Feature determination method, device, electronic device, and storage medium

Abstract

The present application provides a feature determination method, apparatus, electronic device, and storage medium. The method comprises: acquiring a first image corresponding to an initial region of a workpiece, selecting a target region within the first image; generating a template feature using the image of the target region, and determining whether the template feature exists in at least one second image, wherein the at least one second image is an image located around the initial region and having an overlapping area with the initial region. The method provided by the present application avoids feature omission by acquiring a second image around the first image and ensuring that the area corresponding to the second image overlaps with the initial region.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a feature determination method. Background Art

[0002] With the continuous advancement of science and technology, the demand for workpiece processing is also increasing. A workpiece refers to the object being processed during the machining process. Taking a semiconductor wafer as an example, there are multiple target units on the semiconductor wafer, and the target units contain components. Slicing the semiconductor wafer can obtain the components on the semiconductor wafer. When dicing the semiconductor wafer, the location of the dicing lanes must be determined.

[0003] Prior art techniques for determining the location of a cutting path require first finding a feature within the target unit, using that feature to represent the target unit and determine the cutting path location. However, prior art techniques often miss features when determining these features, which can lead to inaccurately determined cutting paths. Therefore, how to characterize the target unit—that is, how to determine the feature that represents the target unit—has become a pressing issue for those skilled in the art. Summary of the Invention

[0004] Based on the above problems, the present application provides a feature determination method and device to solve the problem of missing structural features during determination.

[0005] The feature determination method comprises:

[0006] Acquiring a first image corresponding to an initial area of the workpiece;

[0007] selecting a target area in the first image;

[0008] generating template features using the image of the target area;

[0009] It is determined whether the template feature exists in at least one second image, wherein the at least one second image is an image located around the initial region and having an overlapping region with the initial region.

[0010] Optionally, after generating the template features using the image of the target area, the following steps may also be included:

[0011] The overlapping area is determined, wherein a size of the overlapping area is determined using a size of the target area.

[0012] Optionally, determining the overlapping area includes:

[0013] Taking a straight line passing through the center of the second image and the center of the initial area as a first straight line;

[0014] In a case where the first straight line is perpendicular to any side of the initial area, the width of the overlapping area on the first straight line is determined by using the width of the target area on the first straight line;

[0015] When the first straight line is not perpendicular to any side of the initial area, the width of the overlapping area in the target direction is determined using the width of the target area in the target direction, and the target direction includes a first direction parallel to the first side of the initial area and a second direction parallel to the second side of the initial area, and the first direction is perpendicular to the second direction.

[0016] Optionally, the determining the width of the overlapping area in the target direction by using the width of the target area in the target direction includes:

[0017] Taking the width of the target area in the target direction as a first size;

[0018] half of the difference between the width of the first image in the target direction and the width of the target area in the target direction as the second size;

[0019] The width of the overlapping area in the target direction is the minimum value between the first size and the second size.

[0020] Optionally, adjacent second images have overlapping areas.

[0021] Optionally, the at least one second image is obtained by:

[0022] Determine a sliding window, and use the position of the first image as the initial position of the sliding window;

[0023] moving the sliding window at least once;

[0024] The image within the sliding window after each movement is used as the second image.

[0025] Optionally, the feature determination method further includes:

[0026] Acquire at least one third image around an area corresponding to the second image;

[0027] The template feature is determined in the at least one third image, and an area corresponding to the third image and an area corresponding to the second image have an overlapping area.

[0028] Optionally, the feature determination method further includes:

[0029] At least one fourth image is acquired, wherein a distance between a center of an area corresponding to the fourth image and a center of the initial area is greater than a preset distance.

[0030] Optionally, the feature determination method further includes:

[0031] There are a plurality of target units distributed in an array on the workpiece;

[0032] The area of a region formed by the initial region and the region corresponding to the second image is not less than the area of the target unit.

[0033] Optionally, the moving the sliding window at least once includes:

[0034] The sliding window is moved at least once according to a preset movement trajectory, wherein the movement trajectory includes a spiral movement trajectory.

[0035] Optionally, the target area is a rectangular area.

[0036] The present application also provides a feature determination device, the feature determination device comprising:

[0037] A first image acquisition module acquires a first image corresponding to an initial area of the workpiece;

[0038] a target region selection module, selecting a target region in the first image;

[0039] A template feature generation module generates template features using the image of the target area;

[0040] The feature determination module determines whether the template feature exists in at least one second image, wherein the at least one second image is an image located around the initial area and having an overlapping area with the initial area.

[0041] The present application also provides an electronic device, including a memory and a processor, wherein:

[0042] The memory is used to store computer programs;

[0043] The processor is used to execute the computer program to implement the above-mentioned feature determination method.

[0044] The present application also provides a computer-readable storage medium for storing a computer program, wherein the computer program implements the above-mentioned feature determination method when executed by a processor.

[0045] Compared with the existing technology, this application has the following beneficial effects:

[0046] The method disclosed in the present application can obtain a first image corresponding to an initial area of a workpiece, select a target area within the first image, generate a template feature using the image of the target area, obtain at least one second image of an area surrounding the initial area, each area corresponding to the second image has an overlapping area with the initial area, and determine whether the template feature exists in the at least one second image.

[0047] The method disclosed in this application ensures that the area corresponding to the second image is located around the initial area when acquiring the second image by creating an overlapping area between the area corresponding to the second image and the initial area. When part of a feature is located within the first image and another part of the feature is located within the second image, neither the first image nor the second image can fully record the entire feature, which can lead to omissions when determining template features. Compared with the prior art, feature querying using the method provided in this application reduces feature omissions that occur during feature determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 paying any creative labor.

[0049] Figure 1 A flow chart of a feature determination method provided in this application;

[0050] Figure 2 A flow chart of a method for obtaining a second image provided by this application;

[0051] Figure 3 A schematic diagram of an overlapping portion provided for this application;

[0052] Figure 4 Another schematic diagram of overlapping parts provided for this application;

[0053] Figure 5 Another schematic diagram of overlapping parts provided by this application;

[0054] Figure 6 A schematic diagram of another overlapping portion provided in this application;

[0055] Figure 7 A flow chart of another feature determination method provided in this application;

[0056] Figure 8 A schematic diagram of a spiral trajectory provided for this application;

[0057] Figure 9 A schematic structural diagram of a feature determination device provided in this application. DETAILED DESCRIPTION

[0058] As previously described, prior art methods for determining the location of a cutting path require first identifying a feature, using it to represent a specific area and determine the location of the cutting path. After determining the feature, multiple images are acquired and the feature is searched for within the corresponding area. If only a single feature exists within the corresponding area across all images, this feature can be used to determine the cutting path.

[0059] After research, it was found that the current method of determining features requires searching for unique features within the corresponding areas of multiple images. However, when acquiring multiple images, there is no guarantee that the selected images are adjacent, which means that there may be gaps between the images, and these gaps will lead to the omission of some features when determining features. If the selected multiple images are exactly adjacent and there is no overlapping part, if part of the feature is located in the corresponding area of one image, and the remaining part of the feature is located in the other image, that is, the two images each include part of the feature, and the complete feature cannot be obtained in either image. Therefore, when determining the feature in the corresponding area of the two images, the feature cannot be found in the corresponding area of the two images, which leads to feature omission when determining the feature.

[0060] In order to help those skilled in the art better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0061] It is understood that this method can be applied to a processing device, which is a processing device capable of performing data processing, such as a terminal device or server capable of performing data processing. This method can be executed independently by a terminal device or server, or it can be applied to a network scenario where a terminal device and a server communicate, and executed by the terminal device and the server in cooperation. The terminal device can be a computer, a mobile phone, or other device. The server can be understood to be an application server or a web server. In actual deployment, the server can be a standalone server or a clustered server.

[0062] Figure 1 This is a flow chart of a feature determination method provided in this application, the method comprising the following steps:

[0063] S101: Acquire a first image corresponding to an initial area of a workpiece.

[0064] Workpieces, objects operated during the production or processing process, can be wafers, steel plates, or other objects that need to be produced or processed. They should all fall within the scope of protection of this application. Here, taking a semiconductor wafer as an example, there are multiple target units on the semiconductor wafer, each of which contains a chip or other device.

[0065] The processing device can use any area on the workpiece as the initial area. After the processing device selects the initial area, it can obtain a first image corresponding to the initial area through an image acquisition device, such as a camera, a sensor with image acquisition function, or other device capable of acquiring images.

[0066] S102: Select a target area in the first image.

[0067] After obtaining the first image, the processing device can select a target area within the first image. The target area can be any area within the first image. The target area can be of any shape, specifically a rectangle. The size of the target area can be adjustable, where the length can be adjusted alone, the width can be adjusted alone, or both the length and width can be adjusted simultaneously. The target area can be manually selected, determined by the processing device through preset instructions, or obtained through other means, all of which fall within the scope of protection of this application.

[0068] S103: Generate template features using the image of the target area.

[0069] After the processing device obtains the target area, it needs to use the image of the target area to generate a template feature. The processing device can perform feature extraction on the image of the target area to obtain the template feature. For example, if there is a cross-shaped structure in the image of the target area, the cross-shaped structure is extracted to generate a cross-shaped template feature. Or if there is a red area in the image of the target area, the red area is extracted to generate a red template feature that is consistent with the shape of the red area. Of course, any other features can also fall within the scope of protection of this application.

[0070] S104: Determine whether the template feature exists in at least one second image, wherein the at least one second image is an image located around the initial region and having an overlapping area with the initial region.

[0071] After generating the template feature, the processing device acquires at least one second image. The area corresponding to the second image is selected around the initial area. When selecting the second image, the area corresponding to the second image is overlapped with the initial area. A determination is made as to whether the template feature exists within the area corresponding to the second image. If the template feature does not exist, it is proved that the template feature is unique within the area formed by the initial area and the area corresponding to the at least one second image. Because the template feature is unique, the template feature can be used as a position reference for determining the cutting path of the cutting target unit. If multiple template features exist, the template feature cannot be used as a position reference for determining the cutting path of the cutting target unit.

[0072] The above-mentioned feature determination method obtains a first image corresponding to an initial area of the workpiece, selects a target area within the first image, generates template features using the image of the target area, and determines the template features in at least one second image. The area corresponding to the second image obtained in this application overlaps with the initial area, and the overlapping area ensures that the area corresponding to the second image is located around the initial area. In this way, there is no gap between the initial area and the area corresponding to the second image, which reduces the possibility of missing some features.

[0073] During the feature determination process, when a part of a feature is located at the edge of the first image, neither the first image nor the second image can fully record the entire feature. This situation will also lead to omissions when determining the template features. When obtaining the second image, the occurrence of such omissions can be reduced by selecting an appropriate size of the overlapping part. For this purpose, the present application provides a method for obtaining a second image.

[0074] Figure 2 This is a flow chart of a method for obtaining a second image provided by the present application, the method comprising the following steps:

[0075] S201: Determine a sliding window, and use the position of the first image as the initial position of the sliding window.

[0076] The processing device determines a sliding window, which can be obtained by using a device with an image acquisition function. The position of the first image is used as the initial position of the sliding window, and the sliding window is used to acquire the second image.

[0077] S202: Move the sliding window at least once.

[0078] The number of times the sliding window is moved is consistent with the number of second images obtained. The distance and trajectory of movement of the sliding window can be pre-set preset movement trajectory and preset movement distance.

[0079] S203: Using the image in the sliding window after each movement as the second image.

[0080] The image in the sliding window is used as the second image. The area corresponding to any second image and the initial area have an overlapping area, and the size of the overlapping area is determined by the size of the target area.

[0081] The above method can select at least one second image using a sliding window and acquire multiple images through multiple movements, making the acquisition process simpler and faster. The above method can acquire the second image using a preset movement trajectory and a preset movement distance, making the acquired second image more accurate. In the above method, the size of the overlapping area between the area corresponding to any second image and the initial area is determined using the size of the target area. This determination method can make the selected overlapping area more realistic, further reducing feature omissions.

[0082] In the method provided by this application, there is at least one second image. The overlapping portion between the area corresponding to any second image and the initial area can be determined by the following method. Here, a second image is used as an example:

[0083] When determining the overlapping area, a straight line passing through the center of the corresponding area of the second image and the center of the initial area may be used as the first straight line.

[0084] If the first straight line is perpendicular to any side of the initial area, that is, the second image is located in the positive direction of the first image, such as to the left, right, above, or below. The size of the overlapping area in the direction of the line connecting the centers of the first and second images is determined by the size of the target area in that direction.

[0085] For better explanation, here is Figure 3 As shown, Figure 3 The area within the solid rectangular box in is the initial area. Figure 3 The area within the dotted rectangular box in is the area corresponding to the second image. Figure 3 The black rectangle in the figure is the target area.

[0086] Here, we take the example of the area corresponding to the second image being located directly above the initial area. The overlapping area is located between the area corresponding to the second image and the initial area. The size of the overlapping area in the direction of the line connecting the centers of the first image and the second image is w as shown in the figure, and w is determined based on the size y of the target area in this direction.

[0087] If the first straight line is perpendicular to any side of the initial region, that is, the second image is not located in the positive direction of the first image, such as Figure 4 shown.

[0088] Here, the horizontal direction is selected as the first direction, and the vertical direction is selected as the second direction. The first direction and the second direction are perpendicular. Of course, any other two perpendicular directions can also be used. Here, the horizontal direction is selected as the first direction, and the vertical direction is selected as the second direction. The width m of the overlapping area in the first direction is determined by the width x of the target area in the first direction, and the width w of the overlapping area in the second direction is determined by the width y of the target area in the second direction.

[0089] The above methods are all methods for determining the size of the overlapping area between an area corresponding to a second image and an initial area. The overlapping area between any area corresponding to a second image and an initial area can be determined using the above methods.

[0090] The above method for determining the overlapping area takes into account a variety of situations. If the second image is located in the positive direction of the first image, only the size in the direction of the line connecting the centers of the first image and the second image needs to be considered. If the second image is not located in the positive direction of the first image, the first straight line will be divided into two vertical directions, and the width of the overlapping area will be determined separately in the two directions. The consideration is more comprehensive, and the overlapping area can be determined more concisely according to different situations.

[0091] When determining the width of the overlapping area, we can consider the size of the target area in the initial area. If the target area is smaller in the initial area, such as Figure 3 As shown, w = y can be used to determine the overlapping area. If the target area is larger than the initial area, such as Figure 5 As shown, to determine the width of the overlapped area, half the difference between y1 and y can be used as the overlapped area width, i.e., w = y1 / 2 - y / 2. In practical applications, it is sufficient to simply determine the specific values of y and y1 and half the difference between y1 and y, determine the magnitude of these two values, and use the smaller of the two as the overlapped area width.

[0092] In the above method for determining the width of the overlapping area, the smaller of the two sizes is selected. The smaller the size of the overlapping area, the larger the determined range will be. Taking the two sizes into consideration comprehensively can reduce feature omissions while improving the efficiency of feature search.

[0093] In actual applications, there may be multiple second images, and there may be overlapping areas between two adjacent second images, such as Figure 6 As shown, Figure 6 The areas in the two dotted boxes in are areas corresponding to two adjacent second images. There is an overlapping area between the areas corresponding to the two adjacent second images. The method for determining the overlapping area is the same as the above method.

[0094] When determining the second image, the areas corresponding to adjacent second images are allowed to overlap. This method can reduce the situation where features located between two second images are missed.

[0095] Considering the actual application scenarios, Figure 7 Another feature determination method provided in this application comprises the following steps:

[0096] S701: Acquire a first image corresponding to an initial area of a workpiece.

[0097] The workpiece is a semiconductor wafer, on which multiple target units are distributed in an array. Each target unit contains a component, and the range to be determined should not be less than the range of one target unit.

[0098] The image acquisition unit is used to obtain a first image corresponding to an initial area above the workpiece. The initial area is a rectangular area, and the image acquisition unit selected here is a camera.

[0099] S702: Select a target area in the first image.

[0100] Specifically, the processing device selects a rectangular area in the first image as the target area.

[0101] S703: Generate template features using the image of the target area.

[0102] S704: Acquire at least one second image.

[0103] The image acquisition unit is moved successively according to a preset movement trajectory and a preset movement step length, and after each movement, a second image of the surrounding area of the initial area is acquired by the image acquisition unit.

[0104] The image acquisition unit here is the same as the image acquisition unit used in S701 and the parameters of the image acquisition unit are not adjusted. The second image acquired by the same image acquisition unit has the same shape and size as the first image. The preset movement trajectory can be as follows Figure 8 The spiral movement trajectory shown takes the initial area as the starting position, and each movement has a preset moving step length. After each movement, the image acquisition unit is used to capture the workpiece surface area once to obtain a second image. A second image can be obtained each time the movement is performed.

[0105] S705: Determine whether the range covered by the corresponding area of the second image is smaller than the range of one target unit. If so, execute S706; if not, execute S707.

[0106] S706: Acquire a third image.

[0107] If the area covered by the second image is smaller than the range of one target unit, the feature determination range needs to be expanded. Here, a third image can be obtained to ensure that the feature determination range is no smaller than the range of one target unit. The area covered by the third image here also partially overlaps with the area covered by the second image.

[0108] At least one third image is acquired around an area corresponding to the second image, where the area corresponding to the third image overlaps with the area corresponding to the second image.

[0109] S707: Determine template features in the area corresponding to the acquired image.

[0110] If the acquired images are only the first image and the second image, the template features are determined in the areas corresponding to the first image and the second image respectively. If the acquired images also include the third image, the template features also need to be determined in the area corresponding to the third image.

[0111] S708: Acquire at least one fourth image, and determine template features in the fourth image.

[0112] The preset distance can be an integer multiple of the distance between two adjacent components on the workpiece. The area covered by the fourth image can be located in any direction of the initial area covered by the first image, such as directly above, directly below, directly to the left, directly to the right, etc. The components on the surface of the workpiece are distributed in an array, that is, the fourth image can determine whether the template feature exists on other components. If the template feature exists in all the fourth images obtained, it is considered that the template feature can represent the target unit and can further serve as a reference for determining the cutting path position of the target unit.

[0113] The above method, combined with practical applications, takes into account the range of the target unit on the semiconductor wafer and uses the range of the target unit on the semiconductor wafer to make judgments, ensuring that the determined area can cover at least one target unit. In this way, the omission of features in the feature determination process is further reduced. When acquiring the second image, a spiral movement trajectory is selected. This selection can more comprehensively cover the area surrounding the initial area, improving search efficiency. In addition, the adjacent images selected in the above method all have overlapping areas, which minimizes feature omissions.

[0114] This application also provides Figure 8 The structure diagram 900 of a feature determination device is shown, and the device includes the following modules:

[0115] The first image acquisition module 901 acquires a first image corresponding to an initial area of a workpiece.

[0116] The target area selection module 902 selects a target area in the first image.

[0117] The template feature generation module 903 generates template features using the image of the target area.

[0118] The feature determination module 904 determines whether the template feature exists in at least one second image, wherein the at least one second image is an image located around the initial area and having an overlapping area with the initial area.

[0119] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned feature determination method are implemented.

[0120] In practical applications, the computer-readable storage medium may be any combination of one or more computer-readable media, which may be a computer-readable signal medium or a computer-readable storage medium.

[0121] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0122] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0123] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0124] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0125] It should be noted that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components indicated as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0126] The above is merely one specific embodiment of the present application, but the scope of protection of the present 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 the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A feature determination method, characterized in that: The method comprises: Acquiring a first image corresponding to an initial area of the workpiece; selecting a target area in the first image; generating template features using the image of the target area; determining whether the template feature exists in at least one second image, wherein the at least one second image is an image located around the initial region and having an overlapping region with the initial region; If the template feature does not exist in the second image, use the template feature as a position reference for determining the cutting path of the cutting target unit; if multiple template features exist in the second image, determine that the template feature cannot be used as a position reference for determining the cutting path of the cutting target unit; The method further comprises: There are a plurality of target units distributed in an array on the workpiece; The area of a region formed by the initial region and the region corresponding to the second image is not less than the area of the target unit.

2. The method according to claim 1, characterized in that After generating template features using the image of the target area, the method further includes: The overlapping area is determined, wherein a size of the overlapping area is determined using a size of the target area.

3. The method according to claim 2, characterized in that Determining the overlapping area includes: Using a straight line passing through the center of the second image and the center of the initial area as a first straight line; In a case where the first straight line is perpendicular to any side of the initial area, the width of the overlapping area on the first straight line is determined by using the width of the target area on the first straight line; When the first straight line is not perpendicular to any side of the initial area, the width of the overlapping area in the target direction is determined using the width of the target area in the target direction, and the target direction includes a first direction parallel to the first side of the initial area and a second direction parallel to the second side of the initial area, and the first direction is perpendicular to the second direction.

4. The method according to claim 3, characterized in that The determining the width of the overlapping area in the target direction by using the width of the target area in the target direction includes: Taking the width of the target area in the target direction as a first size; half of the difference between the width of the first image in the target direction and the width of the target area in the target direction as the second size; The width of the overlapping area in the target direction is the minimum value between the first size and the second size.

5. The method according to claim 1, wherein Adjacent second images have overlapping areas.

6. The method according to claim 1, characterized in that The at least one second image is obtained by: Determine a sliding window, and use the position of the first image as the initial position of the sliding window; moving the sliding window at least once; The image within the sliding window after each movement is used as the second image.

7. The method according to claim 1, characterized in that The method further comprises: Acquire at least one third image around an area corresponding to the second image; The template feature is determined in the at least one third image, and an area corresponding to the third image and an area corresponding to the second image have an overlapping area.

8. The method according to claim 1, characterized in that The method further comprises: At least one fourth image is acquired, wherein a distance between a center of an area corresponding to the fourth image and a center of the initial area is greater than a preset distance.

9. The method according to claim 6, characterized in that The moving the sliding window at least once comprises: The sliding window is moved at least once according to a preset movement trajectory, wherein the movement trajectory includes a spiral movement trajectory.

10. The method according to claim 1, characterized in that The target area is a rectangular area.

11. A feature determination device, characterized in that: The device comprises: A first image acquisition module acquires a first image corresponding to an initial area of the workpiece; a target region selection module, selecting a target region in the first image; A template feature generation module generates template features using the image of the target area; A feature determination module determines whether the template feature exists in at least one second image, wherein the at least one second image is an image located around the initial area and overlapping with the initial area; if the template feature does not exist in the second image, the template feature is used as a position reference for determining the cutting path of the cutting target unit; if multiple template features exist in the second image, it is determined that the template feature cannot be used as a position reference for determining the cutting path of the cutting target unit; multiple array-distributed target units exist on the workpiece; the area of the area composed of the initial area and the area corresponding to the second image is not less than the area of the target unit.

12. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store computer programs; The processor is configured to execute the computer program to implement the feature determination method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that Used to store a computer program, wherein when the computer program is executed by a processor, it implements the feature determination method according to any one of claims 1 to 10.

Images