Layered and regional visual detection method for solar silicon wafer fragments

Abstract

The layered and regional visual detection method for solar silicon chip fragments of the present application belongs to the technical field of image processing, and solves the technical problem of automatically detecting solar silicon chip fragments, and comprises the following steps: 1, image acquisition; 2, irregular fragment detection; 3, chamfer point gap detection; 4, chamfer edge gap detection; 5, straight edge gap detection. Through the present application, automatic real-time high-precision detection of solar silicon chip fragments can be realized.

Description

Technical Field

[0001] The invention belongs to the field of machine vision solar silicon wafer detection and provides a layered and regionalized visual detection method for solar silicon wafer fragments. Background Art

[0002] Today, humanity is heavily reliant on fossil fuels. Solar photovoltaic power generation technology, with its clean, efficient, and renewable characteristics, offers a new solution to the energy crisis. As a fundamental component of photovoltaic power generation systems, the quality of solar silicon wafers significantly impacts their performance. During the solar cell production process, silicon wafers are prone to breakage due to factors such as unstable production equipment. This can significantly impact solar cell efficiency and cause significant losses to related companies. To ensure solar cell quality, precise detection of solar silicon wafer fragments is essential.

[0003] Solar wafer fragment detection methods can be categorized into manual inspection, physical inspection, and machine vision. Manual inspection relies on the experience of production workers to identify solar cell fragments. However, this method is susceptible to interference from external factors, resulting in low efficiency and a high rate of false positives. Physical inspection uses physical methods such as ultrasound and lasers to detect surface cracks in solar cells. This method is also susceptible to interference from external factors and is relatively costly.

[0004] Machine vision inspection methods offer fast detection speed, high accuracy, strong real-time performance, and low cost, and are widely used in the field of solar cell fragment detection. Machine vision inspection methods can be divided into those based on traditional machine vision inspection and those based on deep learning. Traditional machine vision inspection methods offer fast detection speed, high accuracy, and low cost, but they also suffer from shortcomings such as low fault tolerance. This is particularly true in large-scale real-time production line applications, where due to unstable production line operation and variable silicon wafer sources, the captured images exhibit problems such as deformation and uneven brightness. Ultimately, these methods result in a high rate of false positives and missed detections with traditional machine vision inspection algorithms. Deep learning-based inspection methods offer a low false positive rate and strong generalization capabilities, but they also exhibit low accuracy, high cost, and high design difficulty.

[0005] Solar wafer fragments come in a wide variety of types and sizes. Due to transportation vibrations, unstable production equipment, and the fragility of silicon wafers, many solar wafers have large gaps, while some have small gaps (less than 0.1mm). This presents a significant challenge in detecting solar wafer fragments. Furthermore, solar wafer fragment detection must be performed in real time to meet actual production throughput requirements.

[0006] Meanwhile, the notch of the solar silicon wafer occurs at the chamfer and straight edge of the silicon wafer, and the notch at the chamfer can be further divided into the notch at the chamfer point (the position where the chamfer of the silicon wafer connects with the edge of the silicon wafer) and the notch at the chamfer edge (the position inside the chamfer of the silicon wafer). The arrangement and distribution of the pixels of the silicon wafer notch are different, and the size of different silicon wafer notches is greatly different, so how to detect the silicon wafer notch type at different positions with high precision and in real time is also a big problem. SUMMARY

[0007] The main purpose of the present application is to overcome the problems of the conventional image algorithm, such as not distinguishing the notch type, missing detection at the chamfer, and difficult detection of small notches, in the application of real-time silicon wafer production line vision detection, and to provide a layered and regional vision detection method for solar silicon wafer fragments. According to the size, position and pixel distribution characteristics of the solar silicon wafer notch, the present application proposes a layered and regional vision detection method for solar silicon wafer fragments.

[0008] The present application is realized by the following technical scheme: a layered and regional vision detection method for solar silicon wafer fragments, comprising the following steps:

[0009] S1, using back light mode, using an industrial camera to collect solar silicon wafer images to obtain an original image I;

[0010] S2, irregular fragment detection; after the original image I is binarized to obtain an image I1, whether it is an irregular fragment is determined by using the area difference between the effective contour and the minimum circumscribed rectangle of the image I1, wherein the effective contour is the contour with the largest area;

[0011] S3, chamfer point notch detection; the chamfer region of the image I is cut to obtain four chamfer images of the silicon wafer, the coordinates of the effective contour in the chamfer are converted, the width of the coordinate points in the effective contour is calculated to obtain chamfer point 1 and chamfer point 2, all coordinate points in the effective contour are traversed and the x coordinate difference and y coordinate difference of the current point and its adjacent points are calculated, and then the sum PDiff of the x coordinate difference and y coordinate difference of the current point is obtained i ; the value of PDiff i is used to determine the outlier; the outlier Outlier i is classified and screened according to the rules to obtain the x-direction outlier and the y-direction outlier; all outliers are traversed, whether there is a continuous gradient anomaly at the chamfer point is determined according to the coordinate difference of the adjacent outliers, if there is, there is a notch at the chamfer point; the area of the effective contour is calculated, if the area of the effective contour is greater than the area threshold, it is determined that the area of the chamfer point of the silicon wafer is abnormal.

[0012] S4, chamfer edge notch detection: perform 2x super-resolution and binarization on the four corner images respectively, perform coordinate transformation on the effective contour in the processed corner image, traverse all coordinate points of the effective contour after coordinate transformation and calculate the x-coordinate difference and y-coordinate difference between the current point and its adjacent points, and obtain the sum of the differences. Determine the abnormal point according to the rules based on the value of the sum of the differences, and finally determine whether there is a notch at the chamfer edge of the silicon wafer based on the coordinate difference of adjacent positive and negative abnormal points;

[0013] S5, straight edge gap detection; crop image I, and perform 2x super-resolution and high grayscale binarization with a binarization threshold of 150 to obtain four straight edge images of the silicon wafer, traverse the valid contours in the straight edge images, calculate the x-direction difference or y-direction difference between the current coordinate point and its adjacent coordinates, then obtain the abnormal points according to the rules based on the values ​​of the x-direction difference or y-direction difference, and finally determine whether the silicon wafer has a left straight edge gap or an upper straight edge gap based on the coordinate difference of adjacent positive and negative abnormal points.

[0014] Furthermore, the specific process of irregular fragment detection in step S2 is as follows:

[0015] S2-1, performing a binarization operation on the original image I to obtain image I1;

[0016] S2-2, find and traverse all contours in image I1, and obtain the valid contour Contour and its minimum circumscribed rectangle Contour_rect;

[0017] S2-3. Calculate the area difference between Contour_rect and Contour using formula (1):

[0018] Area_diff=Contour_rect_area-Contour_area (1)

[0019] Among them, Contour_rect_area and Contour_area are the areas of Contour_rect and Contour respectively;

[0020] S2-4. If Area_diff satisfies formula (2), that is, the difference between the minimum circumscribed rectangle area of ​​the solar cell and its outline area is too large, it is considered that there are irregular fragments in the solar silicon wafer;

[0021] Area_diff>200000 (2)

[0022] S2-5. If it is determined in step S2-4 that irregular fragments exist on the solar silicon wafer, the text "damaged slice!" is output on the image I.

[0023] Furthermore, the specific process of chamfer point notch detection in step S3 is as follows:

[0024] S3-1. Cropping and binarizing the lower right, upper right, lower left, and upper left corners of image I, respectively, to obtain image CP1 of the lower right chamfer, image CP2 of the upper right chamfer, image CP3 of the lower left chamfer, and image CP4 of the upper left chamfer of the solar silicon wafer. The length and width of the cropped areas are both 300.

[0025] S3-2, find and traverse all contours in CP1 to obtain the valid contour ChamferP1;

[0026] S3-3, traverse the coordinate points on ChamferP1 and transform the coordinate points according to formula (3) and formula (4);

[0027] ChamferP 1,X,i =ChamferP 1,x,i +(w-300) (3)

[0028] ChamferP 1,Y,i =ChamferP 1,y,i +(h-300) (4)

[0029] Among them, ChamferP 1,x,i is the x-coordinate of the traversed point, ChamferP 1,y,i is the y coordinate of the traversed point, ChamferP 1,X,i and ChamferP 1,Y,i are the x- and y-coordinates of the point after coordinate conversion, w is the width of image I, and h is the height of image I;

[0030] S3-4, perform the operation of step S3-2 on CP2, CP3 and CP4 respectively to obtain the effective contours ChamferP2, ChamferP3 and ChamferP4. In particular, in step S3-3, for the points in ChamferP2, only coordinate transformation needs to be performed according to formula (3), for the points in ChamferP3, only coordinate transformation needs to be performed according to formula (4), and for the points in ChamferP4, no coordinate transformation is required;

[0031] S3-5, traverse the coordinate points after coordinate transformation in ChamferP1, and calculate the coordinate difference between two adjacent coordinate points according to formula (5):

[0032]

[0033] Among them, X_diff iIndicates the difference between two adjacent coordinate points in the x direction, Y_diff i Indicates the difference between two adjacent coordinate points in the y direction;

[0034] S3-6, traverse the coordinate points in ChamferP1 and calculate the x-width Width_x of the current point according to formula (6) i , and calculate the average value Sumwidth_x of the x-direction width of the current point and the sum of the x-direction widths of the 20 points after the current point according to formula (7) i Finally, the difference ΔWidthx is calculated according to formula (8) i , if the difference satisfies formula (9), this point is the chamfer point Coner1 on the lower left of ChamferP1;

[0035] Width_x i =|ChamferP 1,X,i -300| (6)

[0036]

[0037] ΔWidthx i =Widh_x i -Sumwidth_x i (8)

[0038] ΔWidthx i <0.3 (9) S3-7, the principle is the same as step S3-5, traverse the coordinate points in the contour ChamferP1 and calculate the y-axis width of the current traversed point to obtain the chamfer point Coner2 on the upper right of ChamferP1;

[0039] S3-8, in the contour ChamferP1, traverse each X_diff obtained by formula (5) i and Y_diff i , and calculate PDiff according to formula (10) i :

[0040] PDiff i =|X_diff i |+|Y_diff i | (10)

[0041] According to the calculation results, PDiff i The value is 1 or 2;

[0042] S3-9, starting from PDiff5, traverse the PDiff obtained in step S3-8 in sequence i , according to rules a and b, determine whether there are abnormal points at the chamfer point:

[0043] Rule a: PDiff i-3 PDiff i-2 PDiff i-1 PDiff i PDiff i+1 PDiff i+2 PDiff i+3 There is a value equal to 1 in

[0044] Rule b: PDiff i-4 PDiff i-3 PDiff i-2 PDiff i-1 PDiff i+1 PDiff i+2 PDiff i+3 There is a value equal to 1 in

[0045] When the traversed PDiff i When any of the above rules are met, an outlier is obtained. i ;

[0046] S3-10, Outlier i It is attributed to the chamfer points Coner1 and Coner2, and then the outlier point X_Outlier in the x direction is obtained. i and the outlier point in the y direction Y_Outlier i ;

[0047] S3-11, traverse X_Outlier separately i and Y_Outlier i , and calculate the difference ΔX_Outlier according to formula (11) and formula (12) i and ΔY_Outlier i :

[0048] ΔX_Outlier i =|X_Outlier x,i -X_Outlier x,i-1 | (11)

[0049] ΔY_Outlier i =|Y_Outlier y,i -Y_Outlier y,i-1 | (12)

[0050] Among them, X_Outlier x,i X_Outlier i x coordinate, Y_Outliery,i Y_Outlier i The y coordinate of ΔX_Outlier i or ΔY_Outlier i If it is less than 3, then the X_Outlier i and Y_Outlier i Keep it as an outlier, otherwise remove it from the outlier set. After the traversal is completed, the outlier points X_Outlier in the x and y directions can be obtained again. i and Y_Outlier i ;

[0051] S3-12, detect the abnormal gap of continuous gradient at chamfer point; traverse the X-direction abnormal point X_Outlier i , calculate the difference between adjacent outliers according to formula (11), if there are two consecutive ΔX_outlier i If it is greater than 1, it is determined that there is a continuous abnormal gradient gap at the chamfer point. For the y-direction chamfer point, traverse the y-direction abnormal point Y_Outlier i , calculate the difference between adjacent outliers according to formula (12), if there are two consecutive ΔY_outlier i If it is greater than 1, it is determined that there is a continuous abnormal gradient gap at the chamfer point;

[0052] S3-13, calculate the contour ChamferP1 area C_area by formula (13);

[0053]

[0054] If the value of C_area satisfies formula (14), it is determined that there is an abnormal gap in the chamfer area of ​​the solar silicon wafer;

[0055] C_area>15 (14) S3-14, perform steps S3-5 to S3-13 on the contours ChamferP2, ChamferP3 and ChamferP4, and determine whether there are abnormal area gaps and abnormal continuous gradient gaps at the chamfer points;

[0056] S3-15. If a gap is detected in the above step, the gap position is framed in the image.

[0057] Furthermore, the specific process of the S4 chamfer edge notch detection is as follows:

[0058] S4-1, perform 2x super-resolution and binarization on CP1, CP2, CP3, and CP4, respectively, to obtain a lower right chamfer image CE1, an upper right chamfer image CE2, a lower left chamfer image CE3, and an upper left chamfer image CE4;

[0059] S4-2, find all contours in CE1; traverse all contours and find the valid contour ChamferEdge1, and perform the same operation on CE2, CE3 and CE4 to obtain the valid contours ChamferEdge2, ChamferEdge3 and ChamferEdge4 respectively;

[0060] S4-3, similar to the principles of steps S3-3 and S3-4, perform corresponding coordinate transformation on ChamferEdge1, ChamferEdge2, ChamferEdge3 and ChamferEdge4;

[0061] S4-4, traverse the coordinate points after coordinate transformation in the contour ChamferEdge1, and calculate the x and y coordinate differences between two adjacent coordinate points according to formula (15):

[0062]

[0063] Here, ChamferEdge 1,x,i The x coordinate of the point after coordinate transformation on ChamferEdge1, ChamferEdge 1,y,i The y coordinate of the point after coordinate transformation on ChamferEdge1, Cx_diff i Indicates the difference between adjacent coordinate points in the x direction, Cy_diff i Indicates the difference between adjacent coordinate points in the y direction;

[0064] S4-5, traverse each Cx_diff obtained in step S4-4 i and Cy_diff i , and calculate EDiff according to formula (16) i :

[0065] EDiff i =|Cx_diff i |+|Cy_diff i | (16)

[0066] According to the calculation results, EDiff i The value is 1 or 2;

[0067] S4-6, starting from EDiff5, traverse the EDiff obtained in step S4-5 in sequence i , and judge the abnormal points according to rules c and d:

[0068] Rule c: EDiff i-3 EDiff i-2 EDiffi-1 EDiff i EDiff i+1 EDiff i+2 EDiff i+3 There is a value equal to 1 in

[0069] Rule d: EDiff i-4 EDiff i-3 EDiff i-2 EDiff i-1 EDiff i+1 EDiff i+2 EDiff i+3 There is a value equal to 1 in

[0070] When rule c or rule d is met, the anomaly point is obtained. i , Anomaly x,i Anomaly i x-coordinate of Anomaly y,i Anomaly i The y coordinate of

[0071] S4-7, Traversing the Anomaly i , marked Anomaly x,i Not equal to 0, Anomaly y,i Anomalies equal to 0 are positive anomalies and are marked as Anomaly. y,i Not equal to 0, Anomaly x,i The outlier point equal to 0 is a negative outlier point. If there is a negative outlier point, search counterclockwise to see if there is a positive outlier point. If so, calculate the coordinate difference between the two outlier points according to formula (17), and judge whether the chamfer edge concave meets the detection condition according to formula (18):

[0072]

[0073] Here, τ a is the detection threshold, and the threshold is 20. If formula (18) is satisfied, it is determined that there is a concave notch at the chamfered edge of the solar cell;

[0074] S4-8, for the points in the contours ChamferEdge2, ChamferEdge3 and ChamferEdge4, it is only necessary to repeat the process of steps S4-4 to S4-7 to determine whether there is a concave notch at the upper left chamfer edge of the solar silicon wafer; in particular, for the contours ChamferEdge2 and ChamferEdge3, if there are positive abnormal points, then search counterclockwise to determine whether there are negative abnormal points. If so, then further determine the coordinate difference between the two abnormal points according to formula (17). If the coordinate difference satisfies formula (18), then it is determined that there is a concave notch on the chamfer edge.

[0075] S4-9. If a gap is detected in the above steps, the gap position is framed in the image.

[0076] Furthermore, the specific process of the straight edge gap detection in step S5 is as follows:

[0077] S5-1. Cropping image I based on the chamfer points obtained in the previous step, and performing a 2x super-resolution and high-grayscale binarization with a binarization threshold of 150 on the cropped image to obtain images e1, e2, e3, and e4 representing the left straight edge, right straight edge, top straight edge, and bottom straight edge of the solar cell, respectively.

[0078] S5-2, traverse all contours in each image in images e1, e2, e3 and e4, and then find the valid contours in each image, which are Edge1, Edge2, Edge3 and Edge4 respectively;

[0079] S5-3, traverse the points in Edge1 and calculate the difference between adjacent coordinates in the x direction Ex_diff according to formula (19) i :

[0080] Ex_diff i =Edge 1,x,i+1 -Edge 1,x,i (19)

[0081] Here, Edge 1,x,i is the x coordinate of the midpoint of the traversed contour Edge1, Edge 1,x,i+1 For Edge 1,x,i x coordinates of adjacent points; when Ex_diff i If it is not 0, search counterclockwise for the first non-0 Ex_diff within a distance of 5. i If both are positive, the point is a positive outlier. If both are negative, the point is a negative outlier. If they do not exist or the positive and negative values ​​are opposite, the point is a normal point. The contour points that meet the abnormal conditions are recorded as outliers. i ;

[0082] S5-4. Traverse the outlier point Exoutlier i , set the search distance threshold τ s is 30, if Exoutlier i For a positive outlier, search the distance τ counterclockwise s Is there a negative outlier in the equation? If so, calculate the length ΔEy between the two outliers according to formula (20):

[0083] ΔEy=Exoutlier y,i+n -Exoutlier y,i (20)

[0084] ΔEy<τ e (twenty one)

[0085] Among them, Exoutlier y,i Exoutlier i y coordinate of Exoutlier y,i+n Negative outlier point Exoutlier i+n The y coordinate of e is the detection threshold, which is set to 20. If ΔEy satisfies formula (21), it is determined that there is a left straight edge damage gap in the solar silicon wafer;

[0086] S5-5, performing steps S5-3 to S5-4 on the outline Edge2 to determine whether there is a broken notch on the right straight edge of the solar silicon wafer;

[0087] S5-6, traverse the points in the contour Edge3, and calculate the difference Ey_diff between adjacent coordinates in the y direction according to formula (22) i :

[0088] Ey_diff i =Edge 3,y,i+1 -Edge 3,y,i (twenty two)

[0089] Among them, Edge 3,y,i is the y coordinate of the point in the contour Edge3, Edge 3,y,i+1 For Edge 3,y,i The y coordinates of adjacent points, when the Ey_diff of the i-th contour point i If it is not 0, search counterclockwise for the first non-zero Ey_diff within a distance of 5. i If both are positive, the point is a positive outlier; if both are negative, the point is a negative outlier; if they do not exist or the positive and negative values ​​are opposite, the point is a normal point. The contour points that meet the abnormal conditions are recorded as outliers. i ;

[0090] S5-7, traversing outlier points Eyoutlier i , if Eyoutlier i If it is a negative outlier, search the distance τ counterclockwise. s Is there a positive outlier in the image? If so, calculate the length ΔEx between the two outliers according to formula (23):

[0091] ΔEx=Eyoutlier x,i+n -Eyoutlier x,i (twenty three)

[0092] ΔEx<τ e (twenty four)

[0093] Here, Eyoutlier x,i For Eyoutlier i x coordinate, Eyoutlier x,i+n is a positive outlier point Eyoutlier i+n If ΔEx satisfies formula (24), it is determined that there is a straight edge damage gap on the solar silicon wafer;

[0094] S5-8, performing steps S5-6 to S5-7 for the outline Edge4 to determine whether there is a broken gap on the lower straight edge of the solar cell;

[0095] S5-9. Crop image I according to the chamfer points obtained in the previous step, perform 2x super-resolution and low-grayscale binarization with a binarization threshold of 40 on the cropped image, to obtain images e5, e6, e7, and e8. Perform steps S5-3 to S5-8 on images e5, e6, e7, and e8 to determine whether there are any broken or notched edges on the straight edges of the solar cell.

[0096] S5-10: If a gap is detected in the above steps, the gap position is framed in the image.

[0097] Compared with the prior art, the present invention has the following advantages:

[0098] 1. Layered sequential detection uses two algorithms: large-notch detection for irregular wafers and small-notch detection for regular wafers. The former detects irregularly broken silicon wafers, while the latter detects small notches in different areas of regular silicon wafers, including notches at chamfer points, chamfered edges, and straight edges. This layered sequential detection ensures that the upper-layer large-notch detection algorithm and the lower-layer small-notch detection algorithm do not interfere with each other.

[0099] 2. Divide silicon wafers with regular contours into regions, such as chamfered edges, chamfered points, and straight edge areas, and extract features by region to improve the performance of the detection algorithm.

[0100] 3. For the detection of different levels and different areas, the algorithm of the present invention analyzes the pixel arrangement pattern of the gap in detail, and proposes and implements a pixel-level gap detection algorithm. In the detection of large gaps in irregular slices, the present invention analyzes the concave features of irregular large-sized gaps, and uses the difference between the silicon wafer outline and its minimum circumscribed rectangle to detect irregular large-sized gaps. Before detecting small gaps in regular slices, the present invention uses the characteristics of the sudden change in pixel distribution at the chamfered edge and straight edge of the silicon wafer to obtain the chamfer point of the silicon wafer. In the chamfer point detection area, the present invention obtains the abnormal point through the abnormal difference between adjacent pixel points, and determines whether there is a gap at the chamfer point through indicators such as the number of continuous abnormal points and the area of ​​the abnormal area. In the chamfer edge or straight edge detection area, the present invention searches for positive and negative abnormal points in each area through the relationship between adjacent pixels, compares the relationship between the positive and negative abnormal points of the gap in the current area to obtain suspected gaps, and detects the chamfer edge or straight edge gap based on whether the gap length meets the threshold.

[0101] 4. In the chamfered edge and straight edge areas, the algorithm of the present invention improves the detection accuracy of the gap and enhances the robustness of the detection algorithm by super-resolution processing of the image. BRIEF DESCRIPTION OF THE DRAWINGS

[0102] Figure 1 Flowchart of the present invention;

[0103] Figure 2 This is the original image of a solar cell captured by an industrial camera using backlighting.

[0104] Figure 3 The image in which the gap is detected by the irregular fragment detection step;

[0105] Figure 4 The chamfered image of the cut solar cell;

[0106] Figure 5 The image with the gap detected after the chamfer point gap detection;

[0107] Figure 6 The image with the gap detected after the chamfer edge gap detection;

[0108] Figure 7 The image with the gap detected after the straight edge gap detection; DETAILED DESCRIPTION

[0109] The present invention will be described in further detail below with reference to the accompanying drawings and examples.

[0110] like Figure 1 The method for visually inspecting solar silicon wafer fragments by layer and region includes the following steps:

[0111] S1, such as Figure 2As shown, backlighting is used to capture the image of the solar silicon wafer using an industrial camera to obtain the original image I;

[0112] S2. Irregular fragment detection

[0113] In order to determine whether there are irregular fragments on the solar silicon wafer (large gaps at the chamfers or straight edges of the solar cell), irregular fragment detection is performed on the solar silicon wafer.

[0114] S2-1, performing a binarization operation on the image I to obtain an image I1;

[0115] S2-2, find and traverse all contours in the image I1, and obtain the valid contour Contour (the contour with the largest area among all contours) and its minimum circumscribed rectangle Contour_rect;

[0116] S2-3. Calculate the area difference between Contour_rect and Contour using formula (1):

[0117] Area_diff=Contour_rect_area-Contour_area (1)

[0118] Here, Contour_rect_area and Contour_area are the areas of Contour_rect and Contour respectively;

[0119] S2-4. If Area_diff satisfies formula (2), that is, the difference between the minimum circumscribed rectangle area of ​​the solar cell and its outline area is too large, it is considered that there are irregular fragments in the solar silicon wafer;

[0120] Area_diff>200000 (2)S2-5, such as Figure 3 As shown, if it is determined in step S2-4 that irregular fragments exist in the solar silicon wafer, the text "damaged slice!" is output on the image I.

[0121] S3, chamfer point notch detection

[0122] In order to determine whether there is a gap at the chamfer point of the solar silicon wafer (the junction of the chamfered edge and the straight edge of the solar cell), the chamfer point detection of the solar silicon wafer is performed;

[0123] S3-1, such as Figure 4As shown, the right lower corner region, the right upper corner region, the left lower corner region and the left upper corner region of the image I are cropped and binarized respectively to obtain the right lower chamfer image CP1, the right upper chamfer image CP2, the left lower chamfer image CP3 and the left upper chamfer image CP4 of the solar silicon wafer. The length and width of the cropped region are both 300;

[0124] S3-2, find and traverse all contours in CP1 to obtain the effective contour ChamferP1;

[0125] S3-3, traverse the coordinate points on ChamferP1 and convert the coordinate points according to formula (3) and formula (4);

[0126] ChamferP 1,X,i = ChamferP 1,x,i + (w-300) (3)

[0127] ChamferP 1,Y,i = ChamferP 1,y,i + (h-300) (4)

[0128] Here, ChamferP 1,x,i is the x coordinate of the traversed point, ChamferP 1,y,i is the y coordinate of the traversed point, ChamferP 1,X,i and ChamferP 1,Y,i are the x coordinate and y coordinate of the point after coordinate conversion, w is the width of the image I, and h is the height of the image I;

[0129] S3-4, perform the operation of step S3-2 on CP2, CP3 and CP4 to obtain the effective contours ChamferP2, ChamferP3 and ChamferP4. In particular, in the operation of step S3-3, for the points in ChamferP2, only coordinate conversion according to formula (3) is needed, for the points in ChamferP3, only coordinate conversion according to formula (4) is needed, and for the points in ChamferP4, no coordinate conversion is needed;

[0130] S3-5, traverse the coordinate points after coordinate conversion in ChamferP1, and calculate the coordinate difference between two adjacent coordinate points according to formula (5):

[0131]

[0132] Here, X_diff i represents the difference in x direction between two adjacent coordinate points, and Y_diff i represents the difference in y direction between two adjacent coordinate points;

[0133] S3-6, traverse the coordinate points in ChamferP1 and calculate the x-width Width_x of the current point according to formula (6) i , and calculate the average value Sumwidth_x of the x-direction width of the current point and the sum of the x-direction widths of the 20 points after the current point according to formula (7) i Finally, the difference ΔWidthx is calculated according to formula (8) i If the difference satisfies formula (9), this point is considered to be the chamfer point Coner1 on the lower left of ChamferP1;

[0134] Width_x i =|ChamferP 1,X,i -300| (6)

[0135]

[0136] ΔWidthx i =Widh_x i -Sumwidth_x i (8)

[0137] ΔWidthx i <0.3 (9) S3-7, the principle is the same as step S3-5, traverse the coordinate points in the contour ChamferP1 and calculate the y-axis width of the current traversed point to obtain the chamfer point Coner2 on the upper right of ChamferP1;

[0138] S3-8, in the contour ChamferP1, traverse each X_diff obtained by formula (5) i and Y_diff i , and calculate PDiff according to formula (10) i :

[0139] PDiff i =|X_diff i |+|Y_diff i | (10)

[0140] According to the calculation results, PDiff i The value is 1 or 2;

[0141] S3-9, starting from PDiff5, traverse the PDiff obtained in step S3-8 in sequence i , according to rules a and b, determine whether there are abnormal points at the chamfer point:

[0142] Rule a: (PDiff i-3 PDiff i-2 PDiff i-1PDiff i PDiff i+1 PDiff i+2 PDiff i+3 ) has a value equal to 1.

[0143] Rule b: (PDiff i-4 PDiff i-3 PDiff i-2 PDiff i-1 PDiff i+1 PDiff i+2 PDiff i+3 ) has a value equal to 1.

[0144] When the traversed PDiff i When any of the above rules are met, an outlier is obtained. i ;

[0145] S3-10, Outlier i It is attributed to the chamfer points Coner1 and Coner2, and then the outlier point X_Outlier in the x direction is obtained. i and the outlier point in the y direction Y_Outlier i ;

[0146] S3-11, traverse X_Outlier separately i and Y_Outlier i , and calculate the difference ΔX_Outlier according to formula (11) and formula (12) i and ΔY_Outlier i :

[0147] ΔX_Outlier i =|X_Outlier x,i -X_Outlier x,i-1 | (11)

[0148] ΔY_Outlier i =|Y_Outlier y,i -Y_Outlier y,i-1 | (12)

[0149] Here, X_Outlier x,i X_Outlier i x coordinate, Y_Outlier y,i Y_Outlier i The y coordinate of ΔX_Outlier ior ΔY_Outlier i If it is less than 3, then the X_Outlier i and Y_Outlier i Keep it as an outlier, otherwise remove it from the outlier set. After the traversal is completed, the outlier points X_Outlier in the x and y directions can be obtained again. i and Y_Outlier i ;

[0150] S3-12, detect the abnormal gap of continuous gradient at the chamfer point. Traverse the x-direction abnormal point X_Outlier i , calculate the difference between adjacent outliers according to formula (11), if there are two consecutive ΔX_outlier i If it is greater than 1, it is determined that there is a continuous abnormal gradient gap at the chamfer point. For the y-direction chamfer point, traverse the y-direction abnormal point Y_Outlier i , calculate the difference between adjacent outliers according to formula (12), if there are two consecutive ΔY_outlier i If it is greater than 1, it is determined that there is a continuous abnormal gradient gap at the chamfer point;

[0151] S3-13. To detect abnormal notches in the chamfer area of ​​solar silicon wafers, the contour ChamferP1 area C_area is calculated using formula (13).

[0152]

[0153] If the value of C_area satisfies formula (14), it is determined that there is an abnormal gap in the chamfer area of ​​the solar silicon wafer;

[0154] C_area > 15 (14) S3-14, perform steps S3-5 to S3-13 on the contours ChamferP2, ChamferP3, and ChamferP4 to determine whether there are abnormal area gaps and abnormal continuous gradient gaps at the chamfer points;

[0155] S3-15, such as Figure 5 As shown, if a gap is detected in the above steps, the gap position is framed in the image.

[0156] S4, chamfer edge notch detection

[0157] In order to determine the gaps in the chamfered edges of solar silicon wafers (the straight edge inside the chamfer of the solar cell), the chamfered edges of the solar cell are inspected.

[0158] S4-1, perform 2x super-resolution and binarization on CP1, CP2, CP3, and CP4, respectively, to obtain a lower right chamfer image CE1, an upper right chamfer image CE2, a lower left chamfer image CE3, and an upper left chamfer image CE4;

[0159] S4-2. Find all contours in CE1. Traverse all contours and find the valid contour ChamferEdge1. Repeat the same operation for CE2, CE3, and CE4 to obtain the valid contours ChamferEdge2, ChamferEdge3, and ChamferEdge4 respectively.

[0160] S4-3, similar to the principles of steps S3-3 and S3-4, perform corresponding coordinate transformation on ChamferEdge1, ChamferEdge2, ChamferEdge3 and ChamferEdge4;

[0161] S4-4, traverse the coordinate points after coordinate transformation in the contour ChamferEdge1, and calculate the x and y coordinate differences between two adjacent coordinate points according to formula (15):

[0162]

[0163] Here, ChamferEdge 1,x,i The x coordinate of the point after coordinate transformation on ChamferEdge1, ChamferEdge 1,y,i The y coordinate of the point after coordinate transformation on ChamferEdge1, Cx_diff i Indicates the difference between adjacent coordinate points in the x direction, Cy_diff i Indicates the difference between adjacent coordinate points in the y direction;

[0164] S4-5, traverse each Cx_diff obtained in step S4-4 i and Cy_diff i , and calculate EDiff according to formula (16) i :

[0165] EDiff i =|Cx_diff i |+|Cy_diff i | (16)

[0166] According to the calculation results, EDiff i The value is 1 or 2;

[0167] S4-6, starting from EDiff5, traverse the EDiff obtained in step S4-5 in sequence i, and judge the abnormal points according to rules c and d:

[0168] Rule c: (EDiff i-3 EDiff i-2 EDiff i-1 EDiff i EDiff i+1 EDiff i+2 EDiff i+3 ) has a value equal to 1.

[0169] Rule d: (EDiff i-4 EDiff i-3 EDiff i-2 EDiff i-1 EDiff i+1 EDiff i+2 EDiff i+3 ) has a value equal to 1.

[0170] When rule c or rule d is met, the anomaly point is obtained. i , Anomaly x,i Anomaly i x-coordinate of Anomaly y,i Anomaly i The y coordinate of

[0171] S4-7, Traversing the Anomaly i , marking Anomaly x,i Not equal to 0, Anomaly y,i Anomalies equal to 0 are positive anomalies and are marked as Anomaly. y,i Not equal to 0, Anomaly x,i An outlier equal to 0 is a negative outlier. If there is a negative outlier, search counterclockwise to see if there is a positive outlier. If so, calculate the coordinate difference between the two outliers according to formula (17), and determine whether the chamfered edge concave meets the detection conditions according to formula (18):

[0172]

[0173] Here, τ a is the detection threshold, which is generally set to 20. If formula (18) is satisfied, it is determined that there is a concave notch at the chamfered edge of the solar cell;

[0174] S4-8, for the points in the profiles ChamferEdge2, ChamferEdge3 and ChamferEdge4, only repeat the process of steps S4-4 to S4-7 to determine whether there is a concave notch at the left upper chamfer edge of the solar wafer; in particular, for the profiles ChamferEdge2 and ChamferEdge3, if there is a positive abnormal point, then counterclockwise search whether there is a negative abnormal point, if there is, then further determine the coordinate difference between the two abnormal points according to formula (17), and if the coordinate difference satisfies formula (18), it is determined that the chamfer edge has a concave notch;

[0175] S4-9, as shown in the above steps, if a notch is detected, the notch position is framed in the image. Figure 6

[0176] S5, straight edge notch detection

[0177] In order to determine the notch at the straight edge of the solar cell, the straight edge of the solar cell is detected.

[0178] S5-1, according to the chamfer point obtained in the previous step, the image I is cut, and the cut image is 2 times super-resolution and high gray value binary with a threshold of 150, to obtain images e1, e2, e3 and e4 representing the left straight edge, right straight edge, upper straight edge and lower straight edge of the solar cell respectively;

[0179] S5-2, traverse all the profiles in each image in the images e1, e2, e3 and e4, and then find the effective profiles in each image, which are Edge1, Edge2, Edge3 and Edge4 respectively;

[0180] S5-3, traverse the points in Edge1, and calculate the difference Ex_diff between adjacent coordinates in x direction according to formula (19) i :

[0181] Ex_diff i =Edge 1,x,i+1 -Edge 1,x,i (19)

[0182] Here, Edge 1,x,i is the x coordinate of the point in the profile Edge1 being traversed, and Edge 1,x,i+1 is the x coordinate of the adjacent point of Edge 1,x,i . When Ex_diff i is not 0, then counterclockwise search the first Ex_diff i ​If both are positive, the point is a positive outlier; if both are negative, the point is a negative outlier; if they do not exist or the positive and negative values ​​are opposite, the point is a normal point. The contour points that meet the abnormal conditions are recorded as outliers. i ;

[0183] S5-4. Traverse the outlier point Exoutlier i , set the search distance threshold τ s is 30, if Exoutlier i For a positive outlier, search the distance τ counterclockwise s Is there a negative outlier in the equation? If so, calculate the length ΔEy between the two outliers according to formula (20):

[0184] ΔEy=Exoutlier y,i+n -Exoutlier y,i (20)

[0185] ΔEy<τ e (twenty one)

[0186] Here, Exoutlier y,i Exoutlier i y coordinate of Exoutlier y,i+n Negative outlier point Exoutlier i+n The y coordinate of e is the detection threshold, which is generally set to 20. If ΔEy satisfies formula (21), it is determined that there is a left straight edge damage gap in the solar silicon wafer;

[0187] S5-5, performing steps S5-3 to S5-4 on the outline Edge2 to determine whether there is a broken notch on the right straight edge of the solar silicon wafer;

[0188] S5-6, traverse the points in the contour Edge3, and calculate the difference Ey_diff between adjacent coordinates in the y direction according to formula (22) i :

[0189] Ey_diff i =Edge 3,y,i+1 -Edge 3,y,i (twenty two)

[0190] Here, Edge 3,y,i is the y coordinate of the point in the contour Edge3, Edge 3,y,i+1 For Edge 3,y,i The y coordinates of adjacent points. When the Ey_diff of the i-th contour point i If it is not 0, search counterclockwise for the first non-zero Ey_diff within a distance of 5.i If both are positive, the point is a positive outlier; if both are negative, the point is a negative outlier; if they do not exist or the positive and negative values ​​are opposite, the point is a normal point. The contour points that meet the abnormal conditions are recorded as outliers. i ;

[0191] S5-7, traversing outlier points Eyoutlier i , if Eyoutlier i If it is a negative outlier, search the distance τ counterclockwise. s Is there a positive outlier in the image? If so, calculate the length ΔEx between the two outliers according to formula (23):

[0192] ΔEx=Eyoutlier x,i+n -Eyoutlier x,i (twenty three)

[0193] ΔEx<τ e (twenty four)

[0194] Here, Eyoutlier x,i For Eyoutlier i x coordinate, Eyoutlier x,i+n is a positive outlier point Eyoutlier i+n If ΔEx satisfies formula (24), it is determined that there is a broken notch on the upper straight edge of the solar silicon wafer;

[0195] S5-8, performing steps S5-6 to S5-7 for the outline Edge4 to determine whether there is a broken gap on the lower straight edge of the solar cell;

[0196] S5-9. Crop image I based on the chamfer points obtained in the previous step, super-resolve the cropped image by a factor of 2, and binarize it with a low grayscale threshold of 40 to obtain images e5, e6, e7, and e8. Perform steps S5-3 to S5-8 on images e5, e6, e7, and e8 to determine whether there are any broken or notched edges on the straight edges of the solar cell.

[0197] S5-10, such as Figure 7 As shown, if a gap is detected in the above steps, the gap position is framed in the image.

[0198] When detecting solar silicon wafer fragments, the present invention uses machine vision to accurately and rapidly locate notches in solar silicon wafers, meeting the requirements of actual solar cell production sites. The present invention uses machine vision and image processing algorithms to locate notches at chamfered corners and straight edges of solar silicon wafers, achieving the goal of automatic detection. Based on the location, size, and pixel distribution of the notches, the present invention categorizes wafer notches into irregular notches, notches at chamfered corners, notches at chamfered edges, and notches at straight edges. Notch detection is performed using methods tailored to the characteristics of each notch.

[0199] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for visually inspecting solar silicon wafer fragments by layer and region, characterized in that: The following steps are involved: S1, using backlighting method, using industrial camera to collect solar silicon wafer image, and obtain original image I; S2, irregular fragment detection: Binarize the original image I to obtain image I1, and use the area difference between the effective contour and the minimum bounding rectangle of image I1 to determine whether it is an irregular fragment, where the effective contour is the contour with the largest area among all contours; S3, chamfer point notch detection; crop the chamfer area of ​​image 1 to obtain four chamfer images of the silicon wafer, perform coordinate transformation on the effective contour in the chamfer, calculate the width of the coordinate points in the effective contour to obtain chamfer point 1 and chamfer point 2, traverse all coordinate points in the effective contour and calculate the x-axis coordinate difference and y-axis coordinate difference between the current point and its adjacent points, and then obtain the sum of the x-axis coordinate difference and the y-axis coordinate difference of the current point PDiff i , via PDiff i Determine the abnormal points by taking values; classify and filter the abnormal points according to the rules to obtain the abnormal points in the x-direction and the abnormal points in the y-direction; traverse all the abnormal points and determine whether there is a continuous gradient abnormality at the chamfer point based on the coordinate difference of adjacent abnormal points. If so, there is a gap at the chamfer point; calculate the area of ​​the effective contour. If the area of ​​the effective contour is greater than the area threshold, it is determined that there is an abnormal gap in the area of ​​the silicon wafer chamfer point; S4, chamfer edge gap detection: perform 2x super-resolution and binarization on each of the four chamfer images, perform coordinate transformation on the effective contours in the processed chamfer images, traverse all coordinate points of the effective contours after coordinate transformation and calculate the x-coordinate difference and y-coordinate difference between the current point and its adjacent points, and obtain the sum of the differences. Determine the abnormal point according to the rules based on the value of the sum of the differences, and finally determine whether there is a gap at the chamfer edge of the silicon wafer based on the coordinate difference between adjacent positive and negative abnormal points; S5, straight edge gap detection; crop image I, and perform 2x super-resolution and high grayscale binarization with a binarization threshold of 150 to obtain four straight edge images of the silicon wafer, traverse the valid contours in the straight edge images, calculate the x-direction difference or y-direction difference between the current coordinate point and its adjacent coordinates, then obtain the abnormal points according to the rules based on the values ​​of the x-direction difference or y-direction difference, and finally determine whether the silicon wafer has a left straight edge gap or an upper straight edge gap based on the coordinate difference of adjacent positive and negative abnormal points.

2. The method for visually inspecting solar silicon wafer fragments by layer and region according to claim 1, characterized in that: The specific process of irregular fragment detection in step S2 is as follows: S2-1, performing a binarization operation on the original image I to obtain image I1; S2-2, find and traverse all contours in image I1, and obtain the valid contour Contour and its minimum circumscribed rectangle Contour_rect; S2-3. Calculate the area difference between Contour_rect and Contour using formula (1): Area_diff=Contour_rect_area-Contour_area (1) Among them, Contour_rect_area and Contour_area are the areas of Contour_rect and Contour respectively; S2-4. If Area_diff satisfies formula (2), that is, the difference between the minimum circumscribed rectangle area of ​​the solar cell and its outline area is too large, it is considered that there are irregular fragments in the solar silicon wafer; Area_diff>200000 (2) S2-5. If it is determined in step S2-4 that irregular fragments exist on the solar wafer, the text "damagedslice!" is output on the image I.

3. The method for visually inspecting solar silicon wafer fragments by layer and region according to claim 2, characterized in that: The specific process of chamfer point notch detection in step S3 is as follows: S3-1. Cropping and binarizing the lower right, upper right, lower left, and upper left corners of image I, respectively, to obtain image CP1 of the lower right chamfer, image CP2 of the upper right chamfer, image CP3 of the lower left chamfer, and image CP4 of the upper left chamfer of the solar silicon wafer. The length and width of the cropped areas are both 300. S3-2, find and traverse all contours in CP1 to obtain the valid contour ChamferP1; S3-3, traverse the coordinate points on ChamferP1 and transform the coordinate points according to formula (3) and formula (4); ChamferP 1,X,i =ChamferP 1,x,i +(w-300) (3) ChamferP 1,Y,i =ChamferP 1,y,i +(h-300) (4) Among them, ChamferP 1,x,i is the x-coordinate of the traversed point, ChamferP 1,y,i is the y coordinate of the traversed point, ChamferP 1,X,i and ChamferP 1,Y,i are the x- and y-coordinates of the point after coordinate conversion, w is the width of image I, and h is the height of image I; S3-4, perform the operation of step S3-2 on CP2, CP3 and CP4 respectively to obtain the effective contours ChamferP2, ChamferP3 and ChamferP4. In step S3-3, for the points in ChamferP2, only coordinate transformation needs to be performed according to formula (3); for the points in ChamferP3, coordinate transformation needs to be performed according to formula (4); and for the points in ChamferP4, no coordinate transformation is required; S3-5, traverse the coordinate points after coordinate transformation in ChamferP1, and calculate the coordinate difference between two adjacent coordinate points according to formula (5): Among them, X_diff i Indicates the difference between two adjacent coordinate points in the x direction, Y_diff i Indicates the difference between two adjacent coordinate points in the y direction; S3-6, traverse the coordinate points in ChamferP1 and calculate the x-width Width_x of the current point according to formula (6) i , and calculate the average value Sumwidth_x of the x-direction width of the current point and the sum of the x-direction widths of the 20 points after the current point according to formula (7) i Finally, the difference ΔWidthx is calculated according to formula (8) i , if the difference satisfies formula (9), this point is the chamfer point Coner1 on the lower left of ChamferP1; Width_x i =|ChamferP 1,X,i -300| (6) ΔWidthx i =Widh_x i -Sumwidth_x i (8) ΔWidthx i <0.3 (9) S3-7, the principle is the same as step S3-5, traverse the coordinate points in the contour ChamferP1 and calculate the y-axis width of the current traversed point to obtain the chamfer point Coner2 on the upper right of ChamferP1; S3-8, in the contour ChamferP1, traverse each X_diff obtained by formula (5) i and Y_diff i , and calculate PDiff according to formula (10) i : PDiff i =|X_diff i |+|Y_diff i | (10) According to the calculation results, PDiff i The value is 1 or 2; S3-9, starting from PDiff5, traverse the PDiff obtained in step S3-8 in sequence i , according to rules a and b, determine whether there are abnormal points at the chamfer point: Rule a: PDiff i-3 PDiff i-2 PDiff i-1 PDiff i PDiff i+1 PDiff i+2 PDiff i+3 There is a value equal to 1 in Rule b: PDiff i-4 PDiff i-3 PDiff i-2 PDiff i-1 PDiff i+1 PDiff i+2 PDiff i+3 There is a value equal to 1 in When the traversed PDiff i When any of the above rules are met, an outlier is obtained. i ; S3-10, Outlier i It is attributed to the chamfer points Coner1 and Coner2, and then the outlier point X_Outlier in the x direction is obtained. i and the outlier point in the y direction Y_Outlier i ; S3-11, traverse X_Outlier separately i and Y_Outlier i , and calculate the difference ΔX_Outlier according to formula (11) and formula (12) i and ΔY_Outlier i : ΔX_Outlier i =|X_Outlier x,i -X_Outlier x,i-1 | (11) ΔY_Outlier i =|Y_Outlier y,i -Y_Outlier y,i-1 | (12) Among them, X_Outlier x,i X_Outlier i x coordinate, Y_Outlier y,i Y_Outlier i The y coordinate of ΔX_Outlier i or ΔY_Outlier i If it is less than 3, then the X_Outlier i and Y_Outlier i Keep it as an outlier, otherwise remove it from the outlier set. After the traversal is completed, the outlier points X_Outlier in the x and y directions can be obtained again. i and Y_Outlier i ; S3-12, detect the abnormal gap of continuous gradient at chamfer point; traverse the X-direction abnormal point X_Outlier i , calculate the difference between adjacent outliers according to formula (11), if there are two consecutive ΔX_outlier i If it is greater than 1, it is determined that there is a continuous abnormal gradient gap at the chamfer point. For the y-direction chamfer point, traverse the y-direction abnormal point Y_Outlier i , calculate the difference between adjacent outliers according to formula (12), if there are two consecutive ΔY_outlier i If it is greater than 1, it is determined that there is a continuous abnormal gradient gap at the chamfer point; S3-13, calculate the contour ChamferP1 area C_area by formula (13); If the value of C_area satisfies formula (14), it is determined that there is an abnormal gap in the chamfer area of ​​the solar silicon wafer; C_area>15 (14) S3-14, performing steps S3-5 to S3-13 on the contours ChamferP2, ChamferP3, and ChamferP4 to determine whether there are abnormal area gaps and abnormal continuous gradient gaps at the chamfer points; S3-15. If a gap is detected in the above step, the gap position is framed in the image.

4. The method for visually inspecting solar silicon wafer fragments by layer and region according to claim 3, characterized in that: The specific process of the S4 chamfer edge notch detection is as follows: S4-1, perform 2x super-resolution and binarization on CP1, CP2, CP3, and CP4, respectively, to obtain a lower right chamfer image CE1, an upper right chamfer image CE2, a lower left chamfer image CE3, and an upper left chamfer image CE4; S4-2, find all contours in CE1; traverse all contours and find the valid contour ChamferEdge1, and perform the same operation on CE2, CE3 and CE4 to obtain the valid contours ChamferEdge2, ChamferEdge3 and ChamferEdge4 respectively; S4-3, similar to the principles of steps S3-3 and S3-4, perform corresponding coordinate transformation on ChamferEdge1, ChamferEdge2, ChamferEdge3 and ChamferEdge4; S4-4, traverse the coordinate points after coordinate transformation in the contour ChamferEdge1, and calculate the x and y coordinate differences between two adjacent coordinate points according to formula (15): Among them, ChamferEdge 1,x,i The x coordinate of the point after coordinate transformation on ChamferEdge1, ChamferEdge 1,y,i The y coordinate of the point after coordinate transformation on ChamferEdge1, Cx_diff i Indicates the difference between adjacent coordinate points in the x direction, Cy_diff i Indicates the difference between adjacent coordinate points in the y direction; S4-5, traverse each Cx_diff obtained in step S4-4 i and Cy_diff i , and calculate EDiff according to formula (16) i : EDiff i =|Cx_diff i |+|Cy_diff i | (16) According to the calculation results, EDiff i The value is 1 or 2; S4-6, starting from EDiff5, traverse the EDiff obtained in step S4-5 in sequence i , and judge the abnormal points according to rules c and d: Rule c: EDiff i-3 EDiff i-2 EDiff i-1 EDiff i EDiff i+1 EDiff i+2 EDiff i+3 There is a value equal to 1 in Rule d: EDiff i-4 EDiff i-3 EDiff i-2 EDiff i-1 EDiff i+1 EDiff i+2 EDiff i+3 There is a value equal to 1 in When rule c or rule d is met, the anomaly point is obtained. i , Anomaly x,i Anomaly i x-coordinate of Anomaly y,i Anomaly i The y coordinate of S4-7, Traversing the Anomaly i , marked Anomaly x,i Not equal to 0, Anomaly y,i Anomalies equal to 0 are positive anomalies and are marked as Anomaly. y,i Not equal to 0, Anomaly x,i The outlier point equal to 0 is a negative outlier point. If there is a negative outlier point, search counterclockwise to see if there is a positive outlier point. If so, calculate the coordinate difference between the two outlier points according to formula (17), and judge whether the chamfer edge concave meets the detection condition according to formula (18): Here, τ a is the detection threshold, the threshold is 20, if it satisfies formula (18), it is judged that there is a concave notch at the chamfered edge of the solar cell; S4-8, for the points in the contours ChamferEdge2, ChamferEdge3 and ChamferEdge4, it is only necessary to repeat the process of steps S4-4 to S4-7 to determine whether there is a concave notch at the upper left chamfer edge of the solar silicon wafer; for the contours ChamferEdge2 and ChamferEdge3, if there is a positive abnormal point, then search counterclockwise to see whether there is a negative abnormal point. If so, then further determine the coordinate difference between the two abnormal points according to formula (17). If the coordinate difference satisfies formula (18), it is determined that there is a concave notch on the chamfer edge. S4-9. If a gap is detected in the above steps, the gap position is framed in the image.

5. The method for visually inspecting solar silicon wafer fragments by layer and region according to claim 4, characterized in that: The specific process of the straight edge gap detection in step S5 is as follows: S5-1. Cropping image I based on the chamfer points obtained in the previous step, and performing a 2x super-resolution and high-grayscale binarization with a binarization threshold of 150 on the cropped image to obtain images e1, e2, e3, and e4 representing the left straight edge, right straight edge, top straight edge, and bottom straight edge of the solar cell, respectively. S5-2, traverse all contours in each image in images e1, e2, e3 and e4, and then find the valid contours in each image, which are Edge1, Edge2, Edge3 and Edge4 respectively; S5-3, traverse the points in Edge1 and calculate the difference between adjacent coordinates in the x direction Ex_diff according to formula (19) i : Ex_diff i =Edge 1,x,i+1 -Edge 1,x,i (19) Here, Edge 1,x,i is the x coordinate of the midpoint of the traversed contour Edge1, Edge 1,x,i+1 For Edge 1,x,i x coordinates of adjacent points; when Ex_diff i If it is not 0, search counterclockwise for the first non-0 Ex_diff within a distance of 5. i If both are positive, the point is a positive outlier. If both are negative, the point is a negative outlier. If they do not exist or the positive and negative values ​​are opposite, the point is a normal point. The contour points that meet the abnormal conditions are recorded as outliers. i ; S5-4. Traverse the outlier point Exoutlier i , set the search distance threshold τ s is 30, if Exoutlier i For a positive outlier, search the distance τ counterclockwise s Is there a negative outlier in the equation? If so, calculate the length ΔEy between the two outliers according to formula (20): ΔEy=Exoutlier y,i+n -Exoutlier y,i (20) ΔEy<τ e (21) Among them, Exoutlier y,i Exoutlier i y coordinate of Exoutlier y,i+n Negative outlier point Exoutlier i+n The y coordinate of e is the detection threshold, which is set to 20. If ΔEy satisfies formula (21), it is determined that there is a left straight edge damage gap in the solar silicon wafer; S5-5, performing steps S5-3 to S5-4 on the outline Edge2 to determine whether there is a broken notch on the right straight edge of the solar silicon wafer; S5-6, traverse the points in the contour Edge3, and calculate the difference Ey_diff between adjacent coordinates in the y direction according to formula (22) i : Ey_diff i =Edge 3,y,i+1 -Edge 3,y,i (22) Among them, Edge 3,y,i is the y coordinate of the point in the contour Edge3, Edge 3,y,i+1 For Edge 3,y,i The y coordinates of adjacent points, when the Ey_diff of the i-th contour point i If it is not 0, search counterclockwise for the first non-zero Ey_diff within a distance of 5. i If both are positive, the point is a positive outlier; if both are negative, the point is a negative outlier; if they do not exist or the positive and negative values ​​are opposite, the point is a normal point. The contour points that meet the abnormal conditions are recorded as outliers. i ; S5-7, traversing outlier points Eyoutlier i , if Eyoutlier i If it is a negative outlier, search the distance τ counterclockwise. s Is there a positive outlier in the image? If so, calculate the length ΔEx between the two outliers according to formula (23): ΔEx=Eyoutlier x,i+n -Eyoutlier x,i (23) ΔEx<τ e (24) Here, Eyoutlier x,i For Eyoutlier i x coordinate, Eyoutlier x,i+n is a positive outlier point Eyoutlier i+n If ΔEx satisfies formula (24), it is determined that there is a straight edge damage gap on the solar silicon wafer; S5-8, performing steps S5-6 to S5-7 for the outline Edge4 to determine whether there is a broken gap on the lower straight edge of the solar cell; S5-9. Crop image I according to the chamfer points obtained in the previous step, perform 2x super-resolution and low-grayscale binarization with a binarization threshold of 40 on the cropped image, to obtain images e5, e6, e7, and e8. Perform steps S5-3 to S5-8 on images e5, e6, e7, and e8 to determine whether there are any broken or notched edges on the straight edges of the solar cell. S5-10: If a gap is detected in the above steps, the gap position is framed in the image.

Images