, wherein the pixel points in the edge result form the edge segmentation graph.

With reference to the first aspect, in some optional embodiments, binarizing the second image to obtain a third image includes:

and setting a foreground region in the second image to be white, and setting a background region in the second image to be black, so as to obtain the third image.

With reference to the first aspect, in some optional embodiments, the width of the contour line of the edge segmentation map is two pixels and is white, and determining the corner coordinates of each electrode slice from the third image with the edge segmentation map includes:

traversing a pixel point with a gray value of 255 in the first image with the edge segmentation map;

and if the edge gray value of the layer where the current pixel point is located is 255, the edge gray value of the inner layer is 255, and the edge gray value of the inner two layers is the gray value of the electrode plate, taking the position of the current pixel point as the angular point coordinate of the electrode plate.

With reference to the first aspect, in some optional embodiments, the corner coordinates include corner coordinates of an upper left corner of the electrode pad.

With reference to the first aspect, in some optional embodiments, a region of each electrode pad is associated with a corresponding coordinate, and the region of each electrode pad is used as a region of interest for electrode pad defect detection.

In a second aspect, an embodiment of the present application further provides an electronic device, where the electronic device includes a processor and a memory coupled to each other, where the memory stores a computer program, and when the computer program is executed by the processor, causes the electronic device to perform the method described above.

The invention adopting the technical scheme has the following advantages:

in the technical scheme provided by the application, an original image obtained by shooting a base film is obtained; and compressing the original image according to a preset compression ratio to obtain a compressed first image. The compressed first image is used for carrying out operation processing, so that the operation amount is reduced, and the image segmentation efficiency is improved. Then, performing open operation processing on the first image to obtain a second image; performing binarization processing on the second image to obtain a third image; performing edge segmentation on the third image through a preset double-threshold processing strategy to obtain an edge segmentation graph of the electrode slice in the third image, wherein the width of an edge line in the edge segmentation graph is at least two pixel widths; determining the corner coordinates of each electrode slice from a third image with an edge segmentation map; determining the corresponding angular point coordinates of each electrode slice in the original image according to the preset compression ratio and the angular point coordinates of each electrode slice; and dividing the original image to obtain a graph area of each electrode slice based on the corresponding angular point coordinates in the original image and the preset size of the electrode slice. Therefore, when the base film is deformed and skewed, accurate segmentation can be performed, so that the accuracy and the efficiency of segmenting the independent electrode slice regions from the original image are improved.

Drawings

The present application may be further illustrated by the non-limiting examples given in the accompanying drawings. It is to be understood that the following drawings illustrate only certain embodiments of the present application and are therefore not to be considered limiting of its scope, for the person of ordinary skill in the art may derive other relevant drawings from the drawings without inventive effort.

Fig. 1 is a flow chart of a method for dividing an image of a thin film capacitor electrode according to an embodiment of the present application.

Fig. 2 is a schematic diagram of an original image according to an embodiment of the present application.

Fig. 3 is a schematic diagram of a single electrode sheet according to an embodiment of the present application.

Fig. 4 is a schematic diagram of a single electrode sheet after binarization according to an embodiment of the present application.

Fig. 5 is a schematic diagram of comparison between a binarized image provided in an embodiment of the present application before and after edge segmentation.

Fig. 6 is a schematic diagram of an edge segmentation diagram of a single electrode slice according to an embodiment of the present application.

Fig. 7 is a schematic view of a portion of an edge line of an electrode sheet according to an embodiment of the present application.

Fig. 8 is a schematic diagram of a positioning point of an upper left corner of an electrode sheet according to an embodiment of the present application.

Detailed Description

The present application will be described in detail below with reference to the drawings and the specific embodiments, and it should be noted that in the drawings or the description of the specification, similar or identical parts use the same reference numerals, and implementations not shown or described in the drawings are in a form known to those of ordinary skill in the art. In the description of the present application, the terms "first," "second," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.

Referring to fig. 1, an embodiment of the present application provides a method for dividing a thin film capacitor electrode image, which can be applied to an electronic device, and the electronic device executes or implements each step of the method.

The electronic device may include a processing module and a storage module. The memory module stores a computer program which, when executed by the processing module, enables the electronic device to perform the respective steps in the thin film capacitive electrode image segmentation method described below.

The electronic device may be, but is not limited to, a personal computer, a server, or the like. The thin film capacitor electrode image segmentation method can comprise the following steps:

step 110, obtaining an original image obtained by shooting a base film, wherein the base film comprises a plurality of electrode plates which are arranged in an array and are used for manufacturing a thin film capacitor;

step 120, compressing the original image according to a preset compression ratio to obtain a compressed first image;

step 130, performing an open operation on the first image to obtain a second image;

step 140, performing binarization processing on the second image to obtain a third image;

step 150, performing edge segmentation on the third image through a preset double-threshold processing strategy to obtain an edge segmentation diagram of the electrode slice in the third image;

step 160, determining the angular point coordinates of each electrode slice from the third image with the edge segmentation map;

step 170, determining the corresponding angular point coordinates of each electrode plate in the original image according to the preset compression ratio and the angular point coordinates of each electrode plate;

and 180, dividing the original image to obtain a region of each electrode slice based on the corresponding corner coordinates in the original image and the preset size of the electrode slice.

The following will explain the steps of the image segmentation method of the thin film capacitor electrode in detail, as follows:

in step 110, the electronic device may acquire the original image obtained by capturing the film from the camera in real time, or the electronic device may acquire the original image stored in advance in the storage module from the local, where the manner of acquiring the original image is not particularly limited. The processing module may be a GPU (Graphics Processing Unit, graphics processor) that may be used to perform the steps of the method to perform arithmetic processing on an image.

In step 120, the preset compression ratio may be flexibly set according to practical situations, for example, may be 10 times, 20 times, 40 times, etc. The electronic device can do the Resize processing on the GPU, the smaller the compression of the original image size is, the less the processing time is. The compressed image is the first image.

In step 130, the GPU end performs corrosion and expansion processing on the first image sequentially, so as to implement open operation processing. The purpose of the open operation is to remove the burr on the first image, so as to divide the final edge into more close parts to the outer edge of the image.

In step 140, the binarization processing manner of the image may be flexibly determined according to the actual situation. For example, step 140 may include:

As will be appreciated, in the second image, the foreground region generally refers to the region of the second image that acts as an electrode pad. The background region refers to a region of the space between electrode pads, or a region other than the electrode pads.

The foreground region is set to white, which can be understood as: the gray values of all pixels of the foreground region are set to 255.

The background region is black, which can be understood as: the gray values of all pixels of the background region are set to 0.

Referring to fig. 2, 3 and 4 in combination, fig. 2 can be understood as a schematic diagram of an original image obtained by photographing a base film with a camera. Fig. 3 can be understood as a schematic view of a single electrode sheet on the base film in fig. 2. Fig. 4 is a schematic diagram of the electrode sheet of fig. 3 after binarization.

In this embodiment, step 150 may include:

step 151, determining the gradient amplitude and gradient direction of each pixel point in the third image;

step 152, marking the pixel points with gradient amplitude greater than the first preset threshold (which may be denoted as nthighthreshold, referred to as high threshold) as the first type pixel points representing the strong edges;

step 153, marking pixels with gradient amplitude values greater than a second preset threshold (which may be denoted as nlowThreshold, and refers to a low threshold) and less than or equal to the first preset threshold as second class pixels representing weak edges, wherein the second preset threshold is smaller than the first preset threshold;

step 154, marking the pixel points with the gradient amplitude smaller than or equal to the second preset threshold value as a third type of pixel points representing non-edges;

step 155, obtaining an edge segmentation map of the electrode slice in the third image according to the first class pixel point, the second class pixel point and the third class pixel point by a preset edge tracking strategy.

In this embodiment, various preset thresholds (such as a first preset threshold, a second preset threshold, etc.) may be flexibly determined according to actual situations.

In this embodiment, the gradient magnitude can be understood as: the gray value/change rate of the pixel value in the image, the gradient amplitude represents the intensity of the gray value/change of the pixel value, and can be understood as the edge intensity in the image. And performing convolution operation in the image to calculate the gradient amplitude of each pixel point.

The gradient direction can be understood as: the direction of pixel gray value/pixel value change in the image, i.e., the edge direction in the image. The gradient direction is obtained by calculating the difference in pixel values around the pixel point.

Please refer to fig. 4, fig. 5, fig. 6 and fig. 7 in combination. Fig. 5 (a) can be understood as a simplified microscopic schematic diagram of fig. 4, each unit cell representing a pixel point. Fig. 5 (b) may be understood as a simplified microscopic schematic diagram of fig. 6, and the black pixel in the middle of fig. 5 (b) may be understood as a black region surrounded by a white edge line in fig. 6, specifically, fig. 5 (b) is a schematic diagram of fig. 5 (a) after edge segmentation.

Referring again to fig. 5, the implementation process of steps 151 to 154 may be as follows:

when calculating the gradient amplitude, marking the position of any pixel point in the image as (x, y), and marking the gradient of the pixel point in the x direction as:

float gx=pucsrcdimg [ (y-1) nsrcwidth+x+1] (refer to the position above and to the right of the current pixel point) +2×pucsrcdimg [ y×nsrcwidth+x+1] (refer to the position to the right of the current pixel point) +pucsrcdimg [ (y+1) nsrcwidth+x+1] (refer to the position below and to the right of the current pixel point) -pucsrcdimg [ (y-1) ×nsrcwidth+x-1] (refer to the position above and to the left of the current pixel point) -2×pucsrcdimg [ y×nsrcwidth+x-1] (refer to the position to the left of the current pixel point) -pucsrcdimg [ (y+1) nsrcwidth+x-1] (refer to the position below and to the left of the current pixel point).

The gradient of the pixel point in the y direction is recorded as follows:

float gy=pucsrcdigl [ (y+1) ×nsrcwidth+x-1] (refer to the position at the bottom left of the current pixel) +2×pucsrcdigl [ (y+1) ×nsrcwidth+x ] (refer to the position at the bottom of the current pixel) +pucsrcdigl [ (y+1) ×ncwidth+x+1 ] (refer to the position at the bottom right of the current pixel) -pucsrcdigl [ (y-1) ×nsrcwidth+x-1] (refer to the position at the top left of the current pixel) -2×pucsrcdigl [ (y-1) ×nsrcwidth+x ] (refer to the position at the top of the current pixel) -pucsrcdigl [ (y-1) ×nsrcwidth+x+1] (refer to the position at the top right of the current pixel).

The gradient amplitude of the pixel point is marked as follows:

fgradient=sqrtf (gx+gy), where the sqrtf () function is used to calculate the square root.

GPU in the electronic device judges gradient amplitude fGradient of pixel points (x, y) by a parallel kernel function:

if fGradent > nHighThreshold (refer to a first preset threshold), setting the pixel value of the point to be white (255), and marking the pixel point as a first type pixel point representing a strong edge;

if nlowThreshold < fGradient is less than or equal to nHighthreshold, the pixel is marked as a second type of pixel representing a weak edge, which means that the pixel may be an edge, but needs further verification;

if fGradent is less than or equal to nlowThreshold, the pixel is marked as a third type of pixel that characterizes the non-edge, and the pixel value is set to black (0), such as the black cell in the center of FIG. 5 (b), meaning that such pixel is not an edge point, or is considered a noisy or cluttered edge.

Step 155, obtaining an edge segmentation map of the electrode slice in the third image according to the first class pixel point, the second class pixel point and the third class pixel point by a preset edge tracking strategy, including:

step 1551, adding the first type pixel points in the first image to an edge result;

step 1552, updating the second type pixel point adjacent to the first type pixel point to a new first type pixel point, and adding the new first type pixel point to the edge result;

repeating step 1552 to update the second type pixel point adjacent to the first type pixel point to a new first type pixel point, and adding the new first type pixel point to the edge result until all the second type pixel points are traversed, wherein the pixel points in the edge result form the edge segmentation graph.

Understandably, for pixels marked as weak edges (referring to the second type of pixels), if there are pixels marked as strong edges around them (referring to the first type of pixels), the pixels of the weak edges are re-marked as strong edges, a process called edge tracking. Edge tracking may connect weak edges to strong edges, forming a continuous edge line. By repeating step 1552, all weak edge points can be processed.

In this embodiment, by the double thresholding, the edge region can be distinguished from noise and clutter edges, and by edge tracking, continuous edge lines can be generated, resulting in more accurate and robust edge detection results.

Referring to fig. 6 and 7 in combination, fig. 7 is a partially simplified microscopic view of fig. 6, and each unit cell of fig. 7 represents a pixel. The width of the contour line of the edge segmentation map is two pixels, and the two layers of white pixel points shown in fig. 7 are edge lines, which may be equivalent to the white frame in fig. 6. In step 160, determining corner coordinates of each electrode slice from the third image with the edge segmentation map, comprising:

As can be appreciated, since the pixel value/gray value of each electrode pad edge position is set to 255 and two layers are wrapped, as shown in fig. 7, when traversing to the first upper left corner coordinate, two conditions are set with the point coordinate:

1) The edge pixels of the first layer are 255, and the edge pixels of the inner layer are 255;

2) The inner two-layer edge pixel is 0.

Only the pixel points meeting the two-song condition are used as the upper left corner points of the electrode plates, otherwise, the pixel points continue to traverse in the first image.

Referring to fig. 7 again, if the searched corner point is the corner point of the upper left corner, if the current pixel point is the white cell a in fig. 7, the edge pixel points of the first layer may be the pixel point a and 5 pixel points on the left side of the same row, and 5 pixel points on the lower side of the same column of the pixel point a. The edge pixels of the inner layer are the lower right corner pixel point B adjacent to the current pixel point, and the 5 pixel points on the left side of the same row of the pixel point B, and the 5 pixel points on the lower side of the same column of the pixel point B. The edge pixels of the inner two layers are the lower right corner pixel point C adjacent to the pixel point B, the 5 pixel points on the left side of the same row of the pixel point C, and the 5 pixel points on the lower side of the same column of the pixel point C. Therefore, in the process of searching the corner points, the calculation amount is reduced.

In fig. 7, the upper left white cell a is a pixel point that satisfies the above two conditions, and the pixel point is the corner point of the upper left corner of the electrode plate.

In step 170, after obtaining the corner coordinates of each electrode slice in the third image, an interpolation algorithm may be used to perform inverse operation on the coordinates according to a preset compression ratio, so as to obtain the corner coordinates of each electrode slice on the original image.

The corner coordinates on the original image may be directly used as anchor points for image segmentation, or the corner coordinates may be offset. For example, the coordinates of the corner point are shifted to the upper left corner of the electrode plate by a small amount (for example, 1-5 pixels), so as to obtain the positioning point shown in fig. 8. The white point at the upper left corner of the electrode plate in fig. 8 is the locating point.

In step 180, the size of each electrode pad is typically fixed on the same Zhang Ji film, and the operator can obtain the preset size of the electrode pad by actual measurement. When the image segmentation is performed, the original image can be cut based on the corresponding corner coordinates (or positioning points) and the cutting frame in the original image.

The size of the cutting frame can be the same as or slightly larger than the preset size of the electrode plate. The size of the cutting frame can be flexibly designed according to practical conditions, and only the cutting frame can cut a complete electrode sheet region and does not contain regions of other electrode sheets, so that the cutting frame can be divided into independent electrode sheet regions.

The manner in which the image is segmented/cropped can be understood as: on the original image, since the coordinates of the upper left corner point of each electrode slice are already determined, then each coordinate is extracted on the original image according to the region of the cutting frame (the electrode slices can be divided by offsetting the coordinates of the diagonal points), so that all the pixel points in the region of the cutting frame can be obtained, and a picture region of a single electrode slice is formed. Based on the above method, the inventors split an original image of 12k×12k in size, which is 10 ten thousand electrode pads, by about 150 ms.

Based on the design, the electrode plate can be positioned and separated rapidly and accurately, and when the base film of the flexible film material is deformed and skewed, the accurate segmentation of the single electrode plate can be realized. The divided single electrode slice is associated with the coordinate position, and is used for detecting defects of the electrode slice, such as hypertrophy, burrs and other appearance defects of the electrode slice, and the detection mode is a conventional mode and is not repeated here. After the electrode plate is associated with the coordinate position, the position of the electrode plate with the defect is conveniently positioned.

In this embodiment, the processing module may be an integrated circuit chip with signal processing capability. The processing module may be a general purpose processor. For example, the processor may be a central processing unit (Central Processing Unit, CPU), GPU, application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, and the methods, steps, and logic blocks disclosed in embodiments of the present application may be implemented or performed.

The memory module may be, but is not limited to, random access memory, read only memory, programmable read only memory, erasable programmable read only memory, electrically erasable programmable read only memory, and the like. In this embodiment, the storage module may be configured to store an original image, a region of each electrode slice, coordinates of corner points, a dual-threshold processing policy, and the like. Of course, the storage module may also be used to store a program, and the processing module executes the program after receiving the execution instruction.

It should be noted that, for convenience and brevity of description, specific working processes of the electronic device described above may refer to corresponding processes of each step in the foregoing method, and will not be described in detail herein.

From the foregoing description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented in hardware, or by means of software plus a necessary general hardware platform, and based on this understanding, the technical solution of the present application may be embodied in the form of a software product, where the software product may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disc, a mobile hard disk, etc.), and includes several instructions to cause a computer device (may be a personal computer, an electronic device, or a network device, etc.) to perform the methods described in the respective implementation scenarios of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners as well. The above-described apparatus and method embodiments are merely illustrative, for example, flow charts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. In addition, the functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.

The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for segmenting a thin film capacitive electrode image, the method comprising:

performing binarization processing on the second image to obtain a third image;

2. The method of claim 1, wherein performing edge segmentation on the third image by a preset dual-threshold processing strategy to obtain an edge segmentation map of electrode slices in the third image comprises:

3. The method of claim 2, wherein obtaining an edge segmentation map of the electrode slice in the third image according to the first class of pixels, the second class of pixels, and the third class of pixels by a preset edge tracking strategy comprises:

adding the first type pixel points in the first image to an edge result;

4. The method of claim 1, wherein binarizing the second image to obtain a third image comprises:

5. The method of claim 4, wherein the contour line of the edge segmentation map has a width of two pixels and is white, and determining the corner coordinates of each electrode pad from the third image with the edge segmentation map comprises:

6. The method according to any one of claims 1-5, wherein the corner coordinates comprise corner coordinates of an upper left corner of the electrode pad.

7. The method of any one of claims 1-5, wherein the region of each electrode pad is associated with corresponding coordinates, the region of each electrode pad being a region of interest for electrode pad defect detection.

8. An electronic device comprising a processor and a memory coupled to each other, the memory storing a computer program that, when executed by the processor, causes the electronic device to perform the method of any of claims 1-7.