Chip edge breakage detection method, computing device and storage medium

Abstract

The invention relates to the field of chip intelligent manufacturing, and discloses a chip edge breakage detection method, a computing device and a storage medium, and the method comprises the steps: determining a chip component region where a chip component is located from a segmented image of a chip; determining a minimum surrounding rectangle of the chip component area, wherein four edges of the minimum surrounding rectangle are tangent lines of at least one point on the outline of the chip component area; each edge of the minimum surrounding rectangle moves towards the center to determine a detection rectangle, the center of the detection rectangle coincides with the center of the minimum surrounding rectangle, the length and the width of the detection rectangle are parallel to the length and the width of the minimum surrounding rectangle respectively, and the moving distance between each edge of the detection rectangle and the corresponding edge of the minimum surrounding rectangle is the edge breakage depth; determining a difference set of the minimum enclosing rectangle and the chip component area as a difference area; and if the difference region and the detection rectangle have a common part, determining that the chip has an edge breakage problem.

Description

Technical Field

[0001] The present invention relates to the field of intelligent chip manufacturing, and in particular to a chip edge collapse detection method, computing equipment and storage medium. Background Art

[0002] In the modern electronics industry, chips are widely used in various high-tech devices, and their performance and quality play a key role in the stability and life of the entire system. With the continuous reduction of chip manufacturing processes and the increasing complexity of packaging technology, the physical integrity of chips is particularly important, especially the edge collapse problem that is prone to occur in the edge area of ​​the chip. The edge collapse of the chip will directly affect the packaging quality, signal transmission and the reliability of the chip itself. Therefore, how to efficiently and accurately detect the edge collapse problem of the chip is one of the important topics in the current chip detection field.

[0003] In the prior art, chip edge collapse problems can be detected by manual detection or machine learning detection methods. Manual detection is a traditional detection method, in which the inspector directly observes the edge area of ​​the chip through a microscope or magnifying device to identify whether the chip has edge collapse defects with the naked eye. Although this method can detect edge collapse problems to a certain extent, it is inefficient, and the detection results are greatly affected by the subjective judgment of the inspectors, making it difficult to achieve unified detection standards. In addition, manual detection is gradually unable to cope with high-precision detection, especially when the chip size is reduced and the edge morphology is complicated, the accuracy of manual detection cannot meet the requirements.

[0004] With the development of machine learning technology, especially the application of convolutional neural networks (CNN) in image recognition, some studies have attempted to apply machine learning technology to chip edge collapse detection. These methods extract edge collapse features and classify them by constructing and training a large amount of edge collapse sample data. However, machine learning methods require a large amount of labeled data, which is difficult to obtain and has high requirements for computing resources. In addition, the algorithm training time is long, and the universality of the model varies between different types of chips, so there are still certain challenges in practical application.

[0005] Therefore, a new chip edge collapse detection method is needed. Summary of the invention

[0006] To this end, the present invention provides a chip edge collapse detection method to try to solve or at least alleviate the above problems.

[0007] According to a first aspect of the present invention, there is provided a chip edge chipping detection method suitable for execution in a computing device, the method comprising: determining a chip component area where chip components are located from a segmented image of the chip; determining a minimum enclosing rectangle of the chip component area, wherein four sides of the minimum enclosing rectangle are tangents of at least one point on the contour of the chip component area; moving each side of the minimum enclosing rectangle toward the center to determine a detection rectangle, wherein the center of the detection rectangle coincides with the center of the minimum enclosing rectangle, and the length and width of the detection rectangle are respectively parallel to the length and width of the minimum enclosing rectangle, and the distance that each side of the detection rectangle moves from the corresponding side of the minimum enclosing rectangle is the edge chipping depth; determining a difference set between a minimum circumscribed rectangle and the chip component area as a differential area, wherein the differential area is a portion that belongs to the minimum circumscribed rectangle but does not belong to the fill color area in the segmented image; if the differential area has a common portion with the detection rectangle, it is determined that the chip has an edge chipping problem.

[0008] Optionally, the method according to the present invention further includes: acquiring an image of a chip to be detected, segmenting the image to be detected according to components contained in the chip, and obtaining a segmented image of the chip, wherein the chip segmented image is an image taken of a chip area, including a component in the chip.

[0009] Optionally, in the method according to the present invention, the method further comprises: setting a filling color in the chip component area to obtain a filling color area, wherein the filling color is a pure color, so as to determine the range of the chip component area according to the filling color area.

[0010] Optionally, in the method according to the present invention, determining the minimum enclosing rectangle of the chip component area includes: determining the minimum enclosing rectangle of the chip component area according to the color-filled area.

[0011] Optionally, in the method according to the present invention, the edge collapse depth is the edge collapse detection threshold. When detecting the edge collapse problem of the chip, when the deepest distance of the chip defect from the chip edge is greater than the edge collapse depth, the chip defect is regarded as an edge collapse defect.

[0012] Optionally, in the method according to the present invention, the method also includes: when the differential area and the detection area have a common part, setting the common part to a first color in the segmented image, and setting other areas of the segmented image except the common part to a second color; returning the segmented image with the first color and the second color set to identify the edge collapse defect.

[0013] Optionally, in the method according to the present invention, the method also includes: when the differential area and the detection rectangle have a common part, determining one or more edge chipping defects included in the common part, and each determined edge chipping defect does not overlap with each other in the segmented image; determining the minimum enclosing rectangle of each edge chipping defect; determining the edge of the minimum enclosing rectangle of the edge chipping defect that overlaps with the detection rectangle based on the vertex coordinates of the minimum enclosing rectangle of the edge chipping defect and the vertex coordinates of the detection rectangle, as the overlapping edge; determining the edge of the minimum enclosing rectangle of the fill color area whose distance from the overlapping edge is the edge chipping depth as the schematic edge; and drawing an identification frame of the edge chipping defect in the image to be detected based on the schematic edge and the minimum enclosing rectangle of the edge chipping defect.

[0014] Optionally, in the method according to the present invention, drawing an identification frame of the edge collapse defect in the image to be detected based on the schematic edge and the minimum enclosing rectangle of the edge collapse defect includes: comparing the coordinates of the schematic edge and each edge in the minimum enclosing rectangle of the edge collapse defect, and determining the maximum and minimum values ​​of the coordinates of the schematic edge and each edge in the minimum enclosing rectangle of the edge collapse defect; and determining the position of each edge of the identification frame based on the maximum and minimum values.

[0015] According to a second aspect of the present invention, there is provided a computing device, comprising: one or more processors; a memory; and one or more devices, wherein the one or more devices include instructions for a chip edge collapse detection method.

[0016] According to a third aspect of the present invention, there is provided a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, which, when executed by a computing device, enable the computing device to execute a chip edge collapse detection method.

[0017] The present invention proposes a chip edge collapse detection method, which determines a chip component area where chip components are located from a segmented image of the chip; determines the minimum enclosing rectangle of the chip component area, and moves each side of the minimum enclosing rectangle toward the center to determine a detection rectangle so as to determine a difference set between the minimum circumscribed rectangle and the chip component area as a differential area. If the differential area has a common part with the detection rectangle, it is determined that the chip has an edge collapse problem, thereby realizing detection of whether the chip has an edge collapse defect, and improving the detection speed and efficiency of the chip edge collapse defect.

[0018] Furthermore, the specific location of the edge collapse can be determined and marked in the image to be detected and / or the segmented image, so as to subsequently optimize the front-end process. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to achieve the above and related purposes, the present invention describes certain illustrative aspects in conjunction with the following description and the accompanying drawings, which indicate various ways in which the principles disclosed in the present invention can be practiced, and all aspects and their equivalents are intended to fall within the scope of the claimed subject matter. By reading the following detailed description in conjunction with the accompanying drawings, the above and other purposes, features and advantages disclosed by the present invention will become more apparent. Throughout the present disclosure, the same reference numerals generally refer to the same parts or elements.

[0020] Figure 1 A schematic diagram of a computing device 100 according to an exemplary embodiment of the present invention is shown;

[0021] Figure 2 A schematic diagram showing a chip edge collapse detection method 200 according to an exemplary embodiment of the present invention is shown;

[0022] Figure 3 A schematic diagram of an image to be detected according to an exemplary embodiment of the present invention is shown;

[0023] Figure 4 A schematic diagram of segmenting an image according to an exemplary embodiment of the present invention is shown;

[0024] Figure 5 A schematic diagram of setting a fill color for a chip component region according to an exemplary embodiment of the present invention is shown;

[0025] Figure 6 A schematic diagram of a minimum enclosing rectangle according to an exemplary embodiment of the present invention is shown;

[0026] Figure 7 A schematic diagram showing the depth of chipping according to an exemplary embodiment of the present invention is shown;

[0027] Figure 8 A schematic diagram of a detection rectangle according to an exemplary embodiment of the present invention is shown;

[0028] Fig. 9 A schematic diagram showing a differential region according to an exemplary embodiment of the present invention is shown;

[0029] Fig.10 A schematic diagram with common parts marked according to an exemplary embodiment of the present invention is shown;

[0030] Fig.11 A schematic diagram of drawing a marking frame in an image to be detected according to an exemplary embodiment of the present invention is shown. DETAILED DESCRIPTION

[0031] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to enable the scope of the present disclosure to be fully conveyed to those skilled in the art. The same reference numerals generally refer to the same components or elements.

[0032] According to an embodiment of the present invention, a chip edge collapse detection method of the present invention is suitable for being executed in a computing device. Figure 1 A schematic diagram of a computing device according to an exemplary embodiment of the present invention is shown.

[0033] Figure 1 1 shows a block diagram of a computing device according to an exemplary embodiment of the present invention. In a basic configuration, computing device 100 includes at least one processing unit 120 and system memory 110. According to one aspect, depending on the configuration and type of computing device, system memory 110 includes, but is not limited to, volatile storage (e.g., random access memory), non-volatile storage (e.g., read-only memory), flash memory, or any combination of such memories. According to one aspect, system memory 110 includes operating system 111.

[0034] According to one aspect, operating system 111, for example, is suitable for controlling the operation of computing device 100. Furthermore, examples may be practiced in conjunction with graphics libraries, other operating systems, or any other application programs, and are not limited to any particular application or system. Figure 1 This basic configuration is illustrated in FIG by those components within dashed line 115. According to one aspect, computing device 100 has additional features or functionality. For example, according to one aspect, computing device 100 includes additional data storage devices (removable and / or non-removable), such as magnetic disks, optical disks, or tapes.

[0035] As stated above, according to one aspect, the program module 112 is stored in the system memory 110. According to one aspect, the program module 112 can be implemented as one or more computer program products, and the present application does not limit the type of computer program products, for example, it can include: email, word processing application, spreadsheet application, database application, slide show application, painting or computer-aided application, web browser, etc. In some embodiments according to the present application, the computer program / instructions related to the power grid investment scale prediction method are packaged as a computer program product, and when these computer programs / instructions are executed by the processor (i.e., the processing unit 120), the power grid investment scale prediction method according to the present application is implemented.

[0036] According to one aspect, the examples may be practiced on a circuit comprising discrete electronic components, a packaged or integrated electronic chip containing logic gates, a circuit utilizing a microprocessor, or a single chip containing electronic components or a microprocessor. Figure 1 Each or many components shown in can be integrated in a system on chip (SOC) on a single integrated circuit to practice examples. According to one aspect, such a SOC device may include one or more processing units, a graphics unit, a communication unit, a system virtualization unit, and various application functions, all of which are integrated (or "burned") into a chip substrate as a single integrated circuit. When operated via SOC, the functions described in this article can be operated via a dedicated logic integrated with other components of the computing device 800 on a single integrated circuit (chip). Embodiments of the present invention can also be practiced using other technologies capable of performing logical operations (such as AND, OR, and NOT), including but not limited to mechanical, optical, fluid, and quantum technologies. In addition, embodiments of the present invention can be practiced in a general-purpose computer or in any other circuit or system.

[0037] According to one aspect, the computing device 100 may also have one or more input devices 131, such as a keyboard, a mouse, a pen, a voice input device, a touch input device, etc. Output devices 132 may also be included, such as a display, a speaker, a printer, etc. The aforementioned devices are examples and other devices may also be used. The computing device 100 may include one or more communication connections 133 that allow communication with other computing devices 140. Examples of suitable communication connections 133 include, but are not limited to: RF transmitters, receivers, and / or transceiver circuits; Universal Serial Bus (USB), parallel and / or serial ports. The computing device 100 can be communicatively connected to other computing devices 140 via a communication connection 333.

[0038] The embodiment of the present invention also provides a non-transitory readable storage medium, which stores instructions, and the instructions are used to make the computing device perform a method according to an embodiment of the present invention. The readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be a computer-readable instruction, a data structure, a module of a program, or other data. Examples of readable storage media include, but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, tape disk storage or other magnetic storage device or any other non-transitory readable storage medium.

[0039] According to one aspect, communication media is implemented by computer readable instructions, data structures, program modules, or other data in a modulated data signal (e.g., a carrier wave or other transport mechanism), and includes any information delivery media. According to one aspect, the term "modulated data signal" describes a signal that has one or more characteristics set or changed in a manner that encodes information in the signal. By way of example and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, radio frequency (RF), infrared, and other wireless media.

[0040] It should be noted that, although the computing device shown above only includes the processing unit 120, the system memory 110, the input device 131, the output device 132, and the communication connection 133, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the device may only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0041] Figure 2 FIG. 2 is a schematic diagram showing a chip edge collapse detection method 200 according to an exemplary embodiment of the present invention. Figure 2 As shown, firstly, step 210 is performed to determine the chip component region where the chip component is located from the segmented image of the chip.

[0042] According to one embodiment of the present invention, the present invention first obtains an image of the chip to be tested for edge collapse, that is, the image to be tested. The present invention does not limit the specific method of obtaining the image to be tested, and the image can be obtained by photographing the chip to be tested for edge collapse using a camera or other equipment.

[0043] Figure 3 FIG. 4 is a schematic diagram of an image to be detected according to an exemplary embodiment of the present invention. Figure 3 As shown, from the image to be detected of the chip, it can be seen that there are multiple components contained inside the chip. The present invention does not limit the number and types of components contained inside the chip, such as may include a microprocessor unit, a storage unit, an input / output interface unit, etc. In order to better detect the chip edge collapse problem, the present invention can segment the image to be detected according to the components contained in the chip to obtain a segmented image of an area of ​​the chip. Each segmented image is an image taken of the chip area, and may include one of the chip. The present invention does not limit the specific method of obtaining the segmented image based on the image to be detected, such as the step of segmenting the image can be implemented by a convolutional neural network: the image to be detected is input into the convolutional neural network to obtain a segmented image. Exemplary convolutional neural networks include: Unet network, etc. The present invention does not limit the specific form of the convolutional neural network used to segment the image.

[0044] Figure 4 FIG. 4 shows a schematic diagram of segmenting an image according to an exemplary embodiment of the present invention. Figure 4 As shown, the segmented image includes an image captured of an area of ​​the chip, specifically an image of a chip component of the chip.

[0045] In order to detect the chip edge collapse problem in the segmented image, the segmented image is processed: the area where the chip component is located (ie, the chip component area) is determined from the segmented image.

[0046] According to one embodiment of the present invention, the present invention can also set a fill color in the chip component area in the segmented image. According to one embodiment of the present invention, the set fill color can be specifically implemented as a pure color, such as white, etc., to facilitate subsequent processing of the chip component area. The present invention does not limit the specific method of setting the fill color.

[0047] Figure 5 FIG. 2 is a schematic diagram showing a method of setting a fill color for a chip component region according to an exemplary embodiment of the present invention. Figure 5 As shown, the fill color is set to white.

[0048] Back to Figure 2, then, execute step 220 to determine the minimum enclosing rectangle of the chip component area, the four sides of the minimum enclosing rectangle are tangents of at least one point on the outline of the chip component area. Determining the minimum enclosing rectangle of the chip component area includes: determining the minimum enclosing rectangle of the chip component area according to the color-filled area, that is, determining the minimum enclosing rectangle of the filled color area according to the position of the filled color area in the segmented image. The four sides of the minimum enclosing rectangle are tangents of at least one point on the outline of the color-filled area. The minimum enclosing rectangle of the filled color area can be determined by contour fitting and the like, and the present invention does not limit the specific method of determining the minimum enclosing rectangle. The sides of the minimum enclosing rectangle with the same normal vector direction are parallel to the sides of the segmented image.

[0049] According to an embodiment of the present invention, the present invention further establishes a coordinate system in the segmented image to determine the vertex coordinates of the minimum enclosing rectangle, so as to subsequently determine the identification frame according to the vertex coordinates of the minimum enclosing rectangle.

[0050] Subsequently, step 230 is executed to move each side of the minimum enclosing rectangle toward the center to determine the detection rectangle, the center of the detection rectangle coincides with the center of the minimum enclosing rectangle, and the length and width of the detection rectangle are respectively parallel to the length and width of the minimum enclosing rectangle, and the distance that each side of the detection rectangle moves from the corresponding side of the minimum enclosing rectangle is the edge collapse depth.

[0051] When each side of the minimum enclosing rectangle is moved toward the center to determine the detection rectangle, the center of the detection rectangle coincides with the center of the minimum enclosing rectangle, and the length and width of the detection rectangle are respectively parallel to the length and width of the minimum enclosing rectangle, and the distance that each side of the detection rectangle moves with the corresponding side of the minimum enclosing rectangle is the edge collapse depth.

[0052] Figure 6 FIG. 4 is a schematic diagram showing a minimum enclosing rectangle according to an exemplary embodiment of the present invention. Figure 6 As shown, rectangle A1 is an example of the minimum enclosing rectangle displayed on the segmented image.

[0053] The edge collapse depth is the edge collapse detection threshold. When detecting the edge collapse problem of a chip, if the distance between the deepest part of the chip defect and the chip edge is greater than the edge collapse depth, the chip defect is regarded as an edge collapse defect. The specific setting value of the edge collapse depth can be set as needed.

[0054] Figure 7 FIG. 4 is a schematic diagram showing the depth of edge chipping according to an exemplary embodiment of the present invention. Figure 7 As shown, the distance x is the depth of the edge collapse. When determining the depth of the edge collapse, the endpoints of the line segment indicating the depth of the edge collapse are on the edges of the minimum enclosing rectangle and the detection rectangle, and the line segment is perpendicular to the edge of the connected rectangle.

[0055] Figure 8 FIG. 4 is a schematic diagram showing a detection rectangle according to an exemplary embodiment of the present invention. Figure 8 As shown, the detection rectangle is inside the minimum circumscribed rectangle, and the distance between each side of the detection rectangle and the corresponding minimum enclosing rectangle is the edge collapse depth. Rectangle A2 is the detection rectangle ( Figure 8 An example of the yellow part in the middle displayed on the segmented image.

[0056] Then, step 240 is executed to determine the difference between the minimum bounding rectangle and the chip component area as the differential area. The differential area is the part of the segmented image that belongs to the minimum bounding rectangle but does not belong to the filled color area.

[0057] The difference between the minimum bounding rectangle and the chip component area (i.e., the filled color area) is determined as the difference area. The difference area is the part of the segmented image that belongs to the minimum bounding rectangle but does not belong to the filled color area.

[0058] Fig. 9 FIG. 4 is a schematic diagram showing a differential region according to an exemplary embodiment of the present invention. Fig. 9 As shown, the white part belongs to the minimum enclosing rectangle but not to the filled color area.

[0059] Finally, step 250 is executed. If the differential area and the detection rectangle have a common part, it is determined that the chip has an edge collapse problem.

[0060] Then, it is determined whether the differential area and the detection rectangle have a common part. If there is a common part, it is determined that the chip has a chip edge collapse problem, and if there is no common part, it is determined that the chip does not have a common part.

[0061] When the difference area and the detection area have a common part, the common part is set to the first color in the segmented image, and the other areas of the segmented image except the common part are set to the second color. The first color is different from the second color. Subsequently, the segmented image with the first color and the second color set is returned to identify the edge collapse defect.

[0062] Fig.10 FIG. 2 shows a schematic diagram with common parts marked according to an exemplary embodiment of the present invention. Fig.10 As shown in the figure, the common part of the differential area and the detection rectangle is set to white, and the other areas in the segmented image are set to black. The common part marked by the white part indicates that the chip at this part has a chip edge collapse defect, as well as the shape and location of the chip edge collapse defect.

[0063] According to an embodiment of the present invention, if the difference area and the detection rectangle do not have a common part, a pure color image can be returned, indicating that there is no edge collapse defect in the chip area shown in the segmented image. The pure color image can be the same size as the segmented image, and the color can be set to black. The present invention does not limit the specific form of the pure color image.

[0064] According to one embodiment of the present invention, when the differential area and the detection rectangle have a common portion, one or more edge collapse defects included in the common portion are determined. When the common portion includes multiple edge collapse defects, each determined edge collapse defect does not overlap with each other in the segmented image and has no common pixel points.

[0065] After determining one or more chipping defects, determine the minimum enclosing rectangle of each chipping defect. The sides of the minimum enclosing rectangle of the chipping defect with the same normal vector are parallel to the sides of the segmented image. Subsequently, the sides where the minimum enclosing rectangle of the chipping defect overlaps with the detection rectangle are determined based on the vertex coordinates of the minimum enclosing rectangle of the chipping defect and the vertex coordinates of the detection rectangle; specifically, a rectangular coordinate system can be established in the segmented image, and the coordinate axes are parallel to the sides of the segmented image, such as the horizontal axis is parallel to the long side of the segmented image, and the vertical axis is parallel to the short side of the segmented image.

[0066] Subsequently, the overlapping edges are determined according to the same vertical coordinates or horizontal coordinates in the vertex coordinates of the minimum enclosing rectangle of the chipped edge defect and the vertex coordinates of the detection rectangle, as the overlapping edges. For example, if the horizontal coordinates of the vertices of the minimum enclosing rectangle of the chipped edge defect are the same as the horizontal coordinates of the vertices of the detection rectangle, then it is determined that the edge of the minimum enclosing rectangle of the chipped edge defect coincides with the long side of the detection rectangle; if the vertical coordinates of the vertices of the minimum enclosing rectangle of the chipped edge defect are the same as the horizontal coordinates of the vertices of the detection rectangle, then it is determined that the edge of the minimum enclosing rectangle of the chipped edge defect coincides with the wide side of the detection rectangle.

[0067] Finally, determine the edge in the minimum enclosing rectangle of the filled color area that is the distance from the overlapping edge to the depth of the edge collapse as the schematic edge; draw the identification frame of the edge collapse defect in the image to be detected based on the schematic edge and the minimum enclosing rectangle of the edge collapse defect. When determining the position of the four edges of the identification frame, compare the coordinates of the schematic edge with the edges in the minimum enclosing rectangle of the edge collapse defect, determine the maximum and minimum values ​​of the coordinates of the schematic edge and the edges in the minimum enclosing rectangle of the edge collapse defect, and determine the position of each edge of the identification frame based on the maximum and minimum values.

[0068] According to one embodiment of the present invention, a rectangular coordinate system is established in the segmented image, and the upper left vertex, lower left vertex, lower right vertex, and upper right vertex of the segmented image are respectively recorded as point A, point B, point C, and point D. Point A is used as the origin of the coordinate system, and the y-axis is determined by point A and point B, and the direction from point A to point B is the positive direction of the y-axis; the x-axis is determined by point A and point D, and the direction from point A to point D is the positive direction of the x-axis.

[0069] The coordinates of the four vertices of the minimum enclosing rectangle of the edge chipping defect are (1,1), (2,1), (1,2), (2,2). The coordinates of the four vertices of the detection rectangle are (1,1), (8,1), (8,8), (1,8). The coordinates of the four vertices of the minimum enclosing rectangle of the fill color area are (0,0), (9,0), (9,9), (0,9). The edge chipping distance is 1.

[0070] First, determine the edge of the minimum enclosing rectangle of the chipping defect that coincides with the detection rectangle. That is, the edge formed by the points (1,1) and (2,1) coincides with the edge formed by the points (1,1) and (8,1); the edge formed by the points (1,1) and (1,2) coincides with the edge formed by the points (1,1) and (1,8).

[0071] Then, the schematic edge is determined based on the coincident edge. The edge whose coincident edge distance from the points (1,1) and (8,1) is 1 is the edge connecting the points (0,0) and (9,0); the edge whose coincident edge distance from the points (1,1) and (1,8) is 1 is the edge connecting the points (0,0) and (0,9).

[0072] Then, according to the schematic edge formed by the points (0,0) and (9,0), the schematic edge formed by the points (0,0) and (0,9), and the edge formed by the four vertices (1,1), (2,1), (1,2), and (2,2) of the minimum enclosing rectangle of the edge collapse defect, the maximum and minimum values ​​in the coordinates of each edge are determined. It can be determined that the minimum value of the x-axis coordinate of each edge is 0, the maximum value is 2, and the minimum value of the y-axis coordinate is 0, and the maximum value is 2. Then, the identification box is determined by connecting the points (0,0), (0,2), (2,2), and (2,0) in sequence.

[0073] Fig.11 FIG. 2 shows a schematic diagram of drawing a marking frame in an image to be detected according to an exemplary embodiment of the present invention. Fig.11 As shown, an identification box is drawn in the image to be detected, and the area circled by the identification box is the area where the edge collapse defect is located.

[0074] The present invention proposes a chip edge collapse detection method, which determines the chip component area where the chip component is located from the segmented image of the chip; determines the minimum enclosing rectangle of the chip component area, and moves each side of the minimum enclosing rectangle toward the center to determine the detection rectangle so as to determine the difference set of the minimum circumscribed rectangle and the chip component area as the differential area. If the differential area has a common part with the detection rectangle, it is determined that the chip has an edge collapse problem, thereby realizing the detection of whether the chip has an edge collapse defect, and improving the detection speed and efficiency of the chip edge collapse defect. Furthermore, the specific location of the edge collapse can be determined and marked in the image to be detected and / or the segmented image, so as to optimize the front-end process later.

[0075] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0076] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof.

[0077] In the case where the program code is executed on a programmable computer, the computing device generally includes a processor, a storage medium readable by the processor (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device. The memory is configured to store the program code; the processor is configured to execute the user identity authentication method of the present invention according to the instructions in the program code stored in the memory.

[0078] By way of example and not limitation, computer readable media include computer storage media and communication media. Computer readable media include computer storage media and communication media. Computer storage media stores information such as computer readable instructions, data structures, program modules or other data. Communication media generally embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and includes any information delivery medium. Any combination of the above is also included within the scope of computer readable media.

[0079] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and instructional purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art. The disclosure of the present invention is illustrative, rather than restrictive, with respect to the scope of the present invention.

[0080] As used herein, unless otherwise specified, the use of ordinal numbers "first," "second," "third," etc. to describe common objects merely indicates that different instances of similar objects are involved, and is not intended to imply that the objects so described must have a given order in time, space, order, or in any other manner.

[0081] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and instructional purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art. The disclosure of the present invention is illustrative, rather than restrictive, with respect to the scope of the present invention.

Claims

1. A chip edge collapse detection method, suitable for being executed in a computing device, the method comprising: determining a chip component region where the chip component is located from the segmented image of the chip; Determine a minimum enclosing rectangle of the chip component area, wherein four sides of the minimum enclosing rectangle are tangent lines of at least one point on the outline of the chip component area; Each side of the minimum enclosing rectangle is moved toward the center to determine the detection rectangle, the center of the detection rectangle coincides with the center of the minimum enclosing rectangle, and the length and width of the detection rectangle are respectively parallel to the length and width of the minimum enclosing rectangle, and the distance between each side of the detection rectangle and the corresponding side of the minimum enclosing rectangle is the edge collapse depth; Determine a difference set between a minimum bounding rectangle and a chip component region as a differential region, wherein the differential region is a portion of the segmented image that belongs to the minimum bounding rectangle but does not belong to the fill color region; If the differential area and the detection rectangle have a common portion, it is determined that the chip has an edge collapse problem.

2. The method of claim 1, wherein: The method further comprises: The image to be detected of the chip is acquired, and the image to be detected is segmented according to the components contained in the chip to obtain a segmented image of the chip, wherein the chip segmented image is an image taken of the chip area, including a component in the chip.

3. The method of claim 1, wherein: The method further comprises: A filling color is set in the chip component area to obtain a filling color area, wherein the filling color is a pure color, so that the range of the chip component area is determined according to the filling color area.

4. The method of claim 3, wherein: Determining the minimum enclosing rectangle of the chip component area includes: The minimum enclosing rectangle of the chip component area is determined according to the color-filled area.

5. The method of claim 1, wherein: The edge collapse depth is an edge collapse detection threshold. When detecting the edge collapse problem of a chip, when the deepest distance of the chip defect from the chip edge is greater than the edge collapse depth, the chip defect is regarded as an edge collapse defect.

6. The method of claim 1, wherein: The method further comprises: When the difference area and the detection area have a common part, the common part is set as the first color in the segmented image, and the other areas of the segmented image except the common part are set as the second color; Returns a segmented image with the first and second colors set to identify chipping defects.

7. The method of claim 1, wherein: The method further comprises: When the differential area and the detection rectangle have a common portion, one or more edge collapse defects included in the common portion are determined, and each of the determined edge collapse defects does not overlap with each other in the segmented image; Determine the minimum enclosing rectangle of each edge collapse defect; According to the vertex coordinates of the minimum enclosing rectangle of the chipping defect and the vertex coordinates of the detection rectangle, the edge where the minimum enclosing rectangle of the chipping defect overlaps with the detection rectangle is determined as the overlapping edge; Determine the edge of the minimum enclosing rectangle of the fill color area whose distance from the coincident edge is the edge collapse depth as the schematic edge; An identification frame of the edge collapse defect is drawn in the image to be detected according to the schematic edge and the minimum enclosing rectangle of the edge collapse defect.

8. The method of claim 7, wherein: Drawing an identification frame of the edge collapse defect in the image to be detected according to the schematic edge and the minimum enclosing rectangle of the edge collapse defect includes: Compare the coordinates of the schematic edge with the coordinates of each edge in the minimum enclosing rectangle of the edge collapse defect, and determine the maximum and minimum values ​​of the coordinates of the schematic edge with the coordinates of each edge in the minimum enclosing rectangle of the edge collapse defect; The positions of the sides of the identification box are determined based on the maximum and minimum values.

9. A computing device, characterized in that include: one or more processors; Memory; as well as One or more devices comprising instructions for executing the method according to any one of claims 1-8.

10. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions which, when executed by a computing device, cause the computing device to perform a method according to any one of claims 1-8.

Images