A method, apparatus, equipment and medium for determining chamfer angle
By combining key point detection and contour extraction algorithms with a classification model, the problem of inaccurate chamfer positioning in traditional methods has been solved, enabling high-precision detection and quality assessment of diverse chamfers and improving quality control in LCD panel production.
Patent Information
- Application Number
- CN202310765739.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-26
- Publication Date
- 2025-11-14
- Estimated Expiration
- 2043-06-26
AI Technical Summary
In existing technologies, traditional contour extraction or template matching algorithms are prone to failure when determining the chamfer vertices of LCD panels, resulting in low chamfer accuracy, especially when dealing with diverse chamfer shapes such as those with burrs or rounded chamfers, where the positioning is inaccurate.
Candidate chamfer vertices are determined using a key point detection algorithm, target chamfer vertices are selected by filtering through the minimum bounding rectangle, and chamfer contour points are identified by combining a contour extraction algorithm. The chamfer type is determined by a classification model, chamfer error parameters and difference areas are calculated, and the chamfer quality is comprehensively evaluated from multiple dimensions.
It improves the accuracy of chamfer positioning, reduces interference in the internal area of the LCD panel, effectively identifies diverse chamfer shapes, and improves the accuracy and pass rate of chamfer detection.
Smart Images

Figure CN116823766B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of image processing technology, and in particular to a chamfer determination method, apparatus, device and medium. Background Technology
[0002] Inspection of the appearance quality of LCD panels is a prerequisite for ensuring their normal use. This primarily involves inspecting the appearance of LCD panels before the polarizer is attached, as the appearance of the panel before the polarizer is attached significantly impacts the final quality of the LCD product. The LCD panel manufacturing process includes a cutting process, after which some LCD products will have chamfered edges. It is necessary to identify and inspect the quality of these chamfered edges.
[0003] Currently, the most widely used methods for determining chamfers are contour extraction or template matching algorithms. However, in actual production, the chamfering process cannot always produce an ideal chamfer contour, and the chamfers can take many forms, such as having burrs or being rounded. Traditional contour extraction or template matching algorithms are prone to failing to locate the chamfer vertices, resulting in low accuracy of the final determined chamfer. Summary of the Invention
[0004] This application provides a chamfer determination method, apparatus, device, and medium to solve the problem that traditional contour extraction or template matching algorithms in the prior art are prone to failure in locating chamfer vertices, resulting in low accuracy of the final determined chamfer.
[0005] This application provides a chamfer determination method, the method comprising:
[0006] Based on the key point detection algorithm, candidate chamfer vertices in the target region to be detected are determined;
[0007] If the number of candidate chamfer vertices is at least two, then determine the smallest bounding rectangle containing each candidate chamfer vertex, and determine the first candidate chamfer vertex that is closest to the first preset edge of the smallest bounding rectangle, and the second candidate chamfer vertex that is closest to the second preset edge of the smallest bounding rectangle; determine the first candidate chamfer vertex and the second candidate chamfer vertex as the target chamfer vertex;
[0008] Based on the contour extraction algorithm and the two target chamfer vertices, the chamfer contour points in the minimum bounding rectangle are identified; based on the chamfer contour points and the two target chamfer vertices, the chamfer contour is determined.
[0009] Furthermore, the method also includes:
[0010] Based on the chamfer profile, determine the chamfer type corresponding to the chamfer profile;
[0011] Based on the positions of the two target chamfer vertices, determine the chamfer vertex distance error parameter between the chamfer profile and the standard chamfer.
[0012] Based on the chamfer type and the position of each candidate chamfer profile point, determine the chamfer profile point distance error parameter between the chamfer profile corresponding to the chamfer profile and the standard chamfer.
[0013] Based on the chamfer type and the chamfer profile, determine each difference region between the chamfer corresponding to the chamfer profile and the standard chamfer, and determine the number of difference regions whose area exceeds the area threshold, and the total area of the difference regions whose area exceeds the area threshold;
[0014] At least one of the following is used as the inspection criteria: chamfer type, chamfer vertex distance error parameter, chamfer contour point distance error parameter, quantity, and total area.
[0015] If each sub-content in the inspection content is less than the corresponding threshold requirement, the chamfer corresponding to the chamfer profile is determined to be a qualified chamfer.
[0016] Further, determining the chamfer type of the chamfer corresponding to the chamfer profile based on the chamfer profile includes:
[0017] The chamfer profile is input into the trained classification model to obtain the chamfer type output by the classification model; wherein, the chamfer type includes: standard straight chamfer, standard rounded chamfer, straight chamfer with burrs and rounded chamfer with burrs.
[0018] Further, determining the chamfer profile point distance error parameter between the chamfer profile corresponding to the chamfer profile and the standard chamfer, based on the chamfer type and the position of each chamfer profile point, includes:
[0019] If the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then determine each first distance from each chamfer profile point to the line connecting the two target chamfer vertices; determine the first average, first maximum, and first standard deviation of each first distance, and determine the first average, first maximum, and first standard deviation as the chamfer profile point distance error parameters;
[0020] If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; for each chamfer profile point, determine the line connecting the chamfer profile point and the center of the circle, and determine the intersection point of the line connecting the circle; determine the second distance between the intersection point and the chamfer profile point; determine the second average value, the second maximum value and the second standard deviation of each second distance, and determine the second average value, the second maximum value and the second standard deviation as the chamfer profile point distance error parameters.
[0021] Further, determining each difference region between the chamfer profile and the standard chamfer based on the chamfer type and the chamfer profile includes:
[0022] If the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then each first region enclosed by the chamfer profile and the line connecting the two target chamfer vertices is determined; each first region is determined as the difference region;
[0023] If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; determine the circular arc between the two target chamfer vertices in the circle, and determine each second region enclosed by the circular arc profile and the circular arc; and determine each second region as the difference region.
[0024] Furthermore, determining the chamfer vertex distance error parameter between the chamfer profile and the standard chamfer based on the positions of the two target chamfer vertices includes:
[0025] Determine the intersection point of the two target chamfers along the corresponding edge direction of the LCD panel;
[0026] Determine each distance between each target chamfer vertex and the intersection point, and determine each difference between each distance and a pre-saved standard chamfer size as the chamfer vertex distance error parameter.
[0027] Furthermore, before determining the candidate chamfer vertices in the target region to be detected based on the keypoint detection algorithm, the method further includes:
[0028] Based on the edge detection algorithm, each edge contour line of the LCD panel image is identified;
[0029] If the number of identified edge contour lines is a preset number, then the intersection point of two adjacent edge contour lines is determined, and the target area is determined according to the intersection point and the specifications of the pre-saved target area.
[0030] If the number of identified edge contour lines is not the preset number, the liquid crystal panel is determined to be defective.
[0031] This application embodiment also provides a chamfer determining device, the device comprising:
[0032] The detection module is used to determine candidate chamfer vertices in the target area to be detected based on the key point detection algorithm;
[0033] The determining module is configured to, if the number of candidate chamfer vertices is at least two, determine the smallest bounding rectangle containing each candidate chamfer vertex, and determine the first candidate chamfer vertex closest to the first preset edge of the smallest bounding rectangle, and the second candidate chamfer vertex closest to the second preset edge of the smallest bounding rectangle; determine the first candidate chamfer vertex and the second candidate chamfer vertex as target chamfer vertices; identify chamfer contour points in the smallest bounding rectangle according to the contour extraction algorithm and the two target chamfer vertices; and determine the chamfer contour according to the chamfer contour points and the two target chamfer vertices.
[0034] This application also provides an electronic device, which includes a processor for executing a computer program stored in a memory to implement the steps of any of the chamfer determination methods described above.
[0035] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of any of the chamfer determination methods described above.
[0036] In this embodiment, the electronic device determines candidate chamfer vertices in the target area to be detected based on a key point detection algorithm. If there are at least two candidate chamfer vertices, a minimum bounding rectangle containing each candidate chamfer vertex is determined, and a first candidate chamfer vertex closest to a first preset edge of the minimum bounding rectangle and a second candidate chamfer vertex closest to a second preset edge of the minimum bounding rectangle are determined. The first and second candidate chamfer vertices are determined as target chamfer vertices, and chamfer contour points in the minimum bounding rectangle are identified based on a contour extraction algorithm and the two target chamfer vertices. The chamfer contour is determined based on the chamfer contour points and the two target chamfer vertices. In this embodiment, when the electronic device detects chamfers with burrs or arc features in actual production based on the key point detection algorithm, it can effectively locate chamfer vertices and determine chamfer contour points based on the minimum bounding rectangle, reducing the recognition area and avoiding interference from the internal area of the LCD panel. At the same time, the chamfer vertices can better locate the chamfer contour points, improving the accuracy of chamfer determination. Attached Figure Description
[0037] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0038] Figure 1This is a schematic diagram of a chamfer determination process provided in an embodiment of this application;
[0039] Figure 2 A schematic diagram of the minimum bounding rectangle provided in an embodiment of this application;
[0040] Figure 3 A schematic diagram illustrating common chamfers provided in the embodiments of this application;
[0041] Figure 4 A schematic diagram illustrating the distance error parameters for determining the chamfer profile points in an embodiment of this application;
[0042] Figure 5 A schematic diagram illustrating the distance error parameters for determining the chamfer profile points in an embodiment of this application;
[0043] Figure 6 A schematic diagram illustrating each difference region between the chamfer corresponding to the straight chamfer and the standard chamfer, provided in an embodiment of this application.
[0044] Figure 7 A schematic diagram illustrating each difference region between the chamfer corresponding to the arc chamfer and the standard chamfer provided in the embodiments of this application;
[0045] Figure 8 A schematic diagram illustrating the determination of chamfer vertex distance error parameters provided in an embodiment of this application;
[0046] Figure 9 This is a schematic diagram of a chamfer determination device provided in an embodiment of this application;
[0047] Figure 10 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation
[0048] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0049] To improve the accuracy of chamfer determination, embodiments of this application provide a chamfer determination method, apparatus, device, and medium.
[0050] Example 1:
[0051] Figure 1 This application provides a schematic diagram of a chamfer determination process, which includes:
[0052] S101: Based on the key point detection algorithm, determine the candidate chamfer vertices in the target area to be detected.
[0053] The chamfer determination method provided in this application is applied to an electronic device, which may be a PC or a server.
[0054] In actual production, the chamfering process cannot always produce an ideal chamfer profile, and the chamfers can take many forms, such as having burrs or being rounded. Traditional contour extraction or template matching algorithms are prone to failure in locating the chamfer vertices, resulting in low accuracy of the final chamfer.
[0055] Based on this, in the embodiments of this application, the electronic device can determine multiple candidate chamfer vertices in the target area to be detected based on the key point detection algorithm, and further filter out the target chamfer vertex from the multiple candidate chamfer vertices, so as to improve the accuracy of the finally determined target chamfer vertex.
[0056] When determining candidate chamfer vertices, electronic devices can use a keypoint detection algorithm based on the HRNet model to detect the image corresponding to the target region and determine the candidate chamfer vertices in the target region.
[0057] Specifically, the electronic device inputs the image corresponding to the target region into the HRNet model. The HRNet model scores each pixel in the target region, determines at least one pixel that meets the score threshold, labels this at least one pixel in the image, and outputs the labeled image. After receiving the labeled image output by the HRNet model, the electronic device determines each labeled pixel in the image and determines the position of each pixel in the target region of the display panel, identifying these positions as candidate chamfer vertices in the target region.
[0058] It should be noted that, in the embodiments of this application, the electronic device can also determine candidate chamfer vertices through other key point detection algorithms, such as the electronic device directly scoring each pixel in the image corresponding to the target area, etc., without limitation.
[0059] S102: If the number of candidate chamfer vertices is at least two, then determine the smallest bounding rectangle containing each candidate chamfer vertex, and determine the first candidate chamfer vertex that is closest to the first preset edge of the smallest bounding rectangle, and the second candidate chamfer vertex that is closest to the second preset edge of the smallest bounding rectangle; determine the first candidate chamfer vertex and the second candidate chamfer vertex as target chamfer vertices.
[0060] In this embodiment of the application, when the electronic device determines that the number of candidate chamfer vertices is at least two, the electronic device can determine that there is a chamfer in the target area, and then the electronic device determines the target chamfer vertex from the at least two candidate chamfer vertices.
[0061] In order to reduce the recognition area of the electronic device and reduce interference in the internal area of the liquid crystal panel, in this embodiment of the application, when the electronic device determines the target chamfer vertex, the electronic device can determine the minimum bounding rectangle containing each candidate chamfer vertex, and determine the target chamfer vertex according to the minimum bounding rectangle.
[0062] Specifically, the electronic device determines a first candidate chamfer vertex that is closest to the first preset edge of the minimum bounding rectangle, and a second candidate chamfer vertex that is closest to the second preset edge of the minimum bounding rectangle. The electronic device then determines the first candidate chamfer vertex and the second candidate chamfer vertex as the target chamfer vertex.
[0063] In this embodiment, the first and second preset edges of the minimum bounding rectangle are the two edges of the minimum bounding rectangle that overlap with the liquid crystal panel.
[0064] Figure 2 This is a schematic diagram of the minimum bounding rectangle provided in the embodiments of this application, as shown below. Figure 2 As shown, if the electronic device determines that the candidate chamfer vertices are P1, P2 and P3, then the electronic device determines that the minimum bounding rectangle corresponding to these three candidate chamfer vertices is OP1QP2.
[0065] Furthermore, in this embodiment of the application, if there is only one candidate chamfer vertex, the electronic device determines that no chamfer has been generated in the target area.
[0066] S103: Based on the contour extraction algorithm and the two target chamfer vertices, identify the chamfer contour points in the minimum bounding rectangle; determine the chamfer contour based on the chamfer contour points and the two target chamfer vertices.
[0067] In this embodiment of the application, after the electronic device determines two target chamfer vertices, the electronic device can determine the chamfer profile based on the two target chamfer vertices.
[0068] In this embodiment of the application, the electronic device identifies the chamfer contour points in the minimum bounding rectangle based on the contour extraction algorithm and the two target chamfer vertices; and determines the chamfer contour based on the chamfer contour points and the two target chamfer vertices.
[0069] Specifically, in this embodiment, the electronic device uses the two target chamfer vertices as references and employs a contour extraction algorithm to identify the chamfer contour points within the smallest bounding rectangle. The electronic device sequentially connects each chamfer contour point to the two target chamfer points, and determines the connected image as the chamfer contour in the target region.
[0070] In this embodiment, the electronic device determines candidate chamfer vertices in the target area to be detected based on a key point detection algorithm. If there are at least two candidate chamfer vertices, a minimum bounding rectangle containing each candidate chamfer vertex is determined, and a first candidate chamfer vertex closest to a first preset edge of the minimum bounding rectangle and a second candidate chamfer vertex closest to a second preset edge of the minimum bounding rectangle are determined. The first and second candidate chamfer vertices are determined as target chamfer vertices, and chamfer contour points in the minimum bounding rectangle are identified based on a contour extraction algorithm and the two target chamfer vertices. The chamfer contour is determined based on the chamfer contour points and the two target chamfer vertices. In this embodiment, when the electronic device detects chamfers with burrs or arc features in actual production based on the key point detection algorithm, it can effectively locate chamfer vertices and determine chamfer contour points based on the minimum bounding rectangle, reducing the recognition area and avoiding interference from the internal area of the LCD panel. At the same time, the chamfer vertices can better locate the chamfer contour points, improving the accuracy of chamfer determination.
[0071] Example 2:
[0072] To verify the chamfer, based on the above embodiments, the method in this application embodiment further includes:
[0073] Based on the chamfer profile, determine the chamfer type corresponding to the chamfer profile;
[0074] Based on the positions of the two target chamfer vertices, determine the chamfer vertex distance error parameter between the chamfer profile and the standard chamfer.
[0075] Based on the chamfer type and the position of each candidate chamfer profile point, determine the chamfer profile point distance error parameter between the chamfer profile corresponding to the chamfer profile and the standard chamfer.
[0076] Based on the chamfer type and the chamfer profile, determine each difference region between the chamfer corresponding to the chamfer profile and the standard chamfer, and determine the number of difference regions whose area exceeds the area threshold, and the total area of the difference regions whose area exceeds the area threshold;
[0077] At least one of the following is used as the inspection criteria: chamfer type, chamfer vertex distance error parameter, chamfer contour point distance error parameter, quantity, and total area.
[0078] If each sub-content in the inspection content is less than the corresponding threshold requirement, the chamfer corresponding to the chamfer profile is determined to be a qualified chamfer.
[0079] In the existing technology, minor defects are often allowed by the process specifications. That is, after the chamfer profile is determined, the electronic device will judge whether the chamfer corresponding to the chamfer profile is allowed by the process specifications, that is, whether the chamfer corresponding to the chamfer profile is a qualified chamfer.
[0080] However, in actual industrial production, the standards for determining the quality of chamfering are often in flux. There is a need to improve yield when product grade requirements are not high, and there is also a need to classify processing grades. This makes it difficult for the quality inspection results of qualified chamfers to be compatible with the relatively vague standards in the production process, resulting in poor determination of qualified chamfers.
[0081] In practical applications, if the chamfer size of the LCD panel is too large, that is, the distance between the two chamfer vertices and the vertex of the LCD panel where the chamfer is located is too large, the LCD panel will not be usable; if the chamfer of the LCD panel has too many burrs, the LCD panel will not be usable; if the chamfer profile of the LCD panel deviates significantly from the profile of the standard chamfer, the LCD panel will not be usable.
[0082] Based on this, in the embodiments of this application, the electronic device can analyze the chamfer from multiple dimensions, thereby improving the determination of qualified chamfers.
[0083] In this embodiment of the application, the electronic device may use at least one of the following as inspection content: chamfer type, chamfer vertex distance error parameter between the chamfer profile and the standard chamfer, number of chamfer regions whose area exceeds the area threshold for each difference region between the chamfer profile and the standard chamfer, and total area of chamfer regions whose area exceeds the area threshold, and determine whether the chamfer is a qualified chamfer based on the inspection result.
[0084] The electronic device determines the chamfer type corresponding to the chamfer profile based on the chamfer profile. For example, the electronic device can compare the chamfer profile corresponding to each pre-saved chamfer type with the chamfer profile, determine the target sample chamfer profile with high similarity to the chamfer profile, and determine the chamfer type corresponding to the target sample chamfer profile as the chamfer type corresponding to the chamfer profile.
[0085] The electronic device determines the chamfer vertex distance error parameter between the chamfer profile and the standard chamfer based on the positions of the two target chamfer vertices. For example, the electronic device determines each distance from each target chamfer vertex to the corresponding LCD panel vertex and uses each distance as the chamfer vertex distance error parameter.
[0086] The electronic device determines each difference region between the chamfer and the standard chamfer based on the chamfer type and the chamfer profile. The electronic device determines the area corresponding to each difference region, the number of difference regions whose area exceeds the area threshold, and the total area of difference regions whose area exceeds the area threshold.
[0087] In this embodiment, the electronic device stores threshold requirements corresponding to the chamfer type, the chamfer vertex distance error parameter between the chamfer profile and the standard chamfer, the number of chamfer regions whose area exceeds an area threshold, and the total area of chamfer regions exceeding the area threshold. Furthermore, technicians can adjust each threshold requirement according to actual production needs. The electronic device can use at least one of the above-mentioned chamfer type, chamfer vertex distance error parameter, chamfer profile point distance error parameter, number, and total area of chamfer regions exceeding the area threshold as inspection content. If the electronic device determines that each sub-content of the inspection content is less than the corresponding threshold requirement, then the chamfer corresponding to the chamfer profile is determined to be a qualified chamfer.
[0088] Example 3:
[0089] To further verify the chamfer, based on the above embodiments, in this embodiment, determining the chamfer type corresponding to the chamfer profile according to the chamfer profile includes:
[0090] The chamfer profile is input into the trained classification model to obtain the chamfer type output by the classification model; wherein, the chamfer type includes: standard straight chamfer, standard rounded chamfer, straight chamfer with burrs and rounded chamfer with burrs.
[0091] In this embodiment of the application, the electronic device can use the chamfer type as the inspection content, and determine whether the chamfer is a qualified chamfer based on the inspection result.
[0092] In this embodiment of the application, the electronic device determines the chamfer type of the chamfer corresponding to the chamfer profile based on the chamfer profile. For example, the electronic device can compare the chamfer profile corresponding to each pre-saved chamfer type with the chamfer profile, determine the target sample chamfer profile with high similarity to the chamfer profile, and determine the chamfer type corresponding to the target sample chamfer profile as the chamfer type corresponding to the chamfer profile.
[0093] However, in the method by which electronic devices determine the chamfer type by comparing the chamfer profile with the chamfer profile of the target sample, a large number of sample chamfer profiles need to be stored in the electronic device to make the determined chamfer profile more accurate, which occupies too much storage space of the electronic device and makes the storage pressure of the electronic device too great.
[0094] Based on this, in this embodiment of the application, the electronic device can determine the chamfer type through a classification model. Specifically, in this embodiment of the application, the electronic device inputs the chamfer contour into the trained classification model and obtains the chamfer type output by the classification model. The chamfer type includes a standard straight chamfer, a standard rounded chamfer, a straight chamfer with burrs, and a rounded chamfer with burrs.
[0095] Among them, the standard straight chamfer is a straight line connecting the two chamfer vertices, the standard rounded chamfer is a smooth arc connecting the two chamfer vertices, the burred straight chamfer is a straight line with protruding or concave burrs connecting the two chamfer vertices, and the burred rounded chamfer is an arc connecting the two chamfer vertices with protruding or concave burrs.
[0096] The classification model is a deep learning classification model based on the ResNet18 model.
[0097] Furthermore, in this embodiment, before determining the chamfer type based on the classification model, the electronic device can also use an interpolation algorithm to scale the chamfer contour and input the scaled chamfer contour into the trained classification model for classification. Specifically, the electronic device can shrink the chamfer contour to 64*64 pixels.
[0098] Figure 3 This is a schematic diagram of common chamfers provided in the embodiments of this application, such as... Figure 3 As shown, common chamfers include: standard chamfer, raised burr chamfer, concave burr chamfer, rounded chamfer, rounded raised burr chamfer, rounded concave burr chamfer, straight chamfer for excessively small dimensions, straight chamfer for excessively large dimensions, and missing chamfer (no chamfer). Figure 3 In the standard chamfer, the chamfer for too small a size and the chamfer for too large a size are all chamfer types. The chamfer type for the rounded chamfer is the standard rounded chamfer. The chamfer type for the burr chamfer and the chamfer type for the burr chamfer is the straight chamfer. The chamfer type for the arc burr chamfer and the arc concave burr chamfer is the rounded chamfer.
[0099] Example 4:
[0100] To further verify the chamfer, based on the above embodiments, in this embodiment, determining the chamfer profile point distance error parameter between the chamfer profile corresponding to the chamfer profile and the standard chamfer, according to the chamfer type and the position of each chamfer profile point, includes:
[0101] If the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then determine each first distance from each chamfer profile point to the line connecting the two target chamfer vertices; determine the first average, first maximum, and first standard deviation of each first distance, and determine the first average, first maximum, and first standard deviation as the chamfer profile point distance error parameters;
[0102] If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; for each chamfer profile point, determine the line connecting the chamfer profile point and the center of the circle, and determine the intersection point of the line connecting the circle; determine the second distance between the intersection point and the chamfer profile point; determine the second average value, the second maximum value and the second standard deviation of each second distance, and determine the second average value, the second maximum value and the second standard deviation as the chamfer profile point distance error parameters.
[0103] In this embodiment of the application, when determining the chamfer profile point distance error parameter, the electronic device is based on the chamfer type, each chamfer profile point, and the position of the two target chamfer vertices.
[0104] Specifically, in the embodiments of this application, if the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then each first distance from each chamfer profile point to the line connecting the two target chamfer vertices is determined; the first average value, the first maximum value, and the first standard deviation of each first distance are determined, and the first average value, the first maximum value, and the first standard deviation are determined as the chamfer profile point distance error parameters.
[0105] Figure 4 This is a schematic diagram illustrating the method for determining the distance error parameters of the chamfer profile points in an embodiment of this application. Figure 4 As shown, P1 and P2 are two target chamfer vertices, Q i and Q j For the chamfered profile points, the electronic equipment determines Q respectively. i and Q j The distance d to the line connecting P1 and P2 i =|Q i Q i’ | and d j =|Q j Q j’ |, where Q i’ and Q j’ For Qi and Q j The foot of the perpendicular from the line connecting P1 and P2. The electronic device determines d. i and d j The first average value, the first maximum value, and the first standard deviation are determined, and these three values are used as the distance error parameters for the chamfered profile points.
[0106] It should be noted that the electronic device can also determine the variance of each first distance as the chamfer profile point distance error parameter, without any restrictions.
[0107] If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, the electronic device determines the circles tangent to the two target chamfer vertices respectively; for each chamfer profile point, it determines the line connecting the chamfer profile point and the center of the circle, and determines the intersection of the line connecting the circle; it determines the second distance between the intersection point and the chamfer profile point; it determines the second average, second maximum, and second standard deviation of each second distance, and determines the second average, second maximum, and second standard deviation as the distance error parameter of the chamfer profile point.
[0108] In this embodiment, when determining the circles tangent to two target chamfer vertices, the electronic device can determine the vertices of the liquid crystal panel corresponding to the chamfers of the two target chamfer vertices, determine each line connecting the vertex to each target chamfer vertex, and determine the circles tangent to each line. Furthermore, the electronic device can also draw extensions of the corresponding edge contour lines from the two target chamfer vertices along the horizontal and vertical directions, determine the intersection of the extensions of the two target chamfer vertices, determine each line connecting the intersection to each target chamfer vertex, and determine the circles tangent to each line.
[0109] Figure 5 This is a schematic diagram illustrating the method for determining the distance error parameters of the chamfer profile points in an embodiment of this application. Figure 5 As shown, P1 and P2 are two target chamfer vertices, Q i and Q j As the chamfering contour points, the electronic device constructs circles tangent to both OP1 and OP2 based on vertices O, P1, and P2 of the LCD panel, and determines the centers C of these circles to be tangent to Q. i and Q j Connect the lines and determine the focus Q of the connection. i’ and Q j’ The electronic device determines the second distance d between the intersection point and the two chamfered contour points. i =|Q i Q i’ | and d j =|Q j Q j’|. Electronic devices determine d i and d j The second average, second maximum, and second standard deviation are determined and used as the chamfer profile point distance error parameters.
[0110] It should be noted that the electronic device can also determine the variance of each second distance as the chamfer profile point distance error parameter, without any restrictions.
[0111] Example 5:
[0112] To further verify the chamfer, based on the above embodiments, in this embodiment, determining each difference region between the chamfer corresponding to the chamfer profile and the standard chamfer, according to the chamfer type and the chamfer profile, includes:
[0113] If the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then each first region enclosed by the chamfer profile and the line connecting the two target chamfer vertices is determined; each first region is determined as the difference region;
[0114] If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; determine the circular arc between the two target chamfer vertices in the circle, and determine each second region enclosed by the circular arc profile and the circular arc; and determine each second region as the difference region.
[0115] In this embodiment of the application, when determining each difference region between the chamfer profile and the standard chamfer, the electronic device is based on the chamfer type and the chamfer profile.
[0116] Specifically, in this embodiment, if the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then each first region enclosed by the chamfer profile and the line connecting the two target chamfer vertices is determined; each first region is determined as the difference region.
[0117] Figure 6 This is a schematic diagram illustrating each difference region between the chamfer corresponding to the straight chamfer and the standard chamfer provided in the embodiments of this application. Figure 6 As shown, the electronic device determines the line connecting the two target chamfer vertices P1 and P2, and determines each difference region S1, S2 and S3 enclosed by the chamfer profile and the line connecting them.
[0118] If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; determine the circular arc between the two target chamfer vertices in the circle, and determine each second region enclosed by the circular arc profile and the circular arc; and determine each second region as the difference region.
[0119] In this embodiment, when determining the circles tangent to two target chamfer vertices, the electronic device can determine the vertices of the liquid crystal panel corresponding to the chamfers of the two target chamfer vertices, determine each line connecting the vertex to each target chamfer vertex, and determine the circles tangent to each line. Furthermore, the electronic device can also draw extensions of the corresponding edge contour lines from the two target chamfer vertices along the horizontal and vertical directions, determine the intersection of the extensions of the two target chamfer vertices, determine each line connecting the intersection to each target chamfer vertex, and determine the circles tangent to each line.
[0120] Figure 7 This is a schematic diagram illustrating each difference region between the chamfer and the standard chamfer provided in the embodiments of this application. Figure 7 As shown, the electronic device determines the arcs corresponding to the two target chamfer vertices P1 and P2, and determines each difference region S4 enclosed by the chamfer profile and the arc.
[0121] In this embodiment, after identifying each dissimilar region, the electronic device can use a blob algorithm to filter out regions exceeding the level limit based on parameters such as area, length, width, and aspect ratio, and count the number of these regions. Simultaneously, the electronic device determines the total area of each of the dissimilar regions whose area exceeds the area threshold.
[0122] Example 6:
[0123] To further verify the chamfer, based on the above embodiments, in this embodiment, determining the chamfer vertex distance error parameter between the chamfer profile and the standard chamfer according to the positions of the two target chamfer vertices includes:
[0124] Determine the intersection point of the two target chamfers along the corresponding edge direction of the LCD panel;
[0125] Determine each distance between each target chamfer vertex and the intersection point, and determine each difference between each distance and a pre-saved standard chamfer size as the chamfer vertex distance error parameter.
[0126] In this embodiment of the application, when determining the chamfer vertex distance error parameter, the electronic device determines the intersection point of the two target chamfers along the corresponding edge direction of the liquid crystal panel; the electronic device determines each distance between each target chamfer vertex and the intersection point, and determines each difference between each distance and each pre-saved standard chamfer size as the chamfer vertex distance error parameter.
[0127] Figure 8 This is a schematic diagram illustrating the determination of chamfer vertex distance error parameters provided in an embodiment of this application. Figure 8 As shown, P1 and P2 are two target chamfer vertices, and O is the intersection of the two target chamfers along the corresponding edge direction of the LCD panel. The electronic device determines the lengths of line segments OP1 and OP2, and determines D1 = ||OP1|-R| and D2 = ||OP2|-R|, where R is the standard chamfer size, and D1 and D2 are the chamfer vertex distance error parameters.
[0128] Example 7:
[0129] To improve the efficiency of chamfer detection, based on the above embodiments, in this embodiment, before determining the candidate chamfer vertices in the target region to be detected according to the key point detection algorithm, the method further includes:
[0130] Based on the edge detection algorithm, each edge contour line of the LCD panel image is identified;
[0131] If the number of identified edge contour lines is a preset number, then the intersection point of two adjacent edge contour lines is determined, and the target area is determined according to the intersection point and the specifications of the pre-saved target area.
[0132] If the number of identified edge contour lines is not the preset number, the liquid crystal panel is determined to be defective.
[0133] To improve the efficiency of chamfer detection, in this embodiment of the application, the electronic device will detect the liquid crystal panel, but will not perform chamfer detection on unqualified liquid crystal panels.
[0134] Specifically, in this embodiment of the application, before performing chamfer detection, the electronic device first uses an edge detection algorithm to identify each edge contour line of the liquid crystal panel image. If the number of edge contour lines identified by the electronic device is a preset number, the electronic device determines the intersection point of two adjacent edge contour lines, and determines the target area according to the intersection point and the specifications of the pre-saved target area, and performs chamfer determination and detection on the target area.
[0135] The preset quantity is 4, meaning that if the electronic device detects that each contour of the LCD panel has a contour line, then subsequent chamfer determination and detection will be performed. The dimensions of this pre-saved target area are generally 416*416.
[0136] If the electronic device determines that the number of edge contour lines identified is not the preset number, the electronic device determines that the LCD panel may have chipped edges, broken or other defects, and the electronic device determines that the LCD panel is unqualified.
[0137] Example 8:
[0138] Figure 9 This application provides a schematic diagram of a chamfer determining device, which includes:
[0139] The detection module 901 is used to determine the candidate chamfer vertices in the target area to be detected based on the key point detection algorithm;
[0140] The determining module 902 is configured to, if the number of candidate chamfer vertices is at least two, determine the smallest bounding rectangle containing each candidate chamfer vertex, and determine the first candidate chamfer vertex closest to the first preset edge of the smallest bounding rectangle, and the second candidate chamfer vertex closest to the second preset edge of the smallest bounding rectangle; determine the first candidate chamfer vertex and the second candidate chamfer vertex as target chamfer vertices; identify chamfer contour points in the smallest bounding rectangle according to the contour extraction algorithm and the two target chamfer vertices; and determine the chamfer contour according to the chamfer contour points and the two target chamfer vertices.
[0141] In one possible implementation, the determining module 902 is further configured to: determine the chamfer type of the chamfer corresponding to the chamfer profile based on the chamfer profile; determine the chamfer vertex distance error parameter between the chamfer corresponding to the chamfer profile and the standard chamfer based on the positions of the two target chamfer vertices; determine the chamfer profile point distance error parameter between the chamfer corresponding to the chamfer profile and the standard chamfer based on the chamfer type and the position of each candidate chamfer profile point; determine each difference region between the chamfer corresponding to the chamfer profile and the standard chamfer based on the chamfer type and the chamfer profile, determine the number of difference regions whose area exceeds an area threshold, and the difference regions whose area exceeds the area threshold; use at least one of the chamfer type, the chamfer vertex distance error parameter, the chamfer profile point distance error parameter, the number, and the total area as inspection content; if each sub-content of the inspection content is less than the corresponding threshold requirement, determine that the chamfer corresponding to the chamfer profile is a qualified chamfer.
[0142] In one possible implementation, the determining module 902 is specifically used to input the chamfer contour into the trained classification model to obtain the chamfer type output by the classification model; wherein, the chamfer type includes: standard straight chamfer, standard rounded chamfer, straight chamfer with burrs and rounded chamfer with burrs.
[0143] In one possible implementation, the determining module 902 is specifically configured to: if the chamfer type is a standard straight chamfer or a burred straight chamfer, determine each first distance from each chamfer profile point to the line connecting the two target chamfer vertices; determine a first average value, a first maximum value, and a first standard deviation of each first distance, and define the first average value, the first maximum value, and the first standard deviation as the chamfer profile point distance error parameter; if the chamfer type is a standard circular arc chamfer or a burred circular arc chamfer, determine the circles tangent to the two target chamfer vertices respectively; for each chamfer profile point, determine the line connecting the chamfer profile point to the center of the circle, and determine the intersection of the line connecting the circle; determine a second distance between the intersection and the chamfer profile point; determine a second average value, a second maximum value, and a second standard deviation of each second distance, and define the second average value, the second maximum value, and the second standard deviation as the chamfer profile point distance error parameter.
[0144] In one possible implementation, the determining module 902 is specifically configured to: if the chamfer type is a standard straight chamfer or a straight chamfer with burrs, determine each first region enclosed by the chamfer profile and the line connecting the two target chamfer vertices; and define each first region as the difference region; if the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, determine the circles tangent to the two target chamfer vertices respectively; determine the circular arc between the two target chamfer vertices in the circle, and determine each second region enclosed by the circular arc profile and the circular arc; and define each second region as the difference region.
[0145] In one possible implementation, the determining module 902 is specifically used to determine the intersection point of the two target chamfers along the corresponding edge direction of the liquid crystal panel; determine each distance between each target chamfer vertex and the intersection point, and determine each difference between each distance and a pre-saved standard chamfer size as the chamfer vertex distance error parameter.
[0146] In one possible implementation, the detection module 901 is further configured to identify each edge contour line of the liquid crystal panel image according to an edge detection algorithm; if the number of identified edge contour lines is a preset number, the intersection point of two adjacent edge contour lines is determined, and the target area is determined according to the intersection point and the specifications of the pre-saved target area; if the number of identified edge contour lines is not a preset number, the liquid crystal panel is determined to be unqualified.
[0147] Example 9:
[0148] Based on the above embodiments, this application also provides an electronic device. Figure 10 This application provides a schematic diagram of an electronic device structure, such as... Figure 10 As shown, it includes: processor 1001, communication interface 1002, memory 1003 and communication bus 1004, wherein processor 1001, communication interface 1002 and memory 1003 communicate with each other through communication bus 1004.
[0149] The memory 1003 stores a computer program. When the program is executed by the processor 1001, the processor 1001 performs the following steps:
[0150] Based on the key point detection algorithm, candidate chamfer vertices in the target region to be detected are determined;
[0151] If the number of candidate chamfer vertices is at least two, then determine the smallest bounding rectangle containing each candidate chamfer vertex, and determine the first candidate chamfer vertex that is closest to the first preset edge of the smallest bounding rectangle, and the second candidate chamfer vertex that is closest to the second preset edge of the smallest bounding rectangle; determine the first candidate chamfer vertex and the second candidate chamfer vertex as the target chamfer vertex;
[0152] Based on the contour extraction algorithm and the two target chamfer vertices, the chamfer contour points in the minimum bounding rectangle are identified; based on the chamfer contour points and the two target chamfer vertices, the chamfer contour is determined.
[0153] In one possible implementation, the processor is further configured to:
[0154] Based on the chamfer profile, determine the chamfer type corresponding to the chamfer profile;
[0155] Based on the positions of the two target chamfer vertices, determine the chamfer vertex distance error parameter between the chamfer profile and the standard chamfer.
[0156] Based on the chamfer type and the position of each candidate chamfer profile point, determine the chamfer profile point distance error parameter between the chamfer profile corresponding to the chamfer profile and the standard chamfer.
[0157] Based on the chamfer type and the chamfer profile, determine each difference region between the chamfer corresponding to the chamfer profile and the standard chamfer, determine the number of difference regions whose area exceeds the area threshold, and the difference regions whose area exceeds the area threshold;
[0158] At least one of the following is used as the inspection criteria: chamfer type, chamfer vertex distance error parameter, chamfer contour point distance error parameter, quantity, and total area.
[0159] If each sub-content in the inspection content is less than the corresponding threshold requirement, the chamfer corresponding to the chamfer profile is determined to be a qualified chamfer.
[0160] In one possible implementation, the processor is further configured to:
[0161] The chamfer profile is input into the trained classification model to obtain the chamfer type output by the classification model; wherein, the chamfer type includes: standard straight chamfer, standard rounded chamfer, straight chamfer with burrs and rounded chamfer with burrs.
[0162] In one possible implementation, the processor is further configured to:
[0163] If the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then determine each first distance from each chamfer profile point to the line connecting the two target chamfer vertices; determine the first average, first maximum, and first standard deviation of each first distance, and determine the first average, first maximum, and first standard deviation as the chamfer profile point distance error parameters;
[0164] If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; for each chamfer profile point, determine the line connecting the chamfer profile point and the center of the circle, and determine the intersection point of the line connecting the circle; determine the second distance between the intersection point and the chamfer profile point; determine the second average value, the second maximum value and the second standard deviation of each second distance, and determine the second average value, the second maximum value and the second standard deviation as the chamfer profile point distance error parameters.
[0165] In one possible implementation, the processor is further configured to:
[0166] If the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then each first region enclosed by the chamfer profile and the line connecting the two target chamfer vertices is determined; each first region is determined as the difference region;
[0167] If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; determine the circular arc between the two target chamfer vertices in the circle, and determine each second region enclosed by the circular arc profile and the circular arc; and determine each second region as the difference region.
[0168] In one possible implementation, the processor is further configured to:
[0169] Determine the intersection point of the two target chamfers along the corresponding edge direction of the LCD panel;
[0170] Determine each distance between each target chamfer vertex and the intersection point, and determine each difference between each distance and a pre-saved standard chamfer size as the chamfer vertex distance error parameter.
[0171] In one possible implementation, the processor is further configured to:
[0172] Based on the edge detection algorithm, each edge contour line of the LCD panel image is identified;
[0173] If the number of identified edge contour lines is a preset number, then the intersection point of two adjacent edge contour lines is determined, and the target area is determined according to the intersection point and the specifications of the pre-saved target area.
[0174] If the number of identified edge contour lines is not the preset number, the liquid crystal panel is determined to be defective.
[0175] Since the principle of the above-mentioned electronic device in solving the problem is similar to that of the chamfer determination method, the implementation of the above-mentioned electronic device can be found in the embodiments of the method, and repeated details will not be repeated.
[0176] The communication bus mentioned in the aforementioned electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface 1002 is used for communication between the aforementioned electronic device and other devices. The memory can include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory can also be at least one storage device located remotely from the aforementioned processor.
[0177] The processors mentioned above can be general-purpose processors, including central processing units, network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits, field-programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
[0178] Example 10:
[0179] Based on the above embodiments, this invention also provides a computer-readable storage medium storing a computer program executable by a processor. When the program runs on the processor, it causes the processor to perform the following steps:
[0180] Based on the key point detection algorithm, candidate chamfer vertices in the target region to be detected are determined;
[0181] If the number of candidate chamfer vertices is at least two, then determine the smallest bounding rectangle containing each candidate chamfer vertex, and determine the first candidate chamfer vertex that is closest to the first preset edge of the smallest bounding rectangle, and the second candidate chamfer vertex that is closest to the second preset edge of the smallest bounding rectangle; determine the first candidate chamfer vertex and the second candidate chamfer vertex as the target chamfer vertex;
[0182] Based on the contour extraction algorithm and the two target chamfer vertices, the chamfer contour points in the minimum bounding rectangle are identified; based on the chamfer contour points and the two target chamfer vertices, the chamfer contour is determined.
[0183] In one possible implementation, the method further includes:
[0184] Based on the chamfer profile, determine the chamfer type corresponding to the chamfer profile;
[0185] Based on the positions of the two target chamfer vertices, determine the chamfer vertex distance error parameter between the chamfer profile and the standard chamfer.
[0186] Based on the chamfer type and the position of each candidate chamfer profile point, determine the chamfer profile point distance error parameter between the chamfer profile corresponding to the chamfer profile and the standard chamfer.
[0187] Based on the chamfer type and the chamfer profile, determine each difference region between the chamfer corresponding to the chamfer profile and the standard chamfer, determine the number of difference regions whose area exceeds the area threshold, and the difference regions whose area exceeds the area threshold;
[0188] At least one of the following is used as the inspection criteria: chamfer type, chamfer vertex distance error parameter, chamfer contour point distance error parameter, quantity, and total area.
[0189] If each sub-content in the inspection content is less than the corresponding threshold requirement, the chamfer corresponding to the chamfer profile is determined to be a qualified chamfer.
[0190] In one possible implementation, determining the chamfer type of the chamfer corresponding to the chamfer profile based on the chamfer profile includes:
[0191] The chamfer profile is input into the trained classification model to obtain the chamfer type output by the classification model; wherein, the chamfer type includes: standard straight chamfer, standard rounded chamfer, straight chamfer with burrs and rounded chamfer with burrs.
[0192] In one possible implementation, determining the chamfer profile point distance error parameter between the chamfer profile corresponding to the chamfer profile and the standard chamfer, based on the chamfer type and the position of each chamfer profile point, includes:
[0193] If the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then determine each first distance from each chamfer profile point to the line connecting the two target chamfer vertices; determine the first average, first maximum, and first standard deviation of each first distance, and determine the first average, first maximum, and first standard deviation as the chamfer profile point distance error parameters;
[0194] If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; for each chamfer profile point, determine the line connecting the chamfer profile point and the center of the circle, and determine the intersection point of the line connecting the circle; determine the second distance between the intersection point and the chamfer profile point; determine the second average value, the second maximum value and the second standard deviation of each second distance, and determine the second average value, the second maximum value and the second standard deviation as the chamfer profile point distance error parameters.
[0195] In one possible implementation, determining each difference region between the chamfer profile and the standard chamfer, based on the chamfer type and the chamfer profile, includes:
[0196] If the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then each first region enclosed by the chamfer profile and the line connecting the two target chamfer vertices is determined; each first region is determined as the difference region;
[0197] If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; determine the circular arc between the two target chamfer vertices in the circle, and determine each second region enclosed by the circular arc profile and the circular arc; and determine each second region as the difference region.
[0198] In one possible implementation, determining the chamfer vertex distance error parameter between the chamfer profile corresponding to the standard chamfer and the chamfer profile based on the positions of the two target chamfer vertices includes:
[0199] Determine the intersection point of the two target chamfers along the corresponding edge direction of the LCD panel;
[0200] Determine each distance between each target chamfer vertex and the intersection point, and determine each difference between each distance and a pre-saved standard chamfer size as the chamfer vertex distance error parameter.
[0201] In one possible implementation, before determining candidate chamfer vertices in the target region to be detected based on the keypoint detection algorithm, the method further includes:
[0202] Based on the edge detection algorithm, each edge contour line of the LCD panel image is identified;
[0203] If the number of identified edge contour lines is a preset number, then the intersection point of two adjacent edge contour lines is determined, and the target area is determined according to the intersection point and the specifications of the pre-saved target area.
[0204] If the number of identified edge contour lines is not the preset number, the liquid crystal panel is determined to be defective.
[0205] Since the principle of the computer-readable storage medium in solving the problem is similar to that of chamfer determination, the implementation of the computer-readable storage medium can be found in the embodiments of the method, and repeated details will not be repeated.
[0206] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0207] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0208] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0209] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0210] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.
Claims
1. A method for determining a chamfer, characterized in that, The method includes: Based on the key point detection algorithm, candidate chamfer vertices in the target region to be detected are determined; If the number of candidate chamfer vertices is at least two, then determine the smallest bounding rectangle containing each candidate chamfer vertex, and determine the first candidate chamfer vertex that is closest to the first preset edge of the smallest bounding rectangle, and the second candidate chamfer vertex that is closest to the second preset edge of the smallest bounding rectangle; determine the first candidate chamfer vertex and the second candidate chamfer vertex as the target chamfer vertex; Based on the contour extraction algorithm and the two target chamfer vertices, identify the chamfer contour points in the minimum bounding rectangle; determine the chamfer contour based on the chamfer contour points and the two target chamfer vertices. Based on the chamfer profile, the chamfer is analyzed from multiple dimensions to determine whether the chamfer corresponding to the chamfer profile is a qualified chamfer. The multiple dimensions include chamfer type, chamfer vertex distance error parameter between the chamfer corresponding to the chamfer profile and the standard chamfer, number of chamfer regions whose area exceeds the area threshold for each difference region between the chamfer corresponding to the chamfer profile and the standard chamfer, and the total area of chamfer regions whose area exceeds the area threshold.
2. The method according to claim 1, characterized in that, The step of analyzing the chamfer from multiple dimensions based on the chamfer profile to determine whether the chamfer corresponding to the chamfer profile is a qualified chamfer includes: Based on the chamfer profile, determine the chamfer type corresponding to the chamfer profile; Based on the positions of the two target chamfer vertices, determine the chamfer vertex distance error parameter between the chamfer profile and the standard chamfer. Based on the chamfer type and the position of each candidate chamfer profile point, determine the chamfer profile point distance error parameter between the chamfer profile corresponding to the chamfer profile and the standard chamfer. Based on the chamfer type and the chamfer profile, determine each difference region between the chamfer corresponding to the chamfer profile and the standard chamfer, and determine the number of difference regions whose area exceeds the area threshold, and the total area of the difference regions whose area exceeds the area threshold; At least one of the following is used as the inspection criteria: chamfer type, chamfer vertex distance error parameter, chamfer contour point distance error parameter, quantity, and total area. If each sub-content in the inspection content is less than the corresponding threshold requirement, the chamfer corresponding to the chamfer profile is determined to be a qualified chamfer.
3. The method according to claim 2, characterized in that, The step of determining the chamfer type corresponding to the chamfer profile based on the chamfer profile includes: The chamfer profile is input into the trained classification model to obtain the chamfer type output by the classification model; wherein, the chamfer type includes: standard straight chamfer, standard rounded chamfer, straight chamfer with burrs and rounded chamfer with burrs.
4. The method according to claim 3, characterized in that, The step of determining the chamfer profile point distance error parameter between the chamfer profile corresponding to the chamfer profile and the standard chamfer, based on the chamfer type and the position of each chamfer profile point, includes: If the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then determine each first distance from each chamfer profile point to the line connecting the two target chamfer vertices; determine the first average, first maximum, and first standard deviation of each first distance, and determine the first average, first maximum, and first standard deviation as the chamfer profile point distance error parameters; If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; for each chamfer profile point, determine the line connecting the chamfer profile point and the center of the circle, and determine the intersection point of the line connecting the circle; determine the second distance between the intersection point and the chamfer profile point; determine the second average value, the second maximum value and the second standard deviation of each second distance, and determine the second average value, the second maximum value and the second standard deviation as the chamfer profile point distance error parameters.
5. The method according to claim 3, characterized in that, The step of determining each difference region between the chamfer profile and the standard chamfer, based on the chamfer type and the chamfer profile, includes: If the chamfer type is a standard straight chamfer or a straight chamfer with burrs, then each first region enclosed by the chamfer profile and the line connecting the two target chamfer vertices is determined; each first region is determined as the difference region; If the chamfer type is a standard circular arc chamfer or a circular arc chamfer with burrs, then determine the circles that are tangent to the two target chamfer vertices respectively; determine the circular arc between the two target chamfer vertices in the circle, and determine each second region enclosed by the circular arc profile and the circular arc; and determine each second region as the difference region.
6. The method according to claim 2, characterized in that, The step of determining the chamfer vertex distance error parameter between the chamfer profile and the standard chamfer based on the positions of the two target chamfer vertices includes: Determine the intersection point of the two target chamfers along the corresponding edge direction of the LCD panel; Determine each distance between each target chamfer vertex and the intersection point, and determine each difference between each distance and a pre-saved standard chamfer size as the chamfer vertex distance error parameter.
7. The method according to claim 1, characterized in that, Before determining the candidate chamfer vertices in the target region to be detected based on the key point detection algorithm, the method further includes: Based on the edge detection algorithm, each edge contour line of the LCD panel image is identified; If the number of identified edge contour lines is a preset number, then the intersection point of two adjacent edge contour lines is determined, and the target area is determined according to the intersection point and the specifications of the pre-saved target area. If the number of identified edge contour lines is not the preset number, the liquid crystal panel is determined to be defective.
8. A chamfer determining device, characterized in that, The device includes: The detection module is used to determine candidate chamfer vertices in the target area to be detected based on the key point detection algorithm; The determining module is configured to: if the number of candidate chamfer vertices is at least two, determine the smallest bounding rectangle containing each candidate chamfer vertex, and determine the first candidate chamfer vertex closest to the first preset edge of the smallest bounding rectangle, and the second candidate chamfer vertex closest to the second preset edge of the smallest bounding rectangle; determine the first candidate chamfer vertex and the second candidate chamfer vertex as target chamfer vertices; identify chamfer contour points in the smallest bounding rectangle according to the contour extraction algorithm and the two target chamfer vertices; determine the chamfer contour according to the chamfer contour points and the two target chamfer vertices; and analyze the chamfer from multiple dimensions according to the chamfer contour to determine whether the chamfer corresponding to the chamfer contour is a qualified chamfer; wherein, the multiple dimensions include chamfer type, chamfer vertex distance error parameter between the chamfer corresponding to the chamfer contour and the standard chamfer, the number of chamfer regions whose area exceeds an area threshold and the total area of chamfer regions whose area exceeds the area threshold.
9. An electronic device, characterized in that, The electronic device includes a processor that executes a computer program stored in a memory to implement the steps of the chamfer determination method as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the chamfer determination method as described in any one of claims 1-7.
Citation Information
Patent Citations
Detection method and system of liquid crystal panel
CN115494659A