Method and system for automatically generating positioning area and terminal equipment

Abstract

The invention relates to the technical field of semiconductor detection, provides a method for generating a positioning area in image detection, and particularly relates to a method and a system for automatically generating a positioning area and terminal equipment. According to the invention, the edge distribution states on the plurality of slice images are obtained, the basic positioning area is determined based on the edge distribution states, and geometric space expansion is carried out on the basic positioning area to obtain the final matching frame, so that automatic generation of the positioning area is realized. Compared with the manual drawing process of the positioning area in the prior art, the method can achieve the automatic generation of the positioning area based on the image processing method, thereby improving the image processing efficiency and the accuracy of subsequent detection.

Description

Technical Field

[0001] The present application relates to the field of semiconductor detection technology, and is a method for generating a positioning area in image detection, and specifically relates to a method, system and terminal device for automatically generating a positioning area. Background Art

[0002] Wafer inspection is a key link in the semiconductor integrated circuit manufacturing process. With the continuous development of integrated circuit manufacturing technology, the requirements for wafer inspection are becoming higher and higher. Existing wafer inspection technology usually uses a high-magnification microscope lens for inspection, resulting in a single chip being split into dozens or even hundreds of images for inspection. In this case, each image needs to be marked with a positioning area to ensure the accuracy of the inspection.

[0003] The traditional way of marking the positioning area is to draw it manually, but this method is time-consuming and labor-intensive. With the continuous improvement of detection requirements, the number of images of a single chip is also increasing. The workload of manually drawing the positioning area will become increasingly large, and the efficiency will be greatly reduced. Therefore, a method for automatically generating positioning areas is urgently needed to improve the efficiency of wafer detection. Summary of the invention

[0004] In order to solve the above problems, the present application provides a method, system and terminal device for automatically generating a positioning area, which determines the positioning area by detecting the edge pixels and the straight lines in the chip area. It saves a lot of time and energy without manual drawing and improves the automation level of wafer detection.

[0005] In order to achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:

[0006] In a first aspect, a method for automatically generating a positioning area is provided, which is applied to multiple slice images of a chip, each slice image corresponds to the field of view of each image acquisition device, and the method includes: extracting edges on the multiple slice images; the edges include edges in a first direction and edges in a second direction; traversing each slice image based on a detection frame, determining the edge distribution state of all edges of each slice image within the detection frame area, and selecting a basic positioning area based on the edge distribution state; extending the area based on the edge features in the basic positioning area to obtain a landmark area, and generating a corresponding matching frame based on the landmark area, and generating a positioning area for a complete chip image based on the matching frame; the complete chip image is an image obtained by splicing multiple slice images.

[0007] In some specific implementations, the extracting edges on the multiple slice images includes: filtering the slice images, and extracting edges on the filtered slice images based on a Canny operator to obtain x-direction edges and y-direction edges of the slice images.

[0008] In some specific implementations, the detection frame size is smaller than the size of each of the slice images, and sliding window detection is performed on each of the slice images to determine whether there are edges in the detection frame area corresponding to each sliding window and count the number of edges in each of the detection frame areas.

[0009] In some specific implementations, the edge distribution state in the detection frame area is the number of edges; and selecting the basic positioning area based on the edge distribution state includes: counting the number of edges in multiple detection frame areas, and determining the detection frame area with the largest number of edges as the basic positioning area.

[0010] In some specific implementations, the region extension based on the edge features in the basic positioning region to obtain the landmark region includes: performing edge expansion processing on multiple edges in the basic positioning region based on a target expansion kernel until a critical state is reached, and updating the positioning region in the current state to the landmark region; the critical state is that the current slice image only has edges in the landmark region and does not have other edges.

[0011] In some specific implementations, the target expansion kernel is determined based on a marker edge in the basic positioning region and spatial positions of multiple detection regions, and the marker edge is an edge with the largest area in the basic positioning region.

[0012] In some specific implementations, multiple distances between the mark edge and multiple detection areas are obtained, and the minimum distance is selected as the target expansion kernel.

[0013] In some specific implementations, generating a corresponding matching frame based on the landmark area includes: obtaining a maximum circumscribed rectangle of an edge in the landmark area as the matching frame.

[0014] In a second aspect, a positioning area automatic generation system is provided, comprising: an image receiving unit for receiving a plurality of slice images corresponding to a plurality of field of view ranges acquired by an image acquisition device; an edge extraction unit for extracting edges on the plurality of slice images; an initial positioning unit for generating a basic positioning area; and a positioning area generation unit for generating a positioning area.

[0015] In a third aspect, a terminal device is provided, comprising: a processor and a memory connected to the processor, the memory storing instructions executed by the processor, and the instructions causing the processor to perform operations to perform a method for automatically generating a positioning area as described in any one of the above.

[0016] In a fourth aspect, a readable medium is provided, wherein the readable medium stores computer-readable instructions, wherein the computer-readable instructions include instructions for executing the method for automatically generating a positioning area as described in any one of the above.

[0017] In the technical solution provided in the embodiment of the present application, the edge distribution state on multiple slice images is obtained, and the basic positioning area is determined based on the edge distribution state, and the final matching frame is obtained by geometrically expanding the basic positioning area to achieve automatic generation of the positioning area. Compared with the manual drawing process of the positioning area in the prior art, this method can realize the automatic generation of the positioning area based on the image processing method, thereby improving the image processing efficiency and the accuracy of subsequent detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] The methods, systems and / or programs in the accompanying drawings will be further described according to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein example numbers represent similar mechanisms in the various views of the accompanying drawings.

[0020] Figure 1 It is a schematic diagram of the positioning area provided in the embodiment of the present application on the chip image.

[0021] Figure 2 It is a flowchart of a positioning area generation method provided in an embodiment of the present application.

[0022] Figure 3 It is a schematic diagram of the structure of the positioning area generation system provided in an embodiment of the present application.

[0023] Figure 4 It is a schematic diagram of the server structure provided in an embodiment of the present application.

[0024] Figure 5 It is a schematic diagram of the computer-readable storage medium structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0026] In the following detailed description, numerous specific details are set forth by way of example in order to provide a comprehensive understanding of the relevant guidance. However, it will be apparent to those skilled in the art that the present application may be practiced without these details. In other cases, well-known methods, procedures, systems, compositions and / or circuits have been described at a relatively high level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.

[0027] Flowcharts are used in the present application to illustrate the execution process performed by the system according to the embodiment of the present application. It should be clearly understood that the execution process of the flowchart may not be performed in order. On the contrary, these execution processes may be performed in reverse order or simultaneously. In addition, at least one other execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.

[0028] Before further describing the embodiments of the present invention in detail, the nouns and terms involved in the embodiments of the present invention are described. The nouns and terms involved in the embodiments of the present invention are subject to the following interpretations.

[0029] (1) In response, it is used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0030] (2) Based on is used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or have a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0031] The embodiment of the present application provides a method for automatically generating a positioning area, which is applied to detection and positioning in chip detection on a wafer. With the continuous development of integrated circuit manufacturing technology, the requirements for wafer detection are getting higher and higher. The existing wafer detection technology uses a high-magnification microscope lens for detection, resulting in a single chip being split into dozens or even hundreds of images for detection. In this case, it is necessary to mark the positioning area of ​​each image to ensure the accuracy of the detection.

[0032] The processing logic is to select an edge distribution as a dense area as a basic area on multiple slice images, and based on this basic area, the most expressive edge is used as a landmark edge, and an aggregate is generated based on this landmark edge and the associated edges until the aggregate meets the preset generation end conditions, and a positioning frame is generated based on this aggregate.

[0033] In this embodiment, the above processing method can select a most iconic area on multiple slices as a positioning frame, thereby achieving positioning of the chip image.

[0034] For more information about this method, see Figure 2 The following steps are involved:

[0035] Step S21: Extracting edges on multiple slice images.

[0036] In this embodiment, multiple slice images are images of a partial area of ​​the chip under each field of view, multiple chip slice images constitute a complete chip image, and multiple complete chip images constitute a complete wafer image. Wherein, the chip refers to each independent chip unit on the wafer. For the edge in this embodiment, it is a first direction edge and a second direction edge. Wherein, the first direction edge is an X-direction edge or a Y-direction edge, the second direction edge is an X-direction edge or a Y-direction edge, and the first direction edge and the second direction edge are edges in different directions.

[0037] In this embodiment, the edge extraction process is implemented by an operator extraction method, and the canny operator is preferably selected for implementation. For the canny operator, the edge extraction process first calculates the gradient strength and direction of each pixel in the image, and then uses non-maximum suppression to eliminate the stray effects caused by edge detection, and then uses double threshold detection to determine the real and potential edges, and finally completes the edge extraction by suppressing isolated weak edges.

[0038] In this embodiment, each slice image needs to be filtered before obtaining the gradient strength and direction. Generally, in the prior art, a Gaussian filter is usually used for filtering. For Gaussian filtering, the corresponding Gaussian convolution kernel needs to be determined first. In order to avoid the problem of unsatisfactory filtering results caused by inaccurate selection of the Gaussian convolution kernel, the filtering method of the Gaussian filter in the prior art is abandoned in this embodiment and a median filtering method is used, especially an adaptive median filtering method. For adaptive median filtering, the abnormal pixel points of the image are used to automatically calculate the appropriate filter kernel for noise removal, which effectively prevents the problem of selecting too large or too small filter kernels.

[0039] Specifically, the adaptive median filter is divided into the following two processes, A and B. The processing of process A is expressed as follows: 1. A1 = Z med -Z min ; 2. A2 = Z med -Z max ; 3. If A1>0 and A2<0, jump to process B, otherwise increase the size of the window; 4. If the increased size ≤ S max , then repeat A, otherwise directly output Z med The processing of process B is expressed as: 1. B1 = Z xy -Z min ; 2.B2=Z xy -Z max ; 3. If B1>0 and B2<0, then output Z xy , otherwise output Z med .

[0041] In the adaptive median filtering process of this embodiment, step A first determines whether Z is satisfied. min <Z med <Z max This process is used to determine whether the median point of the current area is a noise point. min <Z med <Z max This condition, the median point is no longer a noise point, jump to B; if Z min =Z med or Z med =Z max , it is considered a noise point, and the window size should be expanded to find a suitable non-noise point in a larger range, and then jump to B. Otherwise, the output median point is a noise point. After jumping to B, determine whether the pixel value of the center point is a noise point. The judgment condition is Z min <Z xy <Z max If Z min =Z xy or Z xy =Z max It is considered to be a noise point. If it is not a noise point, the grayscale value of the current pixel can be retained. If it is a noise point, the median is used to replace the original grayscale value to filter out the noise.

[0042] Step S22: traverse each slice image based on the detection frame, determine the edge distribution state of all edges of each slice image within the detection frame area, and select a basic positioning area based on the edge distribution state.

[0043] In this embodiment, the edge distribution status refers to the number of edges in the current detection frame area. The detection frame can be understood as a sliding window, that is, each slice image is subjected to sliding window processing through the detection frame to determine whether there is an edge in the detection frame area corresponding to each sliding window and to count the edge distribution status in each detection frame area.

[0044] The edge distribution state refers to the number of edges in each detection box area.

[0045] In this embodiment, the edge is used as the generation of the positioning region. However, if multiple slice images contain multiple edges, how to select the edge with the most characteristic expression as the basis for region generation requires screening multiple edges. And if the positioning region is a region with geometric space, after selecting the edge, it is also necessary to expand the geometric space based on this edge, and this edge is a landmark edge.

[0046] In this embodiment, the landmark edge selected should be an edge that can be used for geometric space expansion. Specifically, in this embodiment, an area where the edges are concentrated should be selected as the area for geometric space expansion.

[0047] When the detection frame is a sliding window, the sliding window processing process uses a sliding window to perform edge recognition on each chip slice image after edge extraction, and determines the edge distribution in each window, i.e., each detection frame area. Specifically, the window size of the detection frame, i.e., the sliding window in the present invention should be smaller than the size of the slice image. It is preferred that the window size of the sliding window be 1 / 10 of the length and width of the chip slice image.

[0048] In this embodiment, a sliding window detection is performed on each slice image through a detection frame to determine whether there is an edge in the detection area corresponding to each sliding window and to count the number of edges in each detection area. After the sliding window has completed traversing all slice images on the chip image, the distribution of all edges in the detection area can be obtained.

[0049] The number of edges obtained above is counted to determine the area with the densest edge distribution, that is, the detection area with the largest number of edges as the basic positioning area.

[0050] Step S23. Extend the area based on the edge features in the basic positioning area to obtain a landmark area, generate a corresponding matching frame based on the landmark area, and generate a positioning area for the complete chip image based on the matching frame.

[0051] In this embodiment, for step S22, the edge concentrated distribution area is obtained as the basic positioning area, and the basic positioning area needs to be expanded in geometric space until it reaches a critical state. The expansion of the geometric space is achieved through an expansion operation, and the expansion operation needs to determine the expansion kernel size.

[0052] The size of the expansion kernel is determined according to the edges of different basic positioning areas and the spatial positions of other multiple detection areas.

[0053] Specifically, it is first necessary to determine in the basic positioning area that an edge with a landmark is a landmark edge. In this embodiment, the landmark edge is the edge with the largest area in the basic positioning area, that is, the edge with the largest area is selected in the basic positioning area as the landmark edge, and multiple distances between the landmark edge and other multiple detection areas are calculated, and the smallest distance among the multiple distances is selected as the kernel size of this expansion operation, and all edges in the basic area are expanded based on this kernel to obtain an updated basic positioning area, so as to realize that the area formed by the geometric space expansion of the basic positioning area is the landmark area.

[0054] In this embodiment, the distance calculation between the edge of the mark and other multiple detection areas is implemented based on the Euclidean distance. The Euclidean distance calculation can be implemented using the method in the prior art, which will not be described in detail in this embodiment.

[0055] Among them, the critical state of the geometric space expansion in this embodiment refers to when the current slice image only has edges in the landmark area and no other edges. At this time, the geometric space of the basic positioning area is the final geometric space, which is called an aggregate in this embodiment.

[0056] Finally, the maximum circumscribed rectangle of the aggregate is calculated, and this circumscribed rectangle is used as the matching box generated in this embodiment. The area corresponding to the matching box is the positioning area to be determined in this embodiment. For the representation of this matching box on the chip image, please refer to Figure 1 , where the black box is the matching box finally generated in this embodiment, and the area corresponding to the matching box is the positioning area.

[0057] In this embodiment, the edge distribution state on multiple slice images is obtained, and the basic positioning area is determined based on the edge distribution state, and the final matching frame is obtained by geometrically expanding the basic positioning area to achieve automatic generation of the positioning area. Compared with the manual drawing process of the positioning area in the prior art, this method can realize the automatic generation of the positioning area based on the image processing method, thereby improving the image processing efficiency and the accuracy of subsequent detection.

[0058] In order to better implement the above method, the embodiment of the present application also provides a positioning area automatic generation system, which can be integrated in an electronic device, and the electronic device can be a terminal, a server, etc. Among them, the terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop, a personal computer, etc.; the server can be a single server or a server cluster composed of multiple servers.

[0059] For example, in this embodiment, the method of the embodiment of the present application will be described in detail by taking the system specifically integrated in an electronic device as an example.

[0060] For example, Figure 3 As shown, the system 30 may include an image receiving unit 31, an edge extraction unit 32, an initial positioning unit 33 and a positioning area generation unit 34, wherein:

[0061] The image receiving unit 31 is used to receive a plurality of slice images corresponding to a plurality of visual fields acquired by the image acquisition device.

[0062] In some specific embodiments, the image acquisition device is a microscope lens in an actual scenario for acquiring images of the chip. If the field of view of the microscope lens is small, multiple slice images under multiple fields of view are generated during the chip acquisition process, and the multiple slice images are spliced ​​to form a final chip image.

[0063] The edge extraction unit 32 is used to extract edges on the multiple slice images.

[0064] In some specific implementations, the canny operator is used to extract the edge to obtain the edge in the x direction and the edge in the y direction on the slice image.

[0065] In some specific implementations, when the canny operator is used to extract edges, the slice image needs to be filtered first, and the filter is preferably implemented using a median filter.

[0066] The initial positioning unit 33 is used to generate a basic positioning area.

[0067] In some specific implementations, this process uses a detection frame to traverse each slice image, and determines the edge distribution state of all edges of each slice image within the detection frame area, and selects a basic positioning area based on the edge distribution state.

[0068] In some specific implementations, the size of the detection frame should be smaller than the size of each slice image, and a sliding window detection is performed on each slice image through the detection frame to determine whether there is an edge in the detection frame area corresponding to each sliding window and to count the edge distribution state in each detection frame area. The edge distribution state is the number of edges.

[0069] In some specific implementations, the number of edges in the plurality of detection frame areas is counted, and the detection frame area with the largest number of edges is determined as the basic positioning area.

[0070] The positioning area generating unit 34 is used to generate a positioning area.

[0071] In some specific embodiments, for the landmark region, edge dilation processing is performed on multiple edges in the basic positioning region based on the target dilation kernel until a critical state is reached, and the positioning region in the current state is updated as the landmark region. The critical state is that the current slice image only has edges in the landmark region and does not have other edges.

[0072] In some specific embodiments, the target expansion kernel is determined based on a landmark edge in the basic positioning region and spatial positions of multiple detection regions, where the landmark edge is the edge with the largest area in the basic positioning region.

[0073] In some specific embodiments, multiple distances between the edge of the marker and multiple detection areas are obtained, and the minimum distance is selected as the target dilation kernel.

[0074] In some specific implementations, the maximum bounding rectangle of the edge within the landmark area is obtained as the matching box.

[0075] With respect to the method for automatically generating a positioning area provided in an embodiment of the present application, the edge distribution status on multiple slice images is obtained, and a basic positioning area is determined based on the edge distribution status. The basic positioning area is then geometrically expanded to obtain a final matching frame, thereby realizing automatic generation of the positioning area.

[0076] The embodiment of the present application also provides an electronic device, which can be a terminal, a server, etc. The terminal can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop, a personal computer, etc. The server can be a single server or a server cluster composed of multiple servers, etc.

[0077] In some embodiments, the system may also be integrated into multiple electronic devices. For example, the automatic positioning area generation system may be integrated into multiple servers, and the automatic positioning area generation method of the present application may be implemented by multiple servers.

[0078] In this embodiment, the electronic device of this embodiment is a server as an example for detailed description, for example, Figure 4 As shown, it shows a schematic diagram of the structure of the server involved in the embodiment of the present application, specifically:

[0079] The server may include one or more processing core processors 401, one or more computer-readable storage media memories 402, a power supply 403, an input module 404, and a communication module 405. Those skilled in the art will appreciate that Figure 4 The server structure shown in the figure does not constitute a limitation on the server, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0080] The processor 401 is the control center of the server, and uses various interfaces and lines to connect various parts of the entire server. It executes various functions of the server and processes data by running or executing software programs and / or modules stored in the memory 402, and calling data stored in the memory 402. In some embodiments, the processor 401 may include one or more processing cores; in some embodiments, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 401.

[0081] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the server, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0082] The server also includes a power supply 403 for supplying power to various components. In some embodiments, the power supply 403 may be logically connected to the processor 401 through a power management system, so that the power management system can manage charging, discharging, power consumption, and other functions. The power supply 403 may also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0083] The server may further include an input module 404, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0084] The server may further include a communication module 405. In some embodiments, the communication module 405 may include a wireless module. The server may perform short-range wireless transmission through the wireless module of the communication module 405, thereby providing wireless broadband Internet access for the user. For example, the communication module 405 may be used to help the user send and receive emails, browse web pages, and access streaming media.

[0085] Although not shown, the server may also include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 401 in the server will load the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 will run the application programs stored in the memory 402, thereby implementing the steps in the methods of the embodiments of the present application.

[0086] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0087] As can be seen from the above, the method provided in this embodiment obtains the edge distribution state on multiple slice images, determines the basic positioning area based on the edge distribution state, and obtains the final matching frame by geometrically expanding the basic positioning area to achieve automatic generation of the positioning area. Compared with the manual drawing process of the positioning area in the prior art, this method can achieve automatic generation of the positioning area based on the image processing method, thereby improving the image processing efficiency and the accuracy of subsequent detection.

[0088] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0089] For this purpose, see Figure 5 The embodiment of the present application provides a computer-readable storage medium 50, which stores computer-readable instructions 501. The computer-readable instructions 501 can be loaded by a processor to execute the steps in any one of the methods for automatically generating a positioning area provided in the embodiment of the present application. For example, the instructions can execute the following steps:

[0090] Extracting edges on multiple slice images;

[0091] Traversing each slice image based on the detection frame, determining the edge distribution state of all edges of each slice image within the detection frame area, and selecting a basic positioning area based on the edge distribution state;

[0092] The region is extended based on the edge features in the basic positioning region to obtain a landmark region, a corresponding matching frame is generated based on the landmark region, and a positioning region is generated for the complete chip image based on the matching frame.

[0093] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0094] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including a computer program / instruction, the computer program / instruction being stored in a computer-readable storage medium. A processor of an electronic device reads the computer program / instruction from the computer-readable storage medium, and the processor executes the computer program / instruction, so that the electronic device executes the method provided in various optional implementations of the chip detection aspect provided in the above embodiments.

[0095] Since the instructions stored in the storage medium can execute the steps in any sub-pixel defect detection method provided in the embodiments of the present application, the beneficial effects that can be achieved by any sub-pixel defect detection method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0096] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0097] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0098] The above is a detailed introduction to the sub-pixel defect detection method, device, terminal, storage medium and program product based on imaging features provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for automatically generating a positioning area, characterized in that: Applied to a plurality of slice images of a chip, each slice image corresponds to the field of view of each image acquisition device, the method comprises: Extracting edges on a plurality of slice images; the edges include edges in a first direction and edges in a second direction; Traversing each slice image based on the detection frame, determining the edge distribution state of all edges of each slice image within the detection frame area, and selecting a basic positioning area based on the edge distribution state; Based on the edge features in the basic positioning area, the area is extended to obtain a landmark area, and a corresponding matching frame is generated based on the landmark area. Based on the matching frame, a positioning area is generated for a complete chip image; the complete chip image is an image obtained by splicing multiple slice images.

2. The method for automatically generating a positioning area according to claim 1, characterized in that: The extracting of edges on the plurality of slice images includes: filtering the slice images, and extracting edges of the filtered slice images based on a Canny operator to obtain edges in the x-direction and the y-direction about the slice images.

3. The method for automatically generating a positioning area according to claim 1, characterized in that: The detection frame size is smaller than the size of each slice image, and a sliding window detection is performed on each slice image to determine whether there is an edge in the detection frame area corresponding to each sliding window and to count the edge distribution status in each detection frame area.

4. The method for automatically generating a positioning area according to claim 3, characterized in that: The edge distribution state in the detection frame area is the number of edges; selecting the basic positioning area based on the edge distribution state includes: counting the number of edges in multiple detection frame areas, and determining the detection frame area with the largest number of edges as the basic positioning area.

5. The method for automatically generating a positioning area according to claim 4, characterized in that: The method of performing regional extension based on edge features in the basic positioning area to obtain a landmark area includes: performing edge expansion processing on multiple edges in the basic positioning area based on a target expansion kernel until a critical state is reached, and updating the positioning area in the current state to be a landmark area; the critical state is that the current slice image only has edges in the landmark area and does not have other edges.

6. The method for automatically generating a positioning area according to claim 5, characterized in that: The target expansion kernel is determined based on the marked edge in the basic positioning area and the spatial positions of multiple detection areas, and the marked edge is the edge with the largest area in the basic positioning area.

7. The method for automatically generating a positioning area according to claim 6, characterized in that: A plurality of distances between the edge of the mark and a plurality of detection areas are obtained, and a minimum distance is selected as the target expansion kernel.

8. The method for automatically generating a positioning area according to claim 6, characterized in that: The generating a corresponding matching frame based on the landmark area includes: obtaining a maximum circumscribed rectangle of an edge in the landmark area as the matching frame.

9. A positioning area automatic generation system, characterized in that: include: An image receiving unit, used for receiving a plurality of slice images corresponding to a plurality of visual field ranges acquired by an image acquisition device; An edge extraction unit, used for extracting edges on a plurality of slice images; The initial positioning unit is used to generate the basic positioning area; The positioning area generating unit is used to generate a positioning area.

10. A terminal device, characterized in that: include: A processor and a memory connected to the processor, wherein the memory stores instructions executed by the processor, and the instructions enable the processor to perform operations to perform the method for automatically generating a positioning area as described in any one of claims 1-8.

Images