A detection method, system, terminal device and storage medium for a positioning groove

Abstract

A method, system, terminal device, and storage medium for detecting positioning grooves. The detection method includes: obtaining at least one first detection image corresponding to a first preset area on the front of a test piece; identifying a cutting path in the first detection image based on the first detection image; determining four first detection areas of the test piece based on the cutting path; obtaining a second detection image of the four first detection areas of the test piece; determining a first detection area having positioning grooves based on the second detection image; and calculating the offset angle between the actual position and theoretical position of the positioning groove relative to the test piece based on the angle information of the target detection area. The direction of the cutting path is identified through the image, and the first detection area where the positioning groove exists in the test piece is determined. The first detection area where the positioning groove is located is determined. By calculating the offset angle of the positioning groove, the positioning groove is positioned and the offset angle is corrected in a timely manner when the test piece is subsequently positioned, thereby improving production efficiency.

Description

Technical Field

[0001] The present invention relates to the field of image detection technology, and in particular to a positioning groove detection method, system, terminal equipment and storage medium. Background Art

[0002] In existing semiconductor device manufacturing processes, such as the TSV process, wafers can experience varying degrees of edge chipping. The edges of wafers are provided with positioning grooves (also known as notches or V-grooves) for positioning. This edge chipping can lead to errors in notch recognition.

[0003] In most processes, the orientation of the wafer needs to be determined based on the positioning grooves. The aforementioned edge collapse problem will lead to incorrect positioning groove identification, causing the calibration equipment to fail to work properly and affecting the overall process flow. Summary of the Invention

[0004] The main technical problem solved by the present invention is the difficulty in identifying the positioning grooves used for positioning due to chipped edges of the wafer.

[0005] According to the first aspect, an embodiment provides a method for detecting a positioning groove, comprising:

[0006] Acquire at least one first detection image corresponding to a first preset area on the front side of the object to be tested;

[0007] According to the first detection image, a cutting line in the first detection image is identified, wherein a plurality of cutting lines are provided on the front surface of the test object, the cutting lines including at least one cutting line arranged along a first direction and at least one cutting line arranged along a second direction, the first direction being perpendicular to the second direction;

[0008] Four first inspection areas are determined for the piece to be tested based on the cutting paths, two of which are symmetrical about the center of the piece to be tested along a first direction, and the other two are symmetrical about the center of the piece to be tested along a second direction; the first inspection areas cover the theoretical area where the positioning groove exists on the piece to be tested;

[0009] Acquire second detection images of four first detection areas of the object to be tested;

[0010] Determine a first detection area having a positioning groove according to the second detection image; define the first detection area having the positioning groove as a target detection area;

[0011] The offset angle between the actual position and the theoretical position of the positioning slot relative to the object to be tested is calculated based on the angle information of the target detection area.

[0012] According to the second aspect, an embodiment provides a positioning groove detection system,

[0013] An image acquisition module is used to acquire an image of the front side of the test piece;

[0014] A processing module is configured to obtain, through an image acquisition module, at least one first detection image corresponding to a first preset area on the front surface of the object to be tested; identify, based on the first detection image, a cutting path in the first detection image; determine, based on the cutting path, four first detection areas of the object to be tested; obtain second detection images of the four first detection areas of the object to be tested; determine, based on the second detection images, a first detection area having a positioning groove; and calculate, based on angle information of the target detection area, an offset angle between an actual position and a theoretical position of the positioning groove relative to the object to be tested;

[0015] Among them, a plurality of cutting lanes are provided on the front of the piece to be tested, and the cutting lanes include at least one cutting lane arranged along a first direction and at least one cutting lane arranged along a second direction, and the first direction is perpendicular to the second direction; two first detection areas are symmetrical about the center of the piece to be tested along the first direction, and the other two first detection areas are symmetrical about the center of the piece to be tested along the second direction; the first detection area covers the theoretical existence area of the positioning groove on the piece to be tested; the first detection area with the positioning groove is defined as the target detection area.

[0016] According to a third aspect, an embodiment provides a terminal device, including:

[0017] Memory, used to store programs;

[0018] A processor is configured to implement the method described in the first aspect by executing a program stored in a memory.

[0019] According to a fourth aspect, an embodiment provides a computer-readable storage medium, on which a program is stored. The program can be executed by a processor to implement the method described in the first aspect.

[0020] According to the positioning groove detection method, system, terminal equipment and storage medium of the above-mentioned embodiment, the direction of the cutting path is identified by image recognition, and the first detection area where the positioning groove exists in the workpiece to be tested is determined. By acquiring an image of the first detection area, the first detection area where the positioning groove is located can be determined. By calculating the offset angle of the positioning groove, when the workpiece to be tested needs to be positioned, the positioning groove can be positioned and the offset angle can be corrected in time to improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic structural diagram of a positioning groove detection system provided in an embodiment;

[0022] Figure 2 A schematic structural diagram of a device under test provided in an embodiment;

[0023] Figure 3 A schematic structural diagram of a positioning groove of a test piece provided in an embodiment;

[0024] Figure 4 A flowchart of a method for detecting a positioning groove provided in an embodiment;

[0025] Figure 5 A schematic diagram of a first detection area provided in an embodiment;

[0026] Figure 6 A schematic diagram showing the effects of a first image obtained before and after adjusting the exposure value provided by an embodiment;

[0027] Figure 7 A schematic diagram of a second detection area provided in one embodiment;

[0028] Figure 8 A schematic diagram of position reference points of a positioning groove provided in an embodiment;

[0029] Figure 9 A schematic diagram of another second detection area provided in an embodiment.

[0030] Figure numerals: 1-image acquisition module; 10-part to be tested; 11-cutting path; 12-positioning groove; 121-arc; 122-edge line; 123-position reference point; 2-calibration device; 3-motion mechanism; 4-light source system; 5-processing module; A-first preset area; B-first detection area; X-first preset reference line; Y-second preset reference line. DETAILED DESCRIPTION

[0031] The present invention will be further described in detail below by means of specific embodiments in conjunction with the accompanying drawings. Similar elements in different embodiments are numbered with associated similar elements. In the following embodiments, many detailed descriptions are provided to enable the present application to be better understood. However, those skilled in the art will readily appreciate that some of the features may be omitted in different circumstances, or may be replaced by other elements, materials, or methods. In some cases, some operations related to the present application are not shown or described in the specification. This is to avoid the core portion of the present application being overwhelmed by excessive descriptions, and for those skilled in the art, it is not necessary to describe these related operations in detail. They will fully understand the related operations based on the description in the specification and the general technical knowledge in the art.

[0032] In addition, the features, operations, or characteristics described in the specification may be combined in any appropriate manner to form various embodiments. Furthermore, the steps or actions in the method description may be reordered or adjusted in a manner readily apparent to those skilled in the art. Therefore, the various sequences in the specification and drawings are provided solely for the purpose of clearly describing a particular embodiment and are not intended to be mandatory, unless otherwise specified.

[0033] The serial numbers assigned to components herein, such as "first," "second," etc., are used solely to distinguish the objects being described and do not convey any sequential or technical meaning. References to "connection" and "coupling" herein, unless otherwise specified, include both direct and indirect connections (couplings).

[0034] In product processing, a circular material (referred to as a test piece in this application) is required as a processing substrate. In some single crystal materials or metal materials with stress, it is necessary to mark the edge with a positioning groove for direction positioning during processing. For example, in semiconductor processing, the wafer needs a positioning groove to locate the direction. The positioning groove is generally called a notch groove or a positioning groove, which is used to mark the crystal direction. Corresponding to small-sized wafers, a positioning edge is generally used, which is generally called a flat edge.

[0035] Since wafers need to be positioned multiple times during the semiconductor manufacturing process, wafers using positioning grooves may experience edge collapse during some processes or transportation. The edge collapse interferes with the identification of the positioning grooves. When the positioning grooves are incorrectly identified, it will seriously affect production efficiency and even lead to product processing errors.

[0036] In an embodiment of the present invention, by utilizing the cutting path as a basis, after the cutting path is identified through image, the positions of the four first detection areas where the positioning groove may exist are determined according to the direction of the cutting path, and then the image recognition of the positioning groove and the calculation of the offset angle are performed on the first detection area, thereby improving the subsequent wafer positioning accuracy and efficiency and improving the overall production efficiency.

[0037] Example 1:

[0038] Please refer to Figure 1 This embodiment provides a positioning groove detection system, which may include an image acquisition module 1, a calibration device 2, a motion mechanism 3, a light source system 4 and a processing module 5.

[0039] The image acquisition module 1 is used to acquire an image of the front surface of the test piece 10. The image acquisition module 1 may include a detector (such as a CCD camera) and a lens assembly (such as a low-power lens with a large field of view).

[0040] The motion mechanism 3 is used to drive the image acquisition module 1 to move to a preset position. The motion mechanism 3 may be an XYZ three-axis motion mechanism 3 .

[0041] The calibration device 2 is used to rotate the test piece 10 to determine the center of the test piece 10. The calibration device 2 may have its own imaging system, or may be an imaging system that multiplexes the image acquisition module 1.

[0042] For example, when the device under test 10 is a wafer, the center of the wafer can be determined using the alignment device 2 of the Equipment Front End Module (EFEM). Conventional alignment methods primarily utilize the alignment device 2 to rotate the wafer, combined with image recognition and analysis to determine the wafer center. Therefore, the EFEM alignment device 2 includes a corresponding rotation system and imaging system.

[0043] The light source system 4 is used to provide illumination for the test surface of the test piece 10, and has at least a vertical incident light source and an oblique incident light source. At this time, the light source system 4 has at least three light source conditions, namely vertical incident illumination, oblique incident illumination, and vertical incident illumination + oblique incident illumination.

[0044] The processing module 5 is used to control the operation of various modules, mechanisms, subsystems and devices of the detection system, and is also used to perform image processing analysis and calculation. Specifically, it can be used to control the movement mechanism to drive the image acquisition module 1 to move to a preset area; control the image acquisition module 1 to acquire an image of the wafer; control the calibration device 2 to calibrate the piece to be tested 10 and obtain the center of the piece to be tested 10; control the light source system 4 to form light on the front of the piece to be tested 10 according to preset light source conditions.

[0045] In this application, if Figure 2 As shown, a plurality of cutting lanes 11 are provided on the front of the DUT 10. The cutting lanes 11 include at least one cutting lane 11 arranged along a first direction and at least one cutting lane 11 arranged along a second direction. The first direction is perpendicular to the second direction. The area outside the cutting lanes 11 is defined as the off-street area. The off-street area includes the rectangular intra-chip area formed by the intersection of the cutting lanes 11. Each intra-chip area corresponds to a chip. Figure 3 As shown, the positioning groove 12 is generally shaped like a V-groove, and the V-groove has a side line 122 and an arc line 121. In theory, the center line of the positioning groove 12 is perpendicular or parallel to the cutting line, and the center line of the positioning groove 12 passes through the center of the wafer. However, in the process of processing the V-groove and the cutting path 11 on the wafer, there are processing precision and errors, which lead to an offset angle after the V-groove is processed; due to the existence of the offset angle, the positioning efficiency of the subsequent process will be low or even the positioning will fail, leading to other production and processing problems, such as the misalignment of the slicing knife and the cutting path 11 in the singulation process.

[0046] The following describes the specific process of the detection system detection method. Figure 4 As shown, the detection method may include the following steps:

[0047] Step 1: Obtain the center of the test piece 10.

[0048] Specifically, the DUT 10 is placed on the calibration device 2, and the processing module 5 controls the calibration device 2 to perform center calibration on the DUT 10 to obtain the center of the DUT 10. When the DUT 10 is a wafer, an EFFM calibration device can be used as the calibration device 2 of this detection system.

[0049] Step 2: Acquire at least one first detection image corresponding to the first preset area A on the front surface of the device under test 10 .

[0050] Specifically, if Figure 5 As shown, the processing module 5 controls the motion mechanism 3 to drive the image acquisition module 1 to a position corresponding to the first preset area A, and captures the first preset area A. The center of the first preset area A can be the center of the test piece 10. The aspect ratio of the first preset area A is larger than the spacing between the cutting lanes 11, which ensures that the first detection image contains images corresponding to at least one cutting lane in the first direction and at least one cutting lane in the second direction.

[0051] In practical applications, to improve the imaging quality of the first detection image, the hardware exposure value of the image acquisition module 1 can be adjusted to make the first detection image clearer and distinguish the dicing lane 11 from the area outside the lane. This is also because the color of the wafer surface will present different surface conditions due to differences in the device structure on the wafer and the surface coating.

[0052] It should be noted that in this application, it is assumed that the images captured by the image acquisition module 1 are all grayscale images, or single-channel images, or RGB images that have been black-and-white processed. The clarity of the image can refer to the difference between the average grayscale value of the cutting path area and the average grayscale value of the area outside the path, or the variance of the difference between the pixel values of the cutting path area and the adjacent area outside the cutting path area. It can also be understood as the brightness difference between the cutting path area and the area outside the path.

[0053] Then, before acquiring the first detection image, the detection method may further include:

[0054] Step 201 : Acquire a first image of the front surface of the device under test 10 and determine the clarity of the first image; and adjust the exposure value of the image acquisition device accordingly according to the clarity of the first image.

[0055] Specifically, for different wafers, the processing module 5 controls the image acquisition module 1 to first acquire a first image of the wafer surface. Based on the clarity of the first image, different exposure values are selected to achieve an automatic exposure effect. A preset algorithm can be used for identification, calculating the grayscale value variance of pixels in the out-of-channel area, comparing the calculated variance with a preset standard variance, and adjusting the exposure value accordingly based on the residual of the comparison. The specific parameters for adjusting the exposure value are set based on the specific detection system.

[0056] like Figure 6 As shown, Figure 6 A is the first image without exposure adjustment, Figure 6 B is based on Figure 6 A is the first image after the exposure value is adjusted. It can be seen that Figure 6 B can better distinguish the cutting track 11 from the area outside the track. The grayscale value variance of the pixels in the area outside the track is smaller, and the average grayscale value of the pixels in the area outside the track is closer to 255 (assuming 255 is the maximum grayscale value).

[0057] Step 3: According to the first detection image, identify the cutting path 11 in the first detection image.

[0058] Specifically, the cutting lane 11 in the first detection image may be identified based on a preset second grayscale threshold, a second grayscale difference, or a second grayscale step value. Alternatively, the first detection image may be subjected to binarization processing, curve processing, or contrast processing to more clearly distinguish the cutting lane 11 from areas outside the lane.

[0059] In practical applications, the motion mechanism 3 is often an XYZ three-axis motion mechanism 3. The imaging range of the image acquisition module 1 is rectangular after imaging, with the length and width of the rectangle corresponding to the XY directions of the motion mechanism 3. When imaging the first preset area A, since the cutting path 11 of the workpiece 10 is often not parallel to the XY axes, it is necessary to identify the cutting path 11. This involves determining the angle of the cutting path 11 in the imaging system of the image acquisition module 1, or determining the angle of the cutting path 11 in the coordinate system of the motion mechanism 3.

[0060] In practical applications, after identifying the cutting line 11 in the first detection image, the detection method may further include:

[0061] Step 301: Determine the current angle of the cutting path 11. In this step, after the processing module 5 identifies the cutting path 11, it calculates the angle between the first direction (or second direction) of the cutting path 11 and the first preset reference line X to determine the current angle of the cutting path 11. As shown above, the determined direction can be the direction of the camera coordinate system of the image acquisition module 1 or the movement direction of the motion mechanism 3.

[0062] Step 302: Figure 7 As shown, based on the current angle of the scribe line 11, the device under test 10 is rotated so that the first direction is parallel to the first preset reference line X and the second direction is parallel to the second preset reference line Y. The first preset reference line X and the second preset reference line Y are defined as being perpendicular and both passing through the center of the device under test 10. The processing module 5 controls the calibration device 2 to rotate the wafer so that the direction of the scribe line 11 is perpendicular or parallel to the first preset reference line X and the second preset reference line Y.

[0063] In order to simplify the search and identification efficiency of the subsequent positioning groove 12, the direction of the cutting path 11 needs to be rotated to the right. Of course, steps 301 and 302 are not necessary. The processing module 5 can detect the first detection image, such as Figure 9 As shown, a first preset reference line X and a second preset reference line Y can also be constructed to determine the four first detection areas B. However, since the cutting path 11 is not rotated, the direction of the cutting path 11 is not aligned with the length and width of the shooting area of the image acquisition module 1. This results in a misalignment between the first detection areas B and the cutting path 11. Obtaining the first detection image requires the processing module 5 to use a more complex algorithm. Furthermore, using the XYZ-axis motion mechanism 3 makes it impossible to align the length and width of the image acquisition module 1 with the cutting path 11. In this case, the algorithm required to determine the first detection area B is also more complex.

[0064] Therefore, adopting step 301 and step 302 can simplify the subsequent steps such as the shooting positioning of the image acquisition module 1 and the algorithm of processing the first detection image by the processing module 5.

[0065] Step 4: If Figure 7 As shown, four first detection areas B of the test piece 10 are determined according to the cutting path 11, two of the first detection areas B are symmetrical about the center of the test piece 10 along the first direction, and the other two first detection areas B are symmetrical about the center of the test piece 10 along the second direction; the first detection areas B cover the theoretical existence area of the positioning groove 12 on the test piece 10.

[0066] In the actual production process, even if there is a deviation between the positioning groove 12 and the cutting path 11, there is a smaller deviation range based on the processing accuracy. Therefore, the theoretical position of the positioning groove 12 in the workpiece 10 can be determined based on the processing accuracy. Figure 7As shown, after the wafer is rotated in step 302, the V-groove can only appear at the edges corresponding to the four angles of 0°, 90°, 180°, and 270° (i.e., directly above, directly right, directly below, and directly left in the figure). Therefore, using the larger first inspection area B for image acquisition will inevitably capture the positioning groove 12. Reasonable control of the size of the first inspection area may reduce the impact of misjudgment caused by edge chipping defects.

[0067] Step 5: Acquire the second detection images of the four first detection areas B of the device under test 10 .

[0068] Specifically, the processing module 5 can control the image acquisition module 1 to sequentially acquire images of the four first detection areas B to obtain four second detection images. Specifically, this can be done by aligning the image acquisition module 1 with one of the first detection areas B and rotating the test piece 90° each time. Alternatively, the motion mechanism 3 can be used to drive the image acquisition module 1 to positions corresponding to the four first detection areas B. Alternatively, after acquiring a complete image of the test piece 10, the image is cropped to obtain the four second detection images corresponding to the four first detection areas B. This is determined by the imaging resolution and pixel size of the image acquisition module 1.

[0069] Step 6: Determine the first detection area B having the positioning groove 12 according to the second detection image; define the first detection area B having the positioning groove 12 as the target detection area.

[0070] Specifically, the processing module 5 can use algorithms such as template matching to match the four second detection images using a preset template to determine the first detection area B having the positioning groove 12. Figure 7 Alternatively, the target detection area can be determined by presenting four second detection images on a display and manually judging by an operator and then accepting the operator's confirmation information.

[0071] In practical applications, after determining the first detection area B having the positioning groove 12, the detection method may further include:

[0072] Step 601: Acquire a plurality of second images corresponding to the target detection area under a plurality of light source conditions; the light source conditions include at least one of a vertically incident light source and an obliquely incident light source.

[0073] Step 602: Determine the light source condition that matches the current environment based on the multiple second images.

[0074] Step 603: Reacquire a second detection image corresponding to the target detection area using the matching light source condition.

[0075] Specifically, different lighting conditions affect the imaging quality of the second detection image. To facilitate subsequent identification of the positioning groove 12 and improve the accuracy of the calculation results, after determining the target detection area, the lighting conditions can be switched according to the imaging quality of the current second detection image. The current environment refers to the imaging environment of the detection system.

[0076] Due to the inconsistencies in wafer processing techniques, the camera may capture better images when the wafer is illuminated by a vertical incident light source, or worse when it is illuminated by a vertical incident light source, necessitating the use of an oblique incident light source. The specific light source to use can be determined by comparing images captured under various light sources.

[0077] After determining the light source conditions, the target detection area may be re-photographed; or, the imaging range of the second image is the target detection area, and according to the judgment structure of step 602, the second image matching the light source conditions is directly selected from the multiple second images.

[0078] Image quality can be judged based on the variance of the grayscale values of pixels in the out-of-channel area. Smaller variances and larger grayscale values indicate better image quality. Of course, other available criteria can also be used to determine the light source conditions that match the current environment.

[0079] Of course, steps 601 to 603 can also be performed before step 5. Before acquiring the second detection image, the light source conditions corresponding to the current environment are first determined. In this case, it is not necessary to acquire an image of the target detection area, but rather an image is acquired at any location (preferably one of the first detection areas B).

[0080] Simply executing steps 601 to 603 after step 6 can better ensure the imaging quality of the target detection area and facilitate the subsequent identification of the positioning groove 12.

[0081] Step 7: Calculate the offset angle between the actual position and the theoretical position of the positioning groove 12 relative to the device under test 10 based on the angle information of the target detection area.

[0082] The angle information of the target detection area refers to the angle of the center of the first detection area B relative to the center of the wafer in the above step 4, which can be 0°, 90°, 180° and 270°.

[0083] In practical applications, calculating the offset angle between the actual position and the theoretical position of the positioning slot 12 relative to the test piece 10 may include the following steps:

[0084] Step 701: Determine the position of the position reference point 123 of the positioning groove 12 based on the second detection image; calculate the vertical deviation distance between the position reference point 123 of the positioning groove 12 and the first preset reference line X or the second preset reference line Y, and the position reference point 123 of the positioning groove 12 is located at the midpoint of the arc 121 of the positioning groove 12.

[0085] Specifically, the edge line 122 and the arc 121 of the positioning groove 12 may be identified based on a preset first grayscale threshold, a first grayscale difference, or a first grayscale step value, and the position of the position reference point 123 of the positioning groove 12 may be obtained. For example, a template matching algorithm may be used to match the arc 121 and then calculate the midpoint of the arc 121.

[0086] Step 702: Calculate the offset angle between the actual position and the theoretical position of the positioning groove 12 relative to the test piece 10 based on the vertical deviation distance and the radius of the test piece 10.

[0087] Specifically, according to the angle information of the target detection area, the specific direction of the position reference point 123 of the positioning groove 12 can be obtained, such as Figure 7 and Figure 8 As shown, when the target detection area is the first detection area B directly below, the position reference point 123 of the positioning groove 12 theoretically coincides with the first preset reference line X. At this time, the vertical deviation distance between the position reference point 123 of the positioning groove 12 and the first preset reference line X, combined with the radius of the wafer, can be used to obtain the angle of the current position reference point 123 relative to the center of the wafer, thereby obtaining the offset angle between the actual position and theoretical position of the positioning groove 12 relative to the wafer.

[0088] Of course, the position reference point 123 of the positioning groove 12 can also be preset at other positions, and can be set specifically according to actual conditions. Setting it as the midpoint of the arc 121 is to correspond to the set position and shape of the V-groove on the wafer, which makes calculation easier. Combining the radius of the wafer also facilitates the calculation of the offset angle.

[0089] In summary, the present application uses the positioning groove 12 detection method and detection system to obtain the positioning offset angle of the wafer, so as to facilitate the positioning and calibration of subsequent processes and improve production efficiency.

[0090] Of course, other types of DUTs 10, specifically DUTs 10 having positioning grooves 12 and cutting lanes 11, can also apply the detection method and detection system provided in the embodiments of the present application. The embodiments of the present application are described using wafers as an example, but do not limit the concept of the present application.

[0091] Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments can be implemented by hardware or by computer program. When all or part of the functions in the above embodiments are implemented by computer program, the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, disk, optical disk, hard disk, etc., and the program is executed by a computer to implement the above functions. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above functions can be implemented. In addition, when all or part of the functions in the above embodiments are implemented by computer program, the program can also be stored in a storage medium such as a server, another computer, disk, optical disk, flash disk or mobile hard disk, and saved in the memory of the local device by downloading or copying, or the system of the local device is updated. When the program in the memory is executed by the processor, all or part of the functions in the above embodiments can be implemented.

[0092] The above examples are used to illustrate the present invention, which are only used to help understand the present invention and are not intended to limit the present invention. Those skilled in the art can make several simple deductions, modifications or substitutions based on the concept of the present invention.

Claims

1. A method for detecting a positioning groove, characterized in that: include: Acquiring at least one first detection image corresponding to a first preset area (A) on the front side of the object to be tested (10); According to the first detection image, a cutting path (11) in the first detection image is identified, wherein a plurality of cutting paths (11) are provided on the front surface of the test piece (10), and the cutting paths (11) include at least one cutting path arranged along a first direction and at least one cutting path arranged along a second direction, wherein the first direction is perpendicular to the second direction; Determine the current angle of the cutting path (11), and according to the current angle, rotate the workpiece (10) to make the first direction parallel to a first preset reference line (X), and the second direction parallel to a second preset reference line (Y), and define the first preset reference line (X) and the second preset reference line (Y) to be perpendicular and both pass through the center of the workpiece (10); Four first detection areas (B) of the test piece (10) are determined according to the cutting path (11), two of the first detection areas (B) are symmetrical about the center of the test piece (10) along the first direction, and the other two first detection areas (B) are symmetrical about the center of the test piece (10) along the second direction; the first detection areas (B) cover the theoretical existence area of the positioning groove (12) on the test piece (10); Acquiring second detection images of four first detection areas (B) of the object to be tested (10); Determining the first detection area (B) having the positioning groove (12) according to the second detection image; defining the first detection area (B) having the positioning groove (12) as a target detection area; Determine the position of the position reference point (123) of the positioning groove (12) based on the second detection image; calculate the vertical deviation distance between the position reference point (123) of the positioning groove (12) and the first preset reference line (X) or the second preset reference line (Y), the distance between the position reference point (123) of the positioning groove (12) and the midpoint of the arc (121) of the positioning groove (12); The offset angle between the actual position and the theoretical position of the positioning groove (12) relative to the test piece (10) is calculated based on the vertical deviation distance and the radius of the test piece (10).

2. The detection method according to claim 1, wherein Determining a position reference point (123) of the positioning groove (12) comprises: According to a preset first grayscale threshold, a first grayscale difference or a first grayscale step value, the edge line (122) and the arc line (121) of the positioning groove (12) are identified to obtain the position of the position reference point (123) of the positioning groove (12).

3. The detection method according to claim 1, wherein Before acquiring the first detection image, the detection method further includes: Acquiring a first image of the front side of the test piece (10) and determining the clarity of the first image; According to the clarity of the first image, the exposure value of the image acquisition device is correspondingly adjusted, and the image acquisition device is used to acquire an image of the front side of the test piece (10).

4. The detection method according to claim 1, wherein Identifying a cutting path (11) in the first detection image, comprising: According to a preset second grayscale threshold, a second grayscale difference value or a second grayscale step value, a cutting path (11) in the first detection image is identified.

5. The detection method according to claim 1, wherein After determining the first detection area (B) having the positioning groove (12), the detection method further comprises: Acquiring a plurality of second images corresponding to the first detection area (B) having the positioning groove (12) under a plurality of light source conditions; the light source conditions include at least one of a vertically incident light source and an obliquely incident light source; determining, based on the plurality of second images, a light source condition matching the current environment; The second detection image corresponding to the first detection area (B) having the positioning groove (12) is reacquired using matching light source conditions.

6. A positioning groove detection system, characterized in that: An image acquisition module (1) is used to acquire an image of the front surface of the object to be tested (10); A processing module (5) for: Acquiring at least one first detection image corresponding to a first preset area (A) on the front side of the object to be tested (10) through the image acquisition module (1); According to the first detection image, a cutting path (11) in the first detection image is identified; wherein a plurality of cutting paths (11) are provided on the front surface of the test piece (10), the cutting paths (11) including at least one cutting path (11) arranged along a first direction and at least one cutting path (11) arranged along a second direction, the first direction being perpendicular to the second direction; Determine the current angle of the cutting path (11), and rotate the test piece (10) according to the current angle so that the first direction is parallel to a first preset reference line (X), and the second direction is parallel to a second preset reference line (Y); define the first preset reference line (X) and the second preset reference line (Y) to be perpendicular and both pass through the center of the test piece (10); Four first detection areas (B) of the test piece (10) are determined according to the cutting path (11); wherein two of the first detection areas (B) are symmetrical about the center of the test piece (10) along the first direction, and the other two of the first detection areas (B) are symmetrical about the center of the test piece (10) along the second direction; and the first detection areas (B) cover the theoretical existence area of the positioning groove (12) on the test piece (10); Acquiring second detection images of four first detection areas (B) of the object to be tested (10); Determining the first detection area (B) having the positioning groove (12) according to the second detection image; defining the first detection area (B) having the positioning groove (12) as a target detection area; Determine the position of the position reference point (123) of the positioning groove (12) based on the second detection image; calculate the vertical deviation distance between the position reference point (123) of the positioning groove (12) and the first preset reference line (X) or the second preset reference line (Y); the position reference point (123) of the positioning groove (12) is located at the midpoint of the arc (121) of the positioning groove (12); The offset angle between the actual position and the theoretical position of the positioning groove (12) relative to the test piece (10) is calculated based on the vertical deviation distance and the radius of the test piece (10).

7. A terminal device, characterized in that: include: Memory, used to store programs; A processor, configured to implement the method according to any one of claims 1 to 5 by executing the program stored in the memory.

8. A computer-readable storage medium, characterized in that The medium stores a program, which can be executed by a processor to implement the method according to any one of claims 1 to 5.

Images