A chip quality detection method and device, electronic equipment and storage medium

Abstract

The application provides a chip quality detection method and device, electronic equipment and storage medium. The method comprises the following steps: determining the distance from the midpoint of the detection edge line of the substrate to the detection edge line of the bar corresponding to the midpoint position information and the edge line equation of the bar, to obtain the protruding distance of the chip to be detected; determining the relative angle between the detection edge lines according to the slope of all edge line equations; counting the number of pixel points with different colors from the substrate in the chip image to be detected; inputting the protruding distance, the relative angle and the number of pixel points into the chip detection model to obtain the quality detection result of the chip to be detected; and the chip detection model is trained by the protruding distance, the relative angle and the pixel points of the sample chip, and the corresponding quality detection result. Through the method of the application, the quality of the chip to be detected can be determined, and the accuracy and efficiency of determining the quality of the chip are improved.

Description

Technical Field

[0001] The present invention relates to the field of chip technology, and in particular to a chip quality detection method, device, electronic equipment and storage medium. Background Art

[0002] With the development of science and technology, chips have been widely used in people's lives. In the production process of chips, it is not only necessary to make the chips, but also to test the quality of the finished chips.

[0003] In the prior art, an operator observes the finished chip under a microscope to determine whether the chip is qualified or unqualified. However, the quality error of the chip detected by the operator is large and the detection efficiency is low. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a chip quality detection method, device, electronic device and storage medium, which can determine the quality of the chip to be detected and improve the accuracy and efficiency of determining the chip quality.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting chip quality, the method comprising:

[0006] Obtain edge line equations for the substrate and bars corresponding to the detection edge lines in the image of the chip to be inspected, and midpoint position information of the substrate corresponding to the detection edge line; the detection edge line is an edge line on either side of an edge line perpendicular to a reference line in the image of the chip to be inspected;

[0007] According to the midpoint position information and the edge line equation corresponding to the bar, the distance from the midpoint of the substrate corresponding to the detection edge line to the bar corresponding to the detection edge line is determined to obtain the protrusion distance of the chip to be detected;

[0008] Determine the relative angles between the detected edge lines based on the slopes of all edge line equations;

[0009] Count the number of pixels in the image of the chip to be inspected that have a color different from that of the substrate;

[0010] The protrusion distance, relative angle and number of pixels are input into the chip detection model to obtain the quality detection results of the chip to be detected; the chip detection model is trained through the protrusion distance, relative angle and pixel number of the sample chip and the corresponding quality detection results.

[0011] In a possible implementation, the chip quality detection method further includes:

[0012] Obtaining the protrusion distance, relative angle, and pixel points of the sample chip, as well as the quality inspection results corresponding to the sample chip;

[0013] Standardize the units of protrusion distance, relative angle, and number of pixels of sample chips;

[0014] The protrusion distance, relative angle and number of pixels after unit unification are used as sample data, and the quality inspection results corresponding to the sample chips are used as labels to train the chip inspection model.

[0015] In a possible implementation, obtaining edge line equations of the substrate and the bar corresponding to the detection edge lines respectively includes:

[0016] Extracting position information of at least two edge points of the substrate and the bar corresponding to the detection edge line respectively;

[0017] According to the edge line point position information of the substrate or bar corresponding to the detection edge line, the slope and intercept of the substrate or bar corresponding to the detection edge line are determined, and the edge line equation of the substrate or bar corresponding to the detection edge line is obtained.

[0018] In one possible implementation, determining the slope of the detection edge line corresponding to the substrate or the bar includes:

[0019] Substitute the edge point position information of the substrate or bar corresponding to the detection edge line into the following slope formula to obtain the slope of the substrate or bar corresponding to the detection edge line;

[0020]

[0021] Among them, k is the slope of the detection edge line corresponding to the substrate or bar, n is the number of edge point position information, x i y is the horizontal coordinate of the position information of the ith edge point of the substrate or bar corresponding to the detected edge line, i is the ordinate of the position information of the i-th edge point of the detected edge line corresponding to the substrate or bar.

[0022] In one possible implementation, determining the intercept of the substrate or the bar corresponding to the detection edge line includes:

[0023] Substitute the edge point position information of the substrate or bar corresponding to the detection edge line into the following intercept formula to obtain the intercept of the substrate or bar corresponding to the detection edge line;

[0024]

[0025] Wherein, b is the intercept of the detection edge line corresponding to the substrate or bar, and k is the slope of the detection edge line corresponding to the substrate or bar.

[0026] In a possible implementation, determining the relative angle between the detected edge lines includes:

[0027] Substitute the slopes of all edge line equations into the relative angle formula to obtain the relative angles between the detected edge lines;

[0028] θ=tan -1 k1-tan -1 k2;

[0029] Wherein, θ is the relative angle between the detected edge lines, k1 is the slope of the equation of the edge line corresponding to the substrate, and k2 is the slope of the equation of the edge line corresponding to the bar.

[0030] In a possible implementation, obtaining midpoint position information of a substrate corresponding to a detection edge line includes:

[0031] Extract the position information of the two endpoints of the substrate corresponding to the detection edge line;

[0032] The average value of the horizontal coordinates in the two endpoint position information is determined as the horizontal coordinate in the midpoint position information;

[0033] The average value of the vertical coordinates in the two endpoint position information is determined as the vertical coordinate in the midpoint position information.

[0034] In a second aspect, an embodiment of the present application further provides a chip quality detection device, the chip quality detection device comprising:

[0035] An acquisition module is used to obtain edge line equations of the substrate and the bar corresponding to the detection edge line in the image of the chip to be detected, and the midpoint position information of the detection edge line corresponding to the substrate; the detection edge line is an edge line on either side of the edge line perpendicular to the reference line in the image of the chip to be detected;

[0036] A determination module is used to determine the distance from the midpoint of the substrate corresponding to the detection edge line to the detection edge line corresponding to the bar according to the midpoint position information and the edge line equation corresponding to the bar, so as to obtain the protrusion distance of the chip to be detected;

[0037] The determination module is further used to determine the relative angles between the detected edge lines based on the slopes of all edge line equations;

[0038] A statistics module is used to count the number of pixels in the image of the chip to be detected that have a color different from that of the substrate;

[0039] The input module is used to input the protrusion distance, relative angle and number of pixels into the chip detection model to obtain the quality detection result of the chip to be detected; the chip detection model is trained by the protrusion distance, relative angle and pixel points of the sample chip and the corresponding quality detection results.

[0040] In one possible implementation, a unified module and a training module;

[0041] The acquisition module is also used to obtain the protrusion distance, relative angle and pixel points of the sample chip, as well as the quality inspection results corresponding to the sample chip;

[0042] A unified module is used to unify the units of protrusion distance, relative angle and number of pixels of sample chips;

[0043] The training module is used to train the chip detection model by using the protrusion distance, relative angle and number of pixels after unit unification as sample data and the quality inspection results corresponding to the sample chip as labels.

[0044] In one possible embodiment, the acquisition module is specifically used to extract at least two edge point position information of the detection edge line corresponding to the substrate or the bar, respectively; based on the edge line point position information of the detection edge line corresponding to the substrate or the bar, the slope and intercept of the detection edge line corresponding to the substrate or the bar are determined to obtain the edge line equation of the detection edge line corresponding to the substrate or the bar.

[0045] In one possible implementation, the determination module is specifically configured to substitute edge point position information of the substrate or bar corresponding to the detection edge line into the following slope formula to obtain the slope of the detection edge line corresponding to the substrate or bar; Among them, k is the slope of the detection edge line corresponding to the substrate or bar, n is the number of edge point position information, x i y is the horizontal coordinate of the position information of the ith edge point of the substrate or bar corresponding to the detected edge line, i is the ordinate of the position information of the i-th edge point of the detected edge line corresponding to the substrate or bar.

[0046] In one possible implementation, the determination module is specifically configured to substitute edge point position information of the substrate or bar corresponding to the detection edge line into the following intercept formula to obtain the intercept of the detection edge line corresponding to the substrate or bar; Wherein, b is the intercept of the detection edge line corresponding to the substrate or bar, and k is the slope of the detection edge line corresponding to the substrate or bar.

[0047] In a possible implementation, the determination module is specifically configured to substitute the slopes of all edge line equations into the relative angle formula to obtain the relative angles between the detected edge lines; θ = tan -1 k1-tan -1 k2; where θ is the relative angle between the detected edge lines, k1 is the slope of the edge line equation corresponding to the substrate, and k2 is the slope of the edge line equation corresponding to the bar.

[0048] In one possible embodiment, the acquisition module is specifically used to extract the two endpoint position information corresponding to the detection edge line of the substrate; determine the average value of the horizontal coordinates in the two endpoint position information as the horizontal coordinate in the midpoint position information; and determine the average value of the vertical coordinates in the two endpoint position information as the vertical coordinate in the midpoint position information.

[0049] In a third aspect, an embodiment of the present application further provides an electronic device comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate through the bus, and the processor executes the machine-readable instructions to perform the steps of any chip quality detection method as described in the first aspect.

[0050] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the chip quality detection method as described in any one of the first aspects are executed.

[0051] The present invention provides a chip quality detection method, device, electronic device, and storage medium. The method includes: obtaining edge line equations corresponding to detection edge lines of a substrate and a bar in an image of a chip to be detected, and midpoint position information of the detection edge line corresponding to the substrate; the detection edge line is an edge line on either side of an edge line perpendicular to a reference line in the image of the chip to be detected; determining the distance from the midpoint of the detection edge line corresponding to the substrate to the detection edge line corresponding to the bar based on the midpoint position information and the edge line equation corresponding to the bar, thereby obtaining a protrusion distance of the chip to be detected; determining the relative angle between the detection edge lines based on the slopes of all edge line equations; counting the number of pixels in the image of the chip to be detected that have a color different from that of the substrate; inputting the protrusion distance, relative angle, and number of pixels into a chip detection model to obtain a quality detection result of the chip to be detected; the chip detection model is trained using the protrusion distance, relative angle, and pixel points of sample chips, as well as the corresponding quality detection results. The present invention improves the accuracy and efficiency of determining chip quality by determining the quality of the chip to be detected based on the protrusion distance, relative angle, and pixel points of the chip to be detected. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0053] Figure 1A flow chart of a chip quality detection method provided in an embodiment of the present application is shown;

[0054] Figure 2 A schematic diagram of a chip image to be detected provided in an embodiment of the present application is shown;

[0055] Figure 3 A flow chart showing another chip quality detection method provided in an embodiment of the present application is shown;

[0056] Figure 4 A schematic structural diagram of a chip quality detection device provided in an embodiment of the present application is shown;

[0057] Figure 5 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the contents of this application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0059] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0060] To enable those skilled in the art to utilize the contents of this application, the following embodiments are provided in conjunction with a specific application scenario, the "chip technology field." Those skilled in the art will appreciate that the general principles defined herein can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application. Although this application is primarily described in the "chip technology field," it should be understood that this is merely an exemplary embodiment.

[0061] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0062] The following is a detailed description of a chip quality detection method provided in an embodiment of the present application.

[0063] Reference Figure 1 FIG. 1 is a flow chart of a chip quality detection method provided in an embodiment of the present application. The specific execution process of the chip quality detection method is as follows:

[0064] S101 , obtaining edge line equations of detection edge lines corresponding to the substrate and the bars in the image of the chip to be detected, and midpoint position information of the detection edge line corresponding to the substrate.

[0065] S102 , determining the distance from the midpoint of the substrate corresponding to the detection edge line to the detection edge line corresponding to the bar according to the midpoint position information and the edge line equation corresponding to the bar, and obtaining the protrusion distance of the chip to be detected.

[0066] S103 : Determine the relative angles between the detected edge lines according to the slopes of all edge line equations.

[0067] S104 , counting the number of pixels in the image of the chip to be inspected that have a color different from that of the substrate.

[0068] S105: Input the protrusion distance, relative angle, and number of pixels into a chip detection model to obtain a quality detection result of the chip to be detected.

[0069] The present invention provides a method for detecting chip quality, the method comprising: obtaining edge line equations corresponding to detection edge lines of a substrate and a bar in an image of a chip to be detected, and midpoint position information of the detection edge line corresponding to the substrate; the detection edge line is an edge line on either side of an edge line perpendicular to a reference line in the image of the chip to be detected; determining the distance from the midpoint of the detection edge line corresponding to the substrate to the detection edge line corresponding to the bar based on the midpoint position information and the edge line equation corresponding to the bar, thereby obtaining a protrusion distance of the chip to be detected; determining the relative angle between the detection edge lines based on the slopes of all edge line equations; counting the number of pixels in the image of the chip to be detected that have a color different from that of the substrate; inputting the protrusion distance, relative angle, and number of pixels into a chip detection model to obtain a quality detection result of the chip to be detected; the chip detection model is trained using the protrusion distance, relative angle, and pixel points of sample chips, as well as the corresponding quality detection results. The present invention can determine the quality of the chip to be detected by using the protrusion distance, relative angle, and pixel points of the chip to be detected, thereby improving the accuracy and efficiency of determining chip quality.

[0070] The following describes the exemplary steps of the embodiment of the present application:

[0071] S101 , obtaining edge line equations of detection edge lines corresponding to the substrate and the bars in the image of the chip to be detected, and midpoint position information of the detection edge line corresponding to the substrate.

[0072] In the embodiment of this application, Figure 2 Figure 1 is a schematic diagram of an image of a chip to be inspected provided in an embodiment of the present application. The chip to be inspected shown in the figure includes a substrate and a bar, where the bar refers to a semiconductor laser bar. The edge line equations of the substrate's detection edge line, the edge line equations of the bar's detection edge line, and the midpoint position information of the corresponding detection edge line on the substrate are obtained in the image of the chip to be inspected. A reference line is located in the center of the substrate. This reference line is parallel to the left and right edges of the reference line, or to the upper and lower edges of the substrate. The detection edge line is any edge line on either side of the edge line perpendicular to the reference line. For example, if the reference line is parallel to the left and right edges of the substrate, then the reference line is perpendicular to the upper and lower edges of the substrate and the bar. In other words, the detection edge line can be the upper edge line of the substrate and the upper edge line of the bar, or the lower edge line of the substrate and the lower edge line of the bar. The detection edge lines of the substrate and the bar must be on the same side of the edge line. The midpoint position information refers to the position information of the midpoint of the detection edge line, including the abscissa and ordinate of the midpoint.

[0073] Specifically, the edge line equation of the substrate or bar corresponding to the detection edge line is determined by the following steps:

[0074] I. Extract the position information of at least two edge points of the substrate and the bar corresponding to the detection edge line respectively.

[0075] In the embodiments of the present application, edge point location information refers to the position coordinates of pixel points on the detected edge line, including the horizontal and vertical coordinates of the pixel points. If the detected edge line can be the upper edge line of the substrate or the upper edge line of the bar, the position coordinates of the points on the upper edge line of the substrate and the upper edge line of the bar are extracted.

[0076] II. Determine the slope and intercept of the edge line corresponding to the substrate or bar based on the edge line point position information of the substrate or bar, and obtain the edge line equation of the edge line corresponding to the substrate or bar.

[0077] In the embodiment of the present application, the slope and intercept of the edge line are detected, that is, the slope and intercept of the edge line equation. The edge line equation is a linear equation of one variable, so it is sufficient to determine the slope and intercept in the edge line equation.

[0078] Furthermore, determining the slope of the detection edge line corresponding to the substrate or the bar specifically includes:

[0079] Substitute the edge point position information of the substrate or bar corresponding to the detection edge line into the following slope formula to obtain the slope of the substrate or bar corresponding to the detection edge line.

[0080]

[0081] Among them, k is the slope of the detection edge line corresponding to the substrate or bar, n is the number of edge point position information, x i y is the horizontal coordinate of the position information of the ith edge point of the substrate or bar corresponding to the detected edge line, i is the ordinate of the position information of the i-th edge point of the detected edge line corresponding to the substrate or bar.

[0082] Furthermore, determining the intercept of the detection edge line corresponding to the substrate or the bar specifically includes:

[0083] Substitute the edge point position information of the substrate or bar corresponding to the detection edge line into the following intercept formula to obtain the intercept of the substrate or bar corresponding to the detection edge line.

[0084]

[0085] Where b is the intercept of the detection edge line corresponding to the substrate or bar, k is the slope of the detection edge line corresponding to the substrate or bar, n is the number of edge point position information, x i y is the horizontal coordinate of the position information of the ith edge point of the substrate or bar corresponding to the detected edge line, i is the ordinate of the position information of the i-th edge point of the detected edge line corresponding to the substrate or bar.

[0086] Specifically, the midpoint position information of the substrate corresponding to the detection edge line is determined by the following steps:

[0087] I. Extract the position information of the two endpoints of the substrate corresponding to the detection edge line.

[0088] In the embodiment of the present application, the endpoint position information is the coordinates of the two endpoints of the detection edge line, including the horizontal coordinate and the vertical coordinate.

[0089] II. Determine the average value of the horizontal coordinates in the two endpoint position information as the horizontal coordinate in the midpoint position information.

[0090] III. Determine the average value of the vertical coordinates in the two endpoint position information as the vertical coordinate in the midpoint position information.

[0091] S102 , determining the distance from the midpoint of the substrate corresponding to the detection edge line to the detection edge line corresponding to the bar according to the midpoint position information and the edge line equation corresponding to the bar, and obtaining the protrusion distance of the chip to be detected.

[0092] In the embodiment of the present application, the protrusion distance is one of the quality inspection features of the chip to be inspected. The distance from the midpoint of the inspection edge line of the substrate to the inspection edge line corresponding to the bar is used as the protrusion distance of the chip to be inspected.

[0093] The protrusion distance is determined by the following formula:

[0094]

[0095] Wherein, d is the protrusion distance of the chip to be detected, b2 is the intercept of the edge line equation corresponding to the bar, k2 is the slope of the edge line equation corresponding to the bar, X is the horizontal coordinate of the midpoint position information, and Y is the vertical coordinate of the midpoint position information.

[0096] S103 : Determine the relative angles between the detected edge lines according to the slopes of all edge line equations.

[0097] In the embodiment of the present application, the relative angle refers to the angle between the detection edge line of the substrate and the detection edge line of the bar, which is one of the quality detection features of the chip to be detected.

[0098] Specifically, the slopes of all edge line equations are substituted into the relative angle formula to obtain the relative angles between the detected edge lines.

[0099] θ=tan -1 k1-tan -1 k2;

[0100] Wherein, θ is the relative angle between the detected edge lines, k1 is the slope of the equation of the edge line corresponding to the substrate, and k2 is the slope of the equation of the edge line corresponding to the bar.

[0101] S104 , counting the number of pixels in the image of the chip to be inspected that have a color different from that of the substrate.

[0102] In this embodiment, if a pixel in the image of the chip under inspection differs from the color of the substrate, it is considered an abnormal pixel, indicating that the chip is unqualified. The number of pixels counted is the number of abnormal pixels in the chip. The number of pixels is one of the quality detection features of the chip under inspection.

[0103] S105: Input the protrusion distance, relative angle, and number of pixels into a chip detection model to obtain a quality detection result of the chip to be detected.

[0104] In the embodiment of the present application, the chip detection model is used to determine whether the chip to be detected is qualified. The quality detection results include qualified and unqualified detection results.

[0105] Specifically, the protrusion distance, relative angle and pixel points of the sample chip, as well as the quality inspection result corresponding to the sample chip, are obtained; the units of the protrusion distance, relative angle and number of pixel points of the sample chip are unified; the protrusion distance, relative angle and number of pixel points after the unit unification are used as sample data, and the quality inspection result corresponding to the sample chip is used as a label to train the chip detection model.

[0106] Reference Figure 3 FIG. 1 is a flow chart of another chip quality detection method provided in an embodiment of the present application. The specific execution process of the chip quality detection method is as follows:

[0107] S301 : Obtain the protrusion distance, relative angle, and pixel points of the sample chip, as well as the quality inspection result corresponding to the sample chip.

[0108] In an embodiment of the present application, multiple sample chip images are acquired, and then bilateral filtering is used to filter the sample chip images to remove noise points caused by the light source. The filtered images are edge detected using a 3*3 Sobel operator to identify at least two edge point position information corresponding to the detection edge line of the substrate and the bar in the sample chip image; based on the edge line point position information of the detection edge line corresponding to the substrate or bar, the slope and intercept of the detection edge line corresponding to the substrate or bar are determined to obtain the edge line equation of the detection edge line corresponding to the substrate or bar; then the midpoint position information of the detection edge line corresponding to the substrate is determined; based on the midpoint position information and the edge line equation corresponding to the bar, the distance from the midpoint of the detection edge line corresponding to the substrate to the detection edge line corresponding to the bar is determined to obtain the protrusion distance of the sample chip; based on the slopes of all edge line equations, the relative angles between the detection edge lines are determined to obtain the relative angle of the sample chip; the number of pixels in the chip image to be detected that are different in color from the substrate is counted to obtain the number of pixels of the sample chip. The quality inspection results corresponding to the sample chip are manually calibrated.

[0109] Here, the bilateral filtering in this embodiment is not only related to the pixel value, but also to the pixel position, and can better preserve the edge. The specific formula is as follows:

[0110]

[0111] W q =∑ p∈S G s (p)G r (p);

[0112]

[0113] Where Ip is the gray value of a pixel in the sample chip image, Iq is the gray value of any pixel in the sample chip image except point p, S is all the pixels in the sample chip image, Gr is the spatial distance weight, Gr is the pixel weight, and W q is the sum of the pixel weights of the filter window, and BF is the filtered sample chip image.

[0114] S302: Unify the units of the protrusion distance, relative angle, and number of pixels of the sample chip.

[0115] In the embodiment of the present application, the units of each protrusion distance, each relative angle, and each number of pixels are unified using the following formulas.

[0116]

[0117] Where M is the value after unit unification, N is the protrusion distance or relative angle or number of pixels of a sample chip, A is the minimum value of all protrusion distances or all relative angles or all pixel numbers, and B is the maximum value of all protrusion distances or all relative angles or all pixel numbers.

[0118] Because the units for the sample chip protrusion distance, relative angle, and number of pixels are not uniform and their corresponding numerical ranges differ, the chip detection model's classifier's calculation of the distance between sample chips will depend on values ​​within a wide range, reducing the classifier's accuracy. Unifying the units can avoid this problem by ignoring the influence of the units between features and controlling the range between features to [0, 1], reducing the computational effort.

[0119] S303: Use the protrusion distance, relative angle and number of pixels after unit unification as sample data and the quality inspection results corresponding to the sample chips as labels to train the chip inspection model.

[0120] In the embodiment of the present application, the chip detection model adopts the following model:

[0121]

[0122] Where V is the volume of the hypersphere V(r), C is the penalty coefficient, R is the radius of the hypersphere r, O is the center of the hypersphere parameter, ε i is the slack variable, and m is the number of sample chips.

[0123] Here, assuming that the generated hypersphere parameters are the center and the corresponding hypersphere radius r is greater than zero, the hypersphere volume is minimized, and the center supports linear combinations; similar to the traditional SVM method, it can be required that the distance from all training data points to the center is strictly less than r. However, a slack variable ε of the penalty coefficient C is also constructed. i After solving the Lagrangian duality, we can determine whether the new training data point is inside the hypersphere. If the distance from z to the center is less than or equal to the radius r, it is qualified. If it is outside the hypersphere, it is unqualified.

[0124] The present application provides another chip quality detection method, comprising: obtaining the protrusion distance, relative angle, and pixel count of a sample chip, as well as the quality detection result corresponding to the sample chip; unifying the units of the protrusion distance, relative angle, and number of pixel counts of the sample chip; and using the unified protrusion distance, relative angle, and number of pixel counts as sample data and the quality detection result corresponding to the sample chip as a label to train a chip detection model. The present application can obtain a chip detection model with high accuracy to detect the quality detection result of the chip to be detected.

[0125] Based on the same inventive concept, the embodiments of the present application also provide a chip quality detection device corresponding to the chip quality detection method. Since the principle of solving the problem by the device in the embodiments of the present application is similar to the above-mentioned chip quality detection method in the embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0126] Reference Figure 4 FIG. 1 is a schematic diagram of a chip quality detection device provided in an embodiment of the present application. The chip quality detection includes:

[0127] An acquisition module 401 is configured to obtain edge line equations corresponding to detection edge lines of the substrate and the bars in the image of the chip to be inspected, and midpoint position information of the detection edge lines corresponding to the substrate; the detection edge lines are edge lines on either side of edge lines perpendicular to a reference line in the image of the chip to be inspected;

[0128] Determination module 402, for determining the distance from the midpoint of the substrate corresponding to the detection edge line to the detection edge line corresponding to the bar based on the midpoint position information and the edge line equation corresponding to the bar, thereby obtaining the protrusion distance of the chip to be detected;

[0129] The determination module 402 is further configured to determine relative angles between detected edge lines based on the slopes of all edge line equations;

[0130] A statistics module 403 is used to count the number of pixels in the image of the chip to be detected that have a color different from that of the substrate;

[0131] Input module 404 is used to input the protrusion distance, relative angle and number of pixels into the chip detection model to obtain the quality detection result of the chip to be detected; the chip detection model is trained by the protrusion distance, relative angle and pixel points of the sample chip and the corresponding quality detection results.

[0132] In one possible implementation, the unification module 405 and the training module 406;

[0133] The acquisition module 401 is further used to obtain the protrusion distance, relative angle and pixel points of the sample chip, as well as the quality detection result corresponding to the sample chip;

[0134] A unification module 405 is used to unify the units of the protrusion distance, relative angle and number of pixels of the sample chip;

[0135] The training module 406 is used to train the chip detection model by using the protrusion distance, relative angle and number of pixels after unit unification as sample data and the quality detection results corresponding to the sample chips as labels.

[0136] In one possible embodiment, the acquisition module 401 is specifically used to extract at least two edge point position information of the detection edge line corresponding to the substrate and the bar respectively; based on the edge line point position information of the detection edge line corresponding to the substrate or the bar, the slope and intercept of the detection edge line corresponding to the substrate or the bar are determined to obtain the edge line equation of the detection edge line corresponding to the substrate or the bar.

[0137] In one possible implementation, the determination module 402 is specifically configured to substitute the edge point position information of the substrate or bar corresponding to the detection edge line into the following slope formula to obtain the slope of the detection edge line corresponding to the substrate or bar; Among them, k is the slope of the detection edge line corresponding to the substrate or bar, n is the number of edge point position information, x i y is the horizontal coordinate of the position information of the ith edge point of the substrate or bar corresponding to the detected edge line, i is the ordinate of the position information of the i-th edge point of the detected edge line corresponding to the substrate or bar.

[0138] In one possible implementation, the determination module 402 is specifically configured to substitute the edge point position information of the substrate or bar corresponding to the detection edge line into the following intercept formula to obtain the intercept of the detection edge line corresponding to the substrate or bar; Wherein, b is the intercept of the detection edge line corresponding to the substrate or bar, and k is the slope of the detection edge line corresponding to the substrate or bar.

[0139] In a possible implementation, the determination module 402 is specifically configured to substitute the slopes of all edge line equations into the relative angle formula to obtain the relative angles between the detected edge lines; θ = tan -1 k1-tan -1 k2; where θ is the relative angle between the detected edge lines, k1 is the slope of the edge line equation corresponding to the substrate, and k2 is the slope of the edge line equation corresponding to the bar.

[0140] In one possible embodiment, the acquisition module 401 is specifically used to extract the two endpoint position information corresponding to the detection edge line of the substrate; determine the average value of the horizontal coordinates in the two endpoint position information as the horizontal coordinate in the midpoint position information; and determine the average value of the vertical coordinates in the two endpoint position information as the vertical coordinate in the midpoint position information.

[0141] An embodiment of the present application provides a chip quality detection device, which can determine the quality of the chip to be detected by using the protrusion distance, relative angle and pixel points of the chip to be detected, thereby improving the accuracy and efficiency of determining the chip quality.

[0142] like Figure 5 As shown, an electronic device 500 provided in an embodiment of the present application includes: a processor 501, a memory 502 and a bus, the memory 502 stores machine-readable instructions executable by the processor 501, and when the electronic device is running, the processor 501 communicates with the memory 502 through the bus, and the processor 501 executes the machine-readable instructions to perform the steps of the chip quality detection method as described above.

[0143] Specifically, the memory 502 and the processor 501 can be general-purpose memories and processors, which are not specifically limited here. When the processor 501 runs the computer program stored in the memory 502, the chip quality detection method can be executed.

[0144] Corresponding to the above-mentioned chip quality detection method, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the above-mentioned chip quality detection method are executed.

[0145] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0146] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0147] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0148] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the information processing method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0149] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A chip quality detection method, characterized in that: The chip quality detection method includes: Obtain edge line equations for detection edge lines corresponding to the substrate and the bar in the image of the chip to be inspected, and midpoint position information of the detection edge lines corresponding to the substrate; the detection edge lines are edge lines on either side of edge lines perpendicular to the reference line in the image of the chip to be inspected; Determine the distance from the midpoint of the substrate's corresponding detection edge line to the detection edge line of the bar according to the midpoint position information and the edge line equation corresponding to the bar, and obtain the protrusion distance of the chip to be detected; determining relative angles between the detected edge lines according to the slopes of all edge line equations; Counting the number of pixels in the image of the chip to be detected that have a color different from that of the substrate; The protrusion distance, the relative angle and the number of pixels are input into a chip detection model to obtain a quality detection result of the chip to be detected; the chip detection model is trained through the protrusion distance, relative angle and pixel points of the sample chip and the corresponding quality detection results.

2. The chip quality detection method according to claim 1, characterized in that: The chip quality detection method further includes: Obtaining the protrusion distance, relative angle, and pixel points of the sample chip, as well as the quality inspection result corresponding to the sample chip; Unifying the units of the protrusion distance, relative angle, and number of pixels of the sample chip; The protrusion distance, relative angle and number of pixels after unit unification are used as sample data, and the quality inspection results corresponding to the sample chips are used as labels to train the chip inspection model.

3. The chip quality detection method according to claim 1, characterized in that: Obtain edge line equations for the substrate and bar corresponding to the detection edge lines, including: respectively extracting position information of at least two edge points of the substrate and the bar corresponding to the detection edge line; According to the edge line point position information of the substrate or the bar corresponding to the detection edge line, the slope and intercept of the substrate or the bar corresponding to the detection edge line are determined to obtain the edge line equation of the substrate or the bar corresponding to the detection edge line.

4. The chip quality detection method according to claim 3, characterized in that: Determining the slope of the detection edge line corresponding to the substrate or the bar includes: Substituting the edge point position information of the substrate or the bar corresponding to the detection edge line into the following slope formula to obtain the slope of the substrate or the bar corresponding to the detection edge line; Among them, k is the slope of the detection edge line corresponding to the substrate or bar, n is the number of edge point position information, x i y is the horizontal coordinate of the position information of the ith edge point of the substrate or bar corresponding to the detected edge line, i is the ordinate of the position information of the i-th edge point of the detected edge line corresponding to the substrate or bar.

5. The chip quality detection method according to claim 4, characterized in that: Determining the intercept of the substrate or the bar corresponding to the detection edge line includes: Substituting the edge point position information of the substrate or the bar corresponding to the detection edge line into the following intercept formula to obtain the intercept of the substrate or the bar corresponding to the detection edge line; Wherein, b is the intercept of the detection edge line corresponding to the substrate or bar, and k is the slope of the detection edge line corresponding to the substrate or bar.

6. The chip quality detection method according to claim 1, characterized in that: Determining the relative angle between the detected edge lines includes: Substituting the slopes of all edge line equations into the relative angle formula, the relative angles between the detected edge lines are obtained; θ=time -1 k1-time -1 k2; Wherein, θ is the relative angle between the detected edge lines, k1 is the slope of the equation of the edge line corresponding to the substrate, and k2 is the slope of the equation of the edge line corresponding to the bar.

7. The chip quality detection method according to claim 1, characterized in that: Obtaining midpoint position information of a detection edge line corresponding to the substrate includes: Extracting position information of two endpoints of the substrate corresponding to the detection edge line; Determine the average value of the horizontal coordinates in the two endpoint position information as the horizontal coordinate in the midpoint position information; The average value of the vertical coordinates in the two endpoint position information is determined as the vertical coordinate in the midpoint position information.

8. A chip quality detection device, characterized in that: The chip quality detection device includes: an acquisition module, configured to acquire edge line equations corresponding to detection edge lines of the substrate and the bar in the image of the chip to be inspected, and midpoint position information of the detection edge lines corresponding to the substrate; the detection edge lines are edge lines on either side of edge lines perpendicular to a reference line in the image of the chip to be inspected; a determination module, configured to determine the distance from the midpoint of the detection edge line corresponding to the substrate to the detection edge line corresponding to the bar based on the midpoint position information and the edge line equation corresponding to the bar, thereby obtaining a protrusion distance of the chip to be detected; The determination module is further configured to determine relative angles between the detected edge lines based on the slopes of all edge line equations; A statistics module, configured to count the number of pixels in the image of the chip to be detected that have a color different from that of the substrate; An input module is used to input the protrusion distance, the relative angle and the number of pixels into a chip detection model to obtain a quality detection result of the chip to be detected; the chip detection model is trained by the protrusion distance, relative angle and pixel points of the sample chip and the corresponding quality detection results.

9. An electronic device, characterized in that: include: A processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the machine-readable instructions to perform the steps of the chip quality detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the chip quality detection method according to any one of claims 1 to 7 are executed.

Images