A positioning method and positioning device for chip unsealing

Abstract

The present invention is applicable to the technical field of image recognition, and provides a positioning method and positioning device for chip unsealing, wherein the positioning method for chip unsealing includes: collecting an image of a chip to be unsealed on a storage platform; according to a preset pixel value range corresponding to the storage platform, providing multiple pixels to be identified in the image of the chip to be unsealed; based on the number of other pixels to be identified and the number of background pixels around each current pixel to be identified, screening the initial diagonal points; according to the distribution characteristics of the diagonal points, screening the target diagonal points from the multiple initial diagonal points; according to the target diagonal points, calibrating the opening starting point positioning; the opening starting point positioning is used to control the laser module or plasma module to move to this point, and perform the chip unsealing operation based on the preset trajectory. The present invention also discloses a positioning device, terminal equipment and computer-readable storage medium for chip unsealing, which improves the accuracy of the chip unsealing starting point positioning, thereby improving the quality of chip unsealing.

Description

Technical Field

[0001] The invention belongs to the technical field of image recognition, and in particular relates to a positioning method and a positioning device for chip unsealing. Background Art

[0002] With the rapid development of mobile communications, the market for products such as smartphones and personal IoT terminals has become very mature. Both smartphones and IoT terminals are mainly composed of chips. Chips refer to silicon wafers containing integrated circuits, also known as microcircuits, microchips, and integrated circuits. Chips are very small and are the most important part of computers or other electronic devices, assuming core functions such as computing and storage. For large-scale production and manufacturing, how to improve the detection efficiency and accuracy of chips after production is of great significance.

[0003] Since the chip will be disturbed by various uncertain factors during the production process, some of the packaged chips cannot meet the use standards. Since these chips cannot realize specific functions in terms of electricity or have problems in structure, the produced chips must be tested and packaged leakage detection to remove chips that cannot meet the use standards. However, chips that cannot meet the use standards not only have electrical abnormalities, but also structural mismatches. Therefore, for abnormal packaged chips with structural defects, it is necessary to unseal, parse, and analyze them to find the crux of the problem, so as to propose corresponding improvement measures, prevent the same problem from occurring, and thus improve the overall quality. Unsealing technology has become the most indispensable analysis method in the process of failure analysis (FMEA) of semiconductor electronic components.

[0004] Unsealing technology refers to the use of chemical or physical methods to thin the packaged chip until the surface glass layer cracks, revealing the internal structure of the chip, thereby achieving the purpose of failure analysis. Unsealing technology requires the use of mechanical thinning or laser thinning methods according to the internal structure of the chip to gradually remove the surface structure of the packaged chip. During the unsealing process, since the positioning method of the position to be unsealed uses an image recognition method, it is necessary to use industrial automatic optical inspection technology to obtain images. However, in traditional technologies, the positioning accuracy of the position to be unsealed is low, and the cross-section after unsealing usually has deformation or cracks.

[0005] Therefore, how to improve the positioning accuracy of the to-be-unsealed position during the chip unsealing process is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0006] In view of this, an embodiment of the present invention provides a positioning method and a positioning device for chip unsealing to solve the technical problem of how to improve the positioning accuracy of the to-be-unsealed position during the chip unsealing process.

[0007] A first aspect of an embodiment of the present invention provides a positioning method for chip unsealing, the positioning method for chip unsealing comprising:

[0008] Collect images of chips to be unpacked on the storage table;

[0009] According to the preset pixel value range corresponding to the storage platform, background pixel points corresponding to the preset pixel value range are removed from the image of the chip to be opened to obtain a plurality of pixel points to be identified;

[0010] According to the number of other pixels to be identified and the number of background pixels around each current pixel to be identified, the initial diagonal points are selected; wherein the diagonal points refer to the four vertices of the rectangular chip;

[0011] Selecting a target diagonal point from a plurality of the initial diagonal points according to the distribution characteristics of the initial diagonal points;

[0012] According to the target diagonal point, the unsealing starting point positioning is calibrated; the unsealing starting point positioning is used to control the laser module or plasma module to move to this point, and perform the chip unsealing operation based on a preset trajectory.

[0013] Furthermore, the step of screening the initial diagonal points according to the number of other pixels to be identified and the number of background pixels around each current pixel to be identified includes:

[0014] Extracting a plurality of adjacent pixel points around the current pixel point to be identified to form a pixel region; wherein the current pixel point to be identified is located at the center of the plurality of adjacent pixel points;

[0015] If the number of the background pixels in the pixel area is greater than the number of other pixels to be identified, the current pixel to be identified is used as the initial diagonal point.

[0016] Furthermore, the step of selecting a target diagonal point from a plurality of the initial diagonal points according to the distribution characteristics of the initial diagonal points comprises:

[0017] Filtering a set of continuous diagonal points from the plurality of initial diagonal points; wherein each initial diagonal point in the set of continuous diagonal points is adjacent to other initial diagonal points;

[0018] Counting the number of initial diagonal points in the continuous diagonal point set;

[0019] The initial number of diagonal points is sorted, and a set of continuous diagonal points corresponding to the first four initial number of diagonal points is used as a corner point area;

[0020] According to the number of background pixels in the pixel area corresponding to each initial diagonal point in the corner point area and the current position feature, the target diagonal point in each corner point area is determined.

[0021] Furthermore, the step of determining the target diagonal point in each corner point area according to the number of background pixels in the pixel area corresponding to each initial diagonal point in the corner point area and the current position feature comprises:

[0022] For each initial diagonal point in each of the corner point regions, extract the number of background pixel points corresponding to the initial diagonal point;

[0023] Extracting the initial diagonal point corresponding to the maximum number of background pixels in the corner point area;

[0024] Calculate the first current position feature of the initial diagonal point corresponding to the maximum number of background pixels;

[0025] Acquire a preset standard location feature, and calculate a first similarity between the first current location feature and the standard location feature;

[0026] If the first similarity is greater than a threshold, the initial diagonal point corresponding to the first current position feature is used as the target diagonal point.

[0027] Furthermore, after the step of obtaining the preset standard location feature and calculating the similarity between the current location feature and the standard location feature, the method further includes:

[0028] If the first similarity is not greater than a threshold, then sequentially calculating the second current position features of the initial diagonal points corresponding to the number of background pixels after the maximum number of background pixels;

[0029] Calculating a second similarity between the second current location feature and the standard location feature;

[0030] If the second similarity is greater than a threshold, the initial diagonal point corresponding to the second current position feature is used as the target diagonal point.

[0031] Furthermore, the step of calculating the first current position feature of the initial diagonal point corresponding to the maximum number of background pixels includes:

[0032] Obtain the number of other pixels to be identified around the initial diagonal point corresponding to the maximum number of background pixels;

[0033] Calculate multiple distances between the initial diagonal point corresponding to the maximum number of background pixels and other diagonal points in the continuous diagonal point set;

[0034] Based on the maximum number of background pixels, the number of other pixels to be identified and the multiple distances, a feature vector is constructed, and the feature vector is used as the first current position feature.

[0035] Furthermore, the step of constructing a feature vector based on the maximum number of background pixels, the number of other pixels to be identified and the multiple distances, and using the feature vector as the first current position feature includes:

[0036] Arrange the multiple distances based on their numerical values ​​to obtain a distance vector;

[0037] Combining the distance vector, the maximum number of background pixels and the number of other pixels to be identified to obtain the feature vector;

[0038] The feature vector is used as the first current position feature.

[0039] A second aspect of an embodiment of the present invention provides a positioning device for chip unpacking, comprising:

[0040] A collection unit, used for collecting images of the chips to be unpacked on the storage table;

[0041] A removal unit, configured to remove background pixels corresponding to a preset pixel value range in the image of the chip to be unsealed, according to a preset pixel value range corresponding to the storage platform, to obtain a plurality of pixels to be identified;

[0042] A first screening unit is used to screen initial diagonal points according to the number of other pixels to be identified and the number of background pixels around each current pixel to be identified; wherein the diagonal points refer to the four vertices of the rectangular chip;

[0043] A second screening unit, configured to screen a target diagonal point from a plurality of the initial diagonal points according to distribution characteristics of the initial diagonal points;

[0044] The calibration unit is used to calibrate the opening start point positioning according to the target diagonal point; the opening start point positioning is used to control the laser module or plasma module to move to this point, and perform the chip opening operation based on a preset trajectory.

[0045] A third aspect of an embodiment of the present invention provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the chip unsealing positioning method described in the first aspect are implemented.

[0046] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the chip unsealing positioning method described in the first aspect are implemented.

[0047] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: by collecting the image of the chip to be unsealed on the storage table and removing the background pixels according to the preset pixel value range, the interference information in the image can be effectively removed, and only the valid pixels related to the chip are retained. The initial diagonal points are screened out by analyzing the number of other pixels to be identified and background pixels around the current pixel to be identified. Since the diagonal points are the four vertices of the rectangular chip, the screening process of the initial diagonal points ensures the accurate positioning of the chip edge and provides a reliable basis for the next step of positioning. By analyzing the distribution characteristics of the initial diagonal points, the target diagonal points are further screened out. This step can effectively exclude the diagonal points that are misidentified, ensure the accuracy of the final positioning, and thus reduce the errors that may occur during the chip unsealing process. The unsealing starting point positioning is calibrated according to the target diagonal point to ensure that the laser module or plasma module can be accurately moved to the unsealing starting point position and perform the unsealing operation according to the preset trajectory. This step not only improves the accuracy of the unsealing operation, but also effectively avoids chip damage and improves the unsealing effect. The entire process, from image acquisition, background removal, initial diagonal point screening, target diagonal point optimization to opening start point calibration, is fully automated, reducing manual intervention and improving production efficiency and consistency. In summary, the present invention effectively solves the problem of inaccurate positioning during chip opening through precise image processing and positioning algorithms, and significantly improves the accuracy and efficiency of the opening operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 A schematic flow chart of a chip unsealing positioning method provided by the present invention is shown;

[0050] Figure 2 A schematic diagram of a positioning device for chip unsealing provided by an embodiment of the present invention is shown;

[0051] Figure 3 A schematic diagram of a terminal device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0052] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0053] The embodiments of the present invention provide a positioning method and a positioning device for chip unsealing, so as to solve the technical problem of how to improve the positioning accuracy of the position to be unsealed during the chip unsealing process.

[0054] First, the present invention provides a positioning method for chip unpacking. Figure 1 , Figure 1 FIG. 2 shows a schematic flow chart of a chip unsealing positioning method provided by the present invention. Figure 1 As shown, the chip unsealing positioning method may include the following steps:

[0055] Step 101: Collecting images of the chips to be unpacked on the storage table;

[0056] The camera can be used to capture images of the unsealed area on the storage table. During the image acquisition process, a light field microscope can be used to capture the image with high resolution.

[0057] Step 102: according to the preset pixel value range corresponding to the storage platform, background pixels corresponding to the preset pixel value range are removed from the image of the chip to be opened to obtain a plurality of pixels to be identified;

[0058] In order to facilitate image processing, the color of the platform in this application is quite different from that of the chip to be opened. By presetting the preset pixel value range corresponding to the platform color, the platform area in the image of the chip to be opened is removed to obtain multiple pixels to be identified corresponding to the chip to be opened.

[0059] Step 103: Screening initial diagonal points according to the number of other pixels to be identified and the number of background pixels around each current pixel to be identified; wherein the diagonal points refer to the four vertices of the rectangular chip;

[0060] Since the position of the diagonal point is relatively special, the number of background pixels around the diagonal point is much larger than the number of pixels to be identified (the pixels to be identified refer to the pixels of the chip to be opened, and the background pixels refer to the pixels of the storage table or non-chip). Therefore, based on this rule, this application selects the initial diagonal point by the number of other pixels to be identified and the number of background pixels. The specific screening logic is as follows:

[0061] Specifically, step 103 specifically includes step 1031 to step 1032:

[0062] Step 1031: extract multiple adjacent pixel points around the current pixel point to be identified to form a pixel area; wherein the current pixel point to be identified is located at the center of the multiple adjacent pixel points;

[0063] Taking the current pixel to be identified as the center, multiple adjacent pixel points are extracted to form a pixel area, wherein the number of the multiple adjacent pixel points can be 9, 25, 49, 81, etc.

[0064] Step 1032: If the number of background pixels in the pixel area is greater than the number of other pixels to be identified, the current pixel to be identified is used as the initial diagonal point.

[0065] Since the camera may be affected by light pollution, lens dirt or noise during the acquisition process, abnormal pixels may appear. Among the abnormal pixels, there may be a situation where the number of background pixels is greater than the number of other pixels to be identified. Therefore, in this embodiment, the current pixel to be identified whose number of background pixels is greater than the number of other pixels to be identified is used as the initial diagonal point. In subsequent steps, the initial diagonal points are screened and corrected to avoid the influence of abnormal pixels on the calculation results.

[0066] In this embodiment, multiple adjacent pixels around the current pixel to be identified are extracted to form a pixel area, and the initial diagonal point is accurately screened based on the comparison of the number of background pixels and other pixels to be identified in the pixel area. By determining the current pixel to be identified whose number of background pixels is greater than the number of other pixels to be identified as the initial diagonal point, misjudgment caused by noise or other interference can be effectively avoided. This screening criterion greatly reduces the probability of misidentification and improves the reliability of data in the positioning process. By constructing a pixel area and analyzing the distribution of pixels therein, the diagonal point can be identified quickly and accurately. This method does not require complex calculations, optimizes the efficiency of image processing, and makes the screening process of diagonal points more efficient.

[0067] Step 104: selecting a target diagonal point from a plurality of the initial diagonal points according to the distribution characteristics of the initial diagonal points;

[0068] Since the position distribution of diagonal points has certain regularity, the target diagonal points can be selected from multiple initial diagonal points based on this regularity. The specific logic is as follows:

[0069] Specifically, step 104 includes steps 1041 to 1044:

[0070] Step 1041: Filter a set of continuous diagonal points from the multiple initial diagonal points; wherein each initial diagonal point in the set of continuous diagonal points is adjacent to other initial diagonal points;

[0071] Since the number of background pixels around the diagonal points is also greater than the number of other pixels to be identified, the pixels around the diagonal points will also be determined as initial diagonal points. Therefore, if there is a diagonal point in one place, there must be multiple adjacent continuous initial diagonal points clustered near the diagonal point. Therefore, in this embodiment, the initial diagonal points that are adjacent to each other are regarded as a continuous diagonal point set. The continuous diagonal point set is often more than four (four vertices).

[0072] Step 1042: Counting the number of initial diagonal points in the continuous diagonal point set;

[0073] Step 1043: sorting the initial diagonal point numbers, and taking the continuous diagonal point sets corresponding to the first four initial diagonal point numbers as the corner point region;

[0074] Since there are often fewer initial diagonal points around abnormal pixels, the number of initial diagonal points in the continuous diagonal point set can be screened out, and the continuous diagonal point set corresponding to the true diagonal point can be screened out and used as the corner point area.

[0075] Step 1044: Determine the target diagonal point in each corner point area according to the number of background pixels in the pixel area corresponding to each initial diagonal point in the corner point area and the current position characteristics.

[0076] Since the number of background pixels and the current position characteristics between the real diagonal point and the abnormal pixel point are quite different, the target diagonal point can be screened by the number of background pixels and the current position characteristics. The specific logic is as follows:

[0077] Specifically, step 1044 includes steps A1 to A8:

[0078] Step A1: for each initial diagonal point in each of the corner point areas, extract the number of background pixel points corresponding to the initial diagonal point;

[0079] Step A2: extracting the initial diagonal point corresponding to the maximum number of background pixels in the corner point area;

[0080] Since the number of background pixels at the corner point is often the largest in the area corresponding to the chip, this embodiment extracts the initial diagonal point corresponding to the maximum number of background pixels in the corner point area to determine whether the initial diagonal point is a real corner point.

[0081] Step A3: calculating the first current position feature of the initial diagonal point corresponding to the maximum number of background pixels;

[0082] The first current position feature includes but is not limited to the number of background pixels, the number of pixels to be identified, and the distance between multiple pixels. The specific calculation logic is as follows:

[0083] Specifically, step A3 specifically includes steps A31 to A33:

[0084] Step A31: obtaining the number of other pixels to be identified around the initial diagonal point corresponding to the maximum number of background pixels;

[0085] The number of other pixels to be identified obtained in step 1031 and step 1032 for the initial diagonal point is obtained.

[0086] Step A32: Calculate multiple distances between the initial diagonal point corresponding to the maximum number of background pixels and other diagonal points in the continuous diagonal point set;

[0087] Since in the chip image area corresponding to the chip, there are often only continuous diagonal points in the chip image area near the vertex, that is, the pixels in the continuous diagonal point set are often the pixels near the vertex. If the initial diagonal point is a true diagonal point, the initial diagonal point is closer to the pixels in the continuous diagonal point set and is within a certain numerical range. If the initial diagonal point is an interference point, the initial diagonal point is far away from the pixels in the continuous diagonal point set and will exceed the numerical range. Therefore, the multiple distances between the initial diagonal point corresponding to the maximum number of background pixels and other diagonal points in the continuous diagonal point set can be used as part of the first current position feature.

[0088] Step A33: construct a feature vector based on the maximum number of background pixels, the number of other pixels to be identified and the multiple distances, and use the feature vector as the first current position feature.

[0089] Specifically, step A33 specifically includes steps A331 to A333:

[0090] Step A331: Arrange the multiple distances based on their numerical values ​​to obtain a distance vector;

[0091] Step A332: combining the distance vector, the maximum number of background pixels and the number of other pixels to be identified to obtain the feature vector;

[0092] Step A333: Use the feature vector as the first current position feature.

[0093] In this embodiment, by obtaining the number of other pixels to be identified around the initial diagonal point corresponding to the maximum number of background pixels, combined with multiple distances of other diagonal points in the continuous diagonal point set, a feature vector is comprehensively constructed, so that the feature vector can fully describe the spatial and background information of the initial diagonal point, thereby enhancing the feature description capability. Based on the detailed feature vector, the current position feature of the initial diagonal point can be more accurately characterized. Compared with the extraction method of a single feature, the accuracy of diagonal point positioning is greatly improved, and the accuracy of subsequent target diagonal point recognition is guaranteed. By considering the number of background pixels and the spatial distance features at the same time, it can not only adapt to different image backgrounds, but also maintain a high recognition performance in a complex environment, thereby enhancing the robustness and adaptability of the system in different application scenarios. By constructing a fine feature vector, the difference between the initial diagonal point and its surrounding pixels can be effectively distinguished, the misrecognition rate is reduced, and the reliability of the target diagonal point determination is improved. The use of a structured feature vector as the current position feature makes the subsequent similarity calculation and target diagonal point recognition process more efficient, reduces the computational complexity, and improves the overall processing efficiency. In practical applications, the construction method of the feature vector can be dynamically adjusted according to specific needs to adapt to different recognition accuracy and efficiency requirements, providing high flexibility and adjustability. In summary, the present invention significantly improves the current position feature description capability of the initial diagonal point by constructing a feature vector based on the maximum number of background pixels, the number of other pixels to be identified, and multiple distances, thereby improving the accuracy and efficiency of target diagonal point recognition.

[0094] Step A4: obtaining a preset standard location feature, and calculating a first similarity between the first current location feature and the standard location feature;

[0095] The standard position features are calculated based on the data of the true diagonal points.

[0096] Step A5: If the first similarity is greater than a threshold, the initial diagonal point corresponding to the first current position feature is used as the target diagonal point.

[0097] Step A6: if the first similarity is not greater than a threshold, then sequentially calculating the second current position features of the initial diagonal points corresponding to the number of background pixels after the maximum number of background pixels;

[0098] The number of background pixels after the maximum number of background pixels refers to the second number of background pixels, the third number of background pixels, the fourth number of background pixels, the fifth number of background pixels, and so on. The second current position features of the above number of pixels are calculated in sequence until the second similarity between the second current position feature and the standard position feature is greater than a threshold value, and the target diagonal point is obtained.

[0099] Step A7: calculating a second similarity between the second current location feature and the standard location feature;

[0100] Step A8: If the second similarity is greater than a threshold, the initial diagonal point corresponding to the second current position feature is used as the target diagonal point.

[0101] In this embodiment, by screening a continuous diagonal point set from a plurality of initial diagonal points and sorting them according to the number of initial diagonal points, it is ensured that the most likely diagonal point area is screened out. The target diagonal point is further determined according to the pixel features and the number of background pixels in each diagonal point area, which greatly improves the accuracy of diagonal point positioning. The method can effectively eliminate isolated or noise points by counting the number of initial diagonal points in the continuous diagonal point set and sorting the first four sets based on the number, which can significantly reduce the positioning error caused by noise or misjudgment and improve the reliability of target diagonal point identification. By combining the number of background pixels in the pixel area and the current position characteristics, the target diagonal point is accurately identified. The method of counting and sorting the continuous diagonal point set can quickly lock the potential target diagonal point area, reduce the computational complexity of the algorithm, and improve the processing efficiency and real-time performance. The method has strong adaptability through the analysis of the distribution characteristics of the initial diagonal points, and can be applied to the chip unsealing process of different shapes and sizes, providing technical guarantee for a wide range of industrial applications. In the entire process of screening the target diagonal points, fully automated processing is achieved, reducing human intervention and errors, and significantly improving production efficiency and consistency. At the same time, automated processing can speed up the chip unsealing process and shorten the production cycle. By accurately screening the target diagonal points, the accurate positioning of the unsealing starting point is ensured, thereby controlling the movement path of the laser module or plasma module. This process not only improves the accuracy of the unsealing operation, but also effectively protects the integrity of the chip and reduces the risk of damage.

[0102] Step 105: Calibrate the opening start point positioning according to the target diagonal point; the opening start point positioning is used to control the laser module or plasma module to move to this point, and perform the chip opening operation based on a preset trajectory.

[0103] Chip unsealing operations include but are not limited to plasma control, motion control, and cycle control.

[0104] Plasma control: Use VISA Configure Serial Port VI to connect to the plasma device. Use VISA Write Function to write plasma parameters to the plasma controller, or modify and replace the parameters in the controller. Use VISA Read Function to read the return value of the plasma controller to determine the status of the controller executing the instruction.

[0105] Motion control: The smc_home_move function executes the zero return operation of each axis of the device to correct the position deviation that occurs in long-term motion. At this time, the smc_line_unit function is mainly used to implement linear interpolation motion to complete the difference compensation motion between the coordinates in the data area of ​​the Kaifeng area and realize the positioning motion of the Kaifeng area.

[0106] Loop control: Use the For Loop structure in the labVIEW platform to realize the number of movement cycles, and use the CaseStructure structure to determine the report results in the loop structure. TRUE can continue to execute the unsealing action until the set number of cycles is completed and it stops automatically; FALSE prompts the cause of the error and terminates the current unsealing process.

[0107] In this embodiment, by collecting the image of the chip to be unsealed on the storage table and removing the background pixels according to the preset pixel value range, the interference information in the image can be effectively removed, and only the valid pixels related to the chip are retained. The initial diagonal points are screened out by analyzing the number of other pixels to be identified and background pixels around the current pixel to be identified. Since the diagonal points are the four vertices of the rectangular chip, the screening process of the initial diagonal points ensures the accurate positioning of the chip edge and provides a reliable basis for the next step of positioning. By analyzing the distribution characteristics of the initial diagonal points, the target diagonal points are further screened out. This step can effectively exclude the diagonal points that are misidentified, ensure the accuracy of the final positioning, and thus reduce the errors that may occur during the chip unsealing process. The unsealing starting point positioning is calibrated according to the target diagonal point to ensure that the laser module or plasma module can be accurately moved to the unsealing starting point position, and the unsealing operation is performed according to the preset trajectory. This step not only improves the accuracy of the unsealing operation, but also effectively avoids chip damage and improves the unsealing effect. The entire process, from image acquisition, background removal, initial diagonal point screening, target diagonal point optimization to opening start point calibration, is fully automated, reducing manual intervention and improving production efficiency and consistency. In summary, the present invention effectively solves the problem of inaccurate positioning during chip opening through precise image processing and positioning algorithms, and significantly improves the accuracy and efficiency of the opening operation.

[0108] like Figure 2 The present invention provides a positioning device for chip unsealing, see Figure 2 , Figure 2 A schematic diagram of a positioning device for chip unsealing provided by the present invention is shown. Figure 2 A positioning device for chip unsealing is shown, comprising:

[0109] A collection unit 21, used for collecting images of the chips to be unpacked on the storage table;

[0110] A removal unit 22 is used to remove background pixels corresponding to a preset pixel value range in the chip image to be opened according to a preset pixel value range corresponding to the storage platform, so as to obtain a plurality of pixels to be identified;

[0111] The first screening unit 23 is used to screen the initial diagonal points according to the number of other pixels to be identified and the number of background pixels around each current pixel to be identified; wherein the diagonal points refer to the four vertices of the rectangular chip;

[0112] A second screening unit 24 is used to screen a target diagonal point from the plurality of initial diagonal points according to the distribution characteristics of the initial diagonal points;

[0113] The calibration unit 25 is used to calibrate the opening start point positioning according to the target diagonal point; the opening start point positioning is used to control the laser module or plasma module to move to this point and perform the chip opening operation based on a preset trajectory.

[0114] The present invention provides a positioning device for chip unsealing. By collecting an image of a chip to be unsealed on a storage table and eliminating background pixels according to a preset pixel value range, the interference information in the image can be effectively removed, and only valid pixels related to the chip are retained. The initial diagonal points are screened out by analyzing the number of other pixels to be identified and background pixels around the current pixel to be identified. Since the diagonal points are the four vertices of a rectangular chip, the screening process of the initial diagonal points ensures the precise positioning of the chip edge and provides a reliable basis for the next step of positioning. By analyzing the distribution characteristics of the initial diagonal points, the target diagonal points are further screened out. This step can effectively exclude the misidentified diagonal points and ensure the accuracy of the final positioning, thereby reducing the errors that may occur during the chip unsealing process. The unsealing starting point positioning is calibrated according to the target diagonal points to ensure that the laser module or plasma module can be accurately moved to the unsealing starting point position and perform the unsealing operation according to the preset trajectory. This step not only improves the accuracy of the unsealing operation, but also effectively avoids chip damage and improves the unsealing effect. The entire process, from image acquisition, background removal, initial diagonal point screening, target diagonal point optimization to opening start point calibration, is fully automated, reducing manual intervention and improving production efficiency and consistency. In summary, the present invention effectively solves the problem of inaccurate positioning during chip opening through precise image processing and positioning algorithms, and significantly improves the accuracy and efficiency of the opening operation.

[0115] Figure 3 Schematic diagram of a terminal device provided by an embodiment of the present invention. Figure 3As shown, a terminal device 3 of this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30, such as a chip unsealing positioning program. When the processor 30 executes the computer program 32, the steps in each of the above chip unsealing positioning method embodiments are implemented, such as Figure 1 Alternatively, when the processor 30 executes the computer program 32, the functions of each unit in the above-mentioned device embodiments are realized, for example, Figure 2 Function of the unit shown.

[0116] Exemplarily, the computer program 32 may be divided into one or more units, which are stored in the memory 31 and executed by the processor 30 to complete the present invention. The one or more units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 32 in the terminal device 3. For example, the computer program 32 may be divided into the following specific functions of each unit:

[0117] A collection unit, used for collecting images of the chips to be unpacked on the storage table;

[0118] A removal unit, configured to remove background pixels corresponding to a preset pixel value range in the image of the chip to be unsealed, according to a preset pixel value range corresponding to the storage platform, to obtain a plurality of pixels to be identified;

[0119] A first screening unit is used to screen initial diagonal points according to the number of other pixels to be identified and the number of background pixels around each current pixel to be identified; wherein the diagonal points refer to the four vertices of the rectangular chip;

[0120] A second screening unit, configured to screen a target diagonal point from a plurality of the initial diagonal points according to distribution characteristics of the initial diagonal points;

[0121] The calibration unit is used to calibrate the opening start point positioning according to the target diagonal point; the opening start point positioning is used to control the laser module or plasma module to move to this point, and perform the chip opening operation based on a preset trajectory.

[0122] The terminal device includes but is not limited to a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3 It is only an example of a terminal device 3 and does not constitute a limitation on the terminal device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0123] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0124] The memory 31 may be an internal storage unit of the terminal device 3, such as a hard disk or memory of the terminal device 3. The memory 31 may also be an external storage device of the terminal device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the terminal device 3. The memory 31 is used to store the computer program and other programs and data required by the roaming control device. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0125] It should be understood that the order of execution of the steps in the above embodiment does not necessarily 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 embodiment of the present invention.

[0126] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0127] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0128] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0129] An embodiment of the present invention provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0130] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0131] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0133] In the embodiments provided by the present invention, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed over multiple network units.

[0135] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0136] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0137] As used in the present specification and the appended claims, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to monitoring, depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is monitored" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is monitored" or "in response to monitoring [described condition or event]", depending on the context.

[0138] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0139] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0140] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A positioning method for chip unsealing, characterized in that: The positioning method for chip unsealing includes: Collect images of chips to be unpacked on the storage table; According to the preset pixel value range corresponding to the storage platform, background pixel points corresponding to the preset pixel value range are removed from the image of the chip to be opened to obtain a plurality of pixel points to be identified; Extract multiple adjacent pixel points around the current pixel point to be identified to form a pixel area; wherein the current pixel point to be identified is located at the center of the multiple adjacent pixel points; If the number of the background pixels in the pixel area is greater than the number of other pixels to be identified, the current pixel to be identified is used as the initial diagonal point; wherein the diagonal point refers to the four vertices of the rectangular chip; Filtering a set of continuous diagonal points from the plurality of initial diagonal points; wherein each initial diagonal point in the set of continuous diagonal points is adjacent to other initial diagonal points; Counting the number of initial diagonal points in the continuous diagonal point set; The initial number of diagonal points is sorted, and a set of continuous diagonal points corresponding to the first four initial number of diagonal points is used as a corner point area; Determine the target diagonal point in each corner point area according to the number of background pixels in the pixel area corresponding to each initial diagonal point in the corner point area and the current position feature; According to the target diagonal point, the unsealing starting point positioning is calibrated; the unsealing starting point positioning is used to control the laser module or plasma module to move to the target diagonal point, and perform the chip unsealing operation based on a preset trajectory.

2. The chip unsealing positioning method according to claim 1, characterized in that: The step of determining the target diagonal point in each corner point area according to the number of background pixels in the pixel area corresponding to each initial diagonal point in the corner point area and the current position feature comprises: For each initial diagonal point in each of the corner point regions, extract the number of background pixel points corresponding to the initial diagonal point; Extracting the initial diagonal point corresponding to the maximum number of background pixels in the corner point area; Calculate the first current position feature of the initial diagonal point corresponding to the maximum number of background pixels; Acquire a preset standard location feature, and calculate a first similarity between the first current location feature and the standard location feature; If the first similarity is greater than a threshold, the initial diagonal point corresponding to the first current position feature is used as the target diagonal point.

3. The chip unsealing positioning method according to claim 2, characterized in that: After the step of obtaining the preset standard location feature and calculating the similarity between the current location feature and the standard location feature, the method further includes: If the first similarity is not greater than a threshold, then sequentially calculating the second current position features of the initial diagonal points corresponding to the number of background pixels after the maximum number of background pixels; Calculating a second similarity between the second current location feature and the standard location feature; If the second similarity is greater than a threshold, the initial diagonal point corresponding to the second current position feature is used as the target diagonal point.

4. The chip unsealing positioning method according to claim 2, characterized in that: The step of calculating the first current position feature of the initial diagonal point corresponding to the maximum number of background pixels comprises: Obtain the number of other pixels to be identified around the initial diagonal point corresponding to the maximum number of background pixels; Calculate multiple distances between the initial diagonal point corresponding to the maximum number of background pixels and other diagonal points in the continuous diagonal point set; Based on the maximum number of background pixels, the number of other pixels to be identified and the multiple distances, a feature vector is constructed, and the feature vector is used as the first current position feature.

5. The chip unsealing positioning method according to claim 4, characterized in that: The step of constructing a feature vector based on the maximum number of background pixels, the number of other pixels to be identified and the multiple distances, and using the feature vector as the first current position feature comprises: Arrange the multiple distances based on their numerical values ​​to obtain a distance vector; Combining the distance vector, the maximum number of background pixels and the number of other pixels to be identified to obtain the feature vector; The feature vector is used as the first current position feature.

6. A positioning device for chip unsealing, characterized in that: The positioning device for chip unsealing comprises: A collection unit, used for collecting images of the chips to be unpacked on the storage table; A removal unit, configured to remove background pixels corresponding to a preset pixel value range in the image of the chip to be unsealed, according to a preset pixel value range corresponding to the storage platform, to obtain a plurality of pixels to be identified; A first screening unit is used to extract multiple adjacent pixel points around the current pixel point to be identified to form a pixel area; wherein the current pixel point to be identified is located at the center of the multiple adjacent pixel points; if the number of background pixel points in the pixel area is greater than the number of other pixel points to be identified, the current pixel point to be identified is used as an initial diagonal point; wherein the diagonal points refer to the four vertices of a rectangular chip; A second screening unit is used to screen a set of continuous diagonal points from the multiple initial diagonal points; wherein each initial diagonal point in the set of continuous diagonal points is adjacent to other initial diagonal points; count the number of initial diagonal points in the set of continuous diagonal points; sort the number of initial diagonal points, and use the continuous diagonal point sets corresponding to the first four initial diagonal points as the corner point area; determine the target diagonal point in each corner point area according to the number of background pixels in the pixel area corresponding to each initial diagonal point in the corner point area and the current position feature; The calibration unit is used to calibrate the opening start point positioning according to the target diagonal point; the opening start point positioning is used to control the laser module or plasma module to move to the target diagonal point, and perform the chip opening operation based on a preset trajectory.

7. A terminal device, characterized in that: The terminal device comprises: a memory, a processor and a chip unsealing positioning program stored in the memory and executable on the processor, wherein the chip unsealing positioning program is configured to implement the steps in the chip unsealing positioning method as claimed in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps in the chip unsealing positioning method according to any one of claims 1 to 5 are implemented.

Images