A substrate cutting method and system

Abstract

The application provides a substrate cutting method and system, the substrate cutting method comprises the following steps: S1, image acquisition is performed on a substrate to be cut to obtain a first image, and a first image coordinate of a calibration point on the first image is obtained; S2, feature extraction is performed on a substrate image to obtain a preset cutting path, second image coordinates of a plurality of feature points and third image coordinates of a reference point are obtained respectively, and each second image coordinate is added to a theoretical coordinate set; S3, a first calibration quantity is obtained by processing the first image coordinate and the third image coordinate, and each second image coordinate in the theoretical coordinate set is calibrated to obtain a calibration coordinate set according to the first calibration quantity; S4, an actual cutting path is obtained by processing the calibration coordinate set; and a cutting device cuts the substrate to be cut according to an execution instruction and the actual cutting path. The beneficial effect is to improve the cutting efficiency of the substrate to be cut and the quality identification efficiency of the cut substrate.

Description

Technical Field

[0001] This invention relates to the technical field of image analysis, and more particularly to a substrate cutting method and system. Background Technology

[0002] Currently, in the manufacturing process of liquid crystal display devices, it is necessary to cut the substrate used to drive the liquid crystal display device along a preset cutting path so that the size of the substrate meets the assembly requirements.

[0003] Before substrate cutting, the user needs to manually control the cutting device to cut one substrate to generate a cutting path. After cutting, the user also needs to manually determine whether the cut substrate meets the product standard. When the cut substrate meets the product standard, the corresponding cutting path is saved as a standard path for the cutting device to batch cut other substrates based on the standard path. When the cut substrate does not meet the product standard, the user needs to adjust the cutting path until the substrate meets the product standard. For substrates with different cutting paths, the user needs to manually control the cutting device to cut different substrates to obtain a standard path, which results in low substrate cutting efficiency.

[0004] In addition, manual judgment of whether the cut substrate meets the product standards is prone to misjudgment, which is not conducive to manufacturers controlling the cutting quality of the substrate. Summary of the Invention

[0005] To address the problems existing in the prior art, the present invention provides a substrate cutting method for automatically cutting a substrate to be cut according to a substrate drawing image. The substrate to be cut has a calibration point, and the substrate drawing image includes a reference point corresponding to the calibration point and a preset cutting path.

[0006] The substrate cutting includes:

[0007] Step S1: Acquire an image of the substrate to be cut to obtain a first image containing the calibration point, and obtain the first image coordinates of the calibration point on the first image;

[0008] Step S2: Extract features from the substrate drawing image to obtain the preset cutting path, obtain the second image coordinates of multiple feature points forming the preset cutting path in the substrate drawing image and the third image coordinates of the reference point in the substrate drawing image, and add each of the second image coordinates to a theoretical coordinate set.

[0009] Step S3: Based on the first image coordinates and the third image coordinates, a first calibration value is obtained between the calibration point and the reference point. Based on the first calibration value, each of the second image coordinates in the theoretical coordinate set is calibrated to obtain a calibration coordinate set.

[0010] Step S4: Obtain an actual cutting path based on the calibration coordinate set;

[0011] A cutting device cuts the substrate to be cut according to an externally input execution command and the actual cutting path.

[0012] Preferably, step S3 further includes:

[0013] Step S31: Calculate the coordinate difference between the first image coordinates and the third image coordinates as the first calibration value;

[0014] Step S32: Based on the first calibration amount, each of the second image coordinates in the theoretical coordinate set is calibrated to generate the calibration coordinate set, and then step S4 is executed.

[0015] Preferably, the cutting device includes an encoder, a servo motor connected to the encoder, and a blade driven by the servo motor;

[0016] In step S4, the encoder converts each of the second image coordinates in the calibration coordinate set into a corresponding pulse signal, and the servo motor controls the blade to cut the substrate to be cut along the actual cutting path according to the pulse signal.

[0017] Preferably, if the cutting device cuts the substrate to be cut according to the actual cutting path to obtain a cut substrate, then after executing step S4, a quality identification process is further included, including:

[0018] Step A1: Image acquisition is performed on the cut substrate to obtain a second image;

[0019] Step A2: Determine whether the cut substrate meets a preset cutting standard based on the second image;

[0020] If so, the cut substrate is output as a qualified product, and then the process proceeds to step S4.

[0021] If not, a manual quality inspection is performed on the cut substrate, and then proceed to step S4;

[0022] The manual quality inspection determines whether the cut substrate meets a preset quality inspection standard;

[0023] If so, the cut substrate is output as the qualified product;

[0024] If not, the cut substrate is output as a defective product.

[0025] Preferably, the cut substrate has cut edges formed by the cutting device, and the second image includes all the cut edges, then step A2 includes:

[0026] Step A21: Perform feature extraction on the second image to obtain edge image information of each of the cutting edges;

[0027] Step A22: Based on the edge image information, process to obtain the deviation between each cutting edge in the edge image information and the actual cutting path;

[0028] Step A23: Determine whether each of the aforementioned deviations is within a preset specification range;

[0029] If so, output the result that the cut substrate meets the cutting standard. Based on the result that the cut substrate meets the cutting standard, the cut substrate is the qualified product, and then proceed to step S4.

[0030] If not, output the result that the cut substrate does not meet the cutting standard. Based on the result that the cut substrate does not meet the cutting standard, perform the manual quality inspection on the cut substrate, and then proceed to step S4.

[0031] Preferably, step A21 includes:

[0032] Step A211: Obtain a preprocessed image based on the second image preprocessing;

[0033] Step A212: Obtain the edge image information by performing edge recognition based on the preprocessed image.

[0034] Preferably, a substrate cutting system is also provided, which applies the substrate cutting method described in any one of the above claims, the substrate cutting system comprising:

[0035] The first processing module is used to acquire an image of the substrate to be cut, obtain a first image containing the calibration point, and obtain the first image coordinates of the calibration point on the first image;

[0036] The second processing module, connected to the first processing module, is used to extract features from the substrate drawing image to obtain the preset cutting path, and to obtain the second image coordinates of multiple feature points forming the preset cutting path in the substrate drawing image and the third image coordinates of the reference point in the substrate drawing image, and to add each of the second image coordinates to a theoretical coordinate set.

[0037] The calibration module, connected to the second processing module, is used to process the first image coordinates and the third image coordinates to obtain a first calibration value between the calibration point and the reference point, and to calibrate each of the second image coordinates in the theoretical coordinate set according to the first calibration value to obtain a calibration coordinate set.

[0038] The third processing module, connected to the calibration module, is used to process the calibration coordinate set to obtain an actual cutting path.

[0039] A cutting device, connected to the third processing module, is used to cut the substrate to be cut according to an externally input execution command and the actual cutting path.

[0040] Preferably, the substrate cutting system further includes a quality identification module connected to the third processing module, the quality identification module comprising:

[0041] The acquisition unit is used to acquire an image of the cut substrate to obtain a second image.

[0042] The judgment unit, connected to the acquisition unit, is used to perform a manual quality inspection on the cut substrate when the second image indicates that the cut substrate does not meet a preset cutting standard.

[0043] If the result of the manual quality inspection indicates that the cut substrate meets a preset quality inspection standard, then the cut substrate is output as a qualified product.

[0044] If the result of the manual quality inspection indicates that the cut substrate does not meet the quality inspection standard, then the cut substrate will be output as a defective product.

[0045] The above technical solution has the following advantages or beneficial effects:

[0046] (1) By performing feature recognition on the substrate drawing image to obtain the preset cutting path, before the cutting device cuts the substrate to be cut, it is only necessary to adjust the preset cutting path according to the calibration amount to obtain the actual cutting path. On the one hand, it reduces the workload of users to manually set each feature point in the actual cutting path and improves the cutting efficiency of the substrate. On the other hand, the theoretical coordinate set can be obtained by automatically correcting each second image coordinate in the theoretical coordinate set according to the calibration amount, which reduces the situation where users modify each coordinate in the theoretical coordinate set one by one and improves the correction efficiency.

[0047] (2) By analyzing the deviation between each cutting edge in the second image and the actual cutting path, it is determined whether the substrate after cutting meets the cutting standard. When the substrate after cutting does not meet the cutting standard, manual quality inspection is carried out on the substrate after cutting to make further quality judgment, thereby improving the efficiency of quality identification of the substrate after cutting.

[0048] (3) By converting each second image coordinate in the calibration coordinate set into a corresponding pulse signal, the cutting device is controlled to cut the substrate to be cut along the actual cutting path. Compared with the user manually setting the cutting path, the accuracy of the cutting operation is improved and the probability of the substrate to be cut being damaged due to deviations in the manually set cutting path is reduced. Attached Figure Description

[0049] Figure 1 A flowchart of a substrate cutting method is provided in a preferred embodiment of the present invention.

[0050] Figure 2 The following is a flowchart of step S3 in a preferred embodiment of the present invention;

[0051] Figure 3 A flowchart illustrating the quality identification process in a preferred embodiment of the present invention;

[0052] Figure 4 The following is a flowchart of step A3 in a preferred embodiment of the present invention;

[0053] Figure 5 The following is a flowchart of step A21 in a preferred embodiment of the present invention;

[0054] Figure 6 This is a control principle diagram of the substrate cutting system in a preferred embodiment of the present invention. Detailed Implementation

[0055] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. The present invention is not limited to this embodiment; other embodiments that conform to the spirit of the present invention may also fall within the scope of the present invention.

[0056] In a preferred embodiment of the present invention, based on the above-mentioned problems existing in the prior art, a substrate cutting method is provided, such as... Figure 1 As shown, it is used to automatically cut a substrate to be cut according to a substrate drawing image. The substrate to be cut has a calibration point, and the substrate drawing image contains a reference point corresponding to the calibration point and a preset cutting path.

[0057] The substrate cutting includes:

[0058] Step S1: Acquire an image of the substrate to be cut to obtain a first image containing calibration points, and obtain the first image coordinates of the calibration points on the first image;

[0059] Step S2: Extract features from the substrate drawing image to obtain a preset cutting path, obtain the second image coordinates of multiple feature points forming the preset cutting path in the substrate drawing image and the third image coordinates of the reference point in the substrate drawing image, and add each second image coordinate to a theoretical coordinate set.

[0060] Step S3: Based on the first image coordinates and the third image coordinates, a first calibration value between the calibration point and the reference point is obtained, and the second image coordinates in the theoretical coordinate set are calibrated according to the first calibration value to obtain a calibration coordinate set.

[0061] Step S4: Obtain an actual cutting path based on the calibration coordinate set;

[0062] A cutting device cuts the substrate to be cut according to an externally input execution command and the actual cutting path.

[0063] Specifically, in this embodiment, the substrate drawing includes multiple outline lines and multiple cutting lines. By reading the substrate drawing, a substrate drawing image is obtained. Then, feature recognition is performed on the substrate drawing image to obtain a preset cutting path containing each cutting line.

[0064] In one embodiment, the multiple feature points forming the preset cutting path include, but are not limited to: the starting point of the preset cutting path, the ending point of the preset cutting path, and at least one turning point indicating that the cutting line turns.

[0065] Compared with manually set cutting paths, the actual cutting path obtained by this substrate cutting method is more accurate, reducing the probability of deviations in the actual cutting path due to human judgment.

[0066] In a preferred embodiment of the present invention, such as Figure 2 As shown, step S3 further includes:

[0067] Step S31: Calculate the coordinate difference between the first image coordinates and the third image coordinates as the first calibration value;

[0068] Step S32: Based on the first calibration value, each second image coordinate in the theoretical coordinate set is calibrated to generate a calibration coordinate set, and then step S4 is executed.

[0069] Specifically, in this embodiment, in step S31, the calibration values ​​of the second image coordinates in the directions of each coordinate axis are obtained according to the coordinate difference processing, and each second image coordinate is calibrated according to each calibration value to obtain the corresponding calibrated coordinates, and each calibrated coordinate is added to the calibration coordinate set.

[0070] In a preferred embodiment of the present invention, the cutting device includes an encoder, a servo motor connected to the encoder, and a blade driven by the servo motor.

[0071] In step S4, the encoder converts each second image coordinate in the calibration coordinate set into a corresponding pulse signal, and the servo motor controls the blade to cut the substrate along the actual cutting path according to the pulse signal.

[0072] In a preferred embodiment of the present invention, the cutting device cuts the substrate to be cut according to the actual cutting path to obtain a cut substrate. After step S4, a quality identification process is further included, such as... Figure 3 As shown, it includes:

[0073] Step A1: Acquire an image of the cut substrate to obtain a second image;

[0074] Step A2: Determine whether the cut substrate meets the preset cutting standard based on the second image;

[0075] If so, the cut substrate is a qualified product, and then proceed to step S4;

[0076] If not, perform a manual quality inspection on the cut substrate, and then proceed to step S4;

[0077] Manual quality inspection is used to determine whether the cut substrate meets a preset quality inspection standard.

[0078] If so, the cut substrate will be output as a qualified product;

[0079] If not, the cut substrate will be output as a defective product.

[0080] Specifically, in this embodiment, after the substrate to be cut is completed, quality identification is required. The image recognition method is used to automatically determine whether the cut substrate meets the cutting standard. If the cut substrate does not meet the cutting standard, it will be subject to manual quality inspection to reduce the probability of substandard substrates flowing out of the production line after cutting and improve the quality inspection efficiency of the cut substrate.

[0081] In a preferred embodiment of the present invention, the cut substrate has cut edges formed by the cutting device, and the second image includes all cut edges, such as... Figure 4 As shown, step A2 includes:

[0082] Step A21: Perform feature extraction on the second image to obtain edge image information of each cutting edge;

[0083] Step A22: Based on the edge image information, the deviation between each cutting edge in the edge image information and the actual cutting path is obtained;

[0084] Step A23: Determine whether each deviation is within a preset specification range;

[0085] If so, the output shows that the cut substrate meets the cutting standard. Based on the result that the cut substrate meets the cutting standard, the cut substrate is output as a qualified product, and then the process proceeds to step S4.

[0086] If not, output the result that the cut substrate does not meet the cutting standard. Based on the result that the cut substrate does not meet the cutting standard, perform manual quality inspection on the cut substrate, and then proceed to step S4.

[0087] Specifically, in this embodiment, an imaging device is used to acquire images of the cut substrate to obtain various second images. Since the imaging device has a limited acquisition range, multiple image acquisitions are required to ensure the clarity of the acquired images.

[0088] In another embodiment, the camera device acquires images at each feature point along the actual cutting path.

[0089] For a cut substrate, each time the camera captures a second image, it calculates the deviation between the cut edge in the second image and the actual cut path.

[0090] If the cutting edge in the second image is within a preset specification range, the corresponding cutting edge marking result is qualified; if the cutting edge in the second image is not within the preset specification range, the corresponding cutting edge marking result is unqualified.

[0091] The camera moves to the next feature point and captures a second image containing the cutting edge corresponding to the next feature point. The above action of marking the cutting edge is repeated until the camera has captured and marked the second images corresponding to all feature points. Then, all the second images and their corresponding marking results are output as comparison results.

[0092] When all marking results are qualified, it means that the cut substrate meets the cutting standard; when there is a marking that is unqualified, it means that the cut substrate does not meet the standard. The user needs to manually determine whether the unqualified substrate can be accepted in order to decide whether the cut substrate can proceed to the next process.

[0093] In another embodiment, the process of calculating the deviation of the cutting edge is as follows:

[0094] First, the coordinates of each edge contained in the cutting edge are obtained by processing the edge image information. At least two consecutive edge coordinates form a feature line segment. The feature slope of the feature line segment and the set slope corresponding to the set line segment at the feature point of the actual cutting path in the image acquisition are calculated. The feature slope is compared with the set slope. If the error between each feature slope and the set slope is within the specification range, the cutting edge in the second image meets the cutting standard. If the error between the feature slope and the set slope is not within the specification range, the cutting edge in the second image does not meet the cutting standard.

[0095] In another embodiment, in the planar coordinate system corresponding to the edge image information, with the X-axis as the reference, two first endpoints are selected at both ends of a set line segment, and two second endpoints with the same X-coordinate values ​​as the two first endpoints are selected from the feature line segment. For the same X-coordinate value, the difference between the Y-coordinate value of the first endpoint and the Y-coordinate value of the second endpoint is compared. If all differences are within the specified range, the cutting edge in the second image meets the cutting standard; if there is a difference that is not within the specified range, the cutting edge in the second image does not meet the cutting standard.

[0096] In another embodiment, in the planar coordinate system corresponding to the edge image information, with the Y-axis as the reference, two first endpoints are selected at both ends of a set line segment, and two second endpoints with the same Y-coordinate values ​​as the two first endpoints are selected from the feature line segment. For the same Y-coordinate value, the difference between the X-coordinate value of the first endpoint and the X-coordinate value of the second endpoint is compared. If all differences are within the specified range, the cutting edge in the second image meets the cutting standard; if there is a difference that is not within the specified range, the cutting edge in the second image does not meet the cutting standard.

[0097] In a preferred embodiment of the present invention, such as Figure 5 As shown, step A21 includes:

[0098] Step A211: Obtain a preprocessed image based on the second image preprocessing;

[0099] Step A212: Edge image information is obtained by performing edge recognition based on the preprocessed image.

[0100] Specifically, in this embodiment, step A211 includes:

[0101] First, the second image is binarized to obtain a first image;

[0102] Next, the image is mapped onto a coordinate system, and the derivative of the image along the X-axis of the coordinate system is taken to obtain A. 2x Taking the derivative of the first-order graph along the Y-axis of the coordinate system yields A. 2y ;

[0103] Then, A 2x and A 2y A is obtained by superposition. 2xy and A 2xy Centralized processing is implemented;

[0104] Next, the centralized A 2xy The input is fed into a pre-trained first model, and the first model outputs a sensitive area processing region R.

[0105] In step A212, edge recognition is performed on the sensitive area processing region R to obtain the edge image information corresponding to the cutting edge.

[0106] Before training the first model, a training database needs to be established. This database includes each historical second image and local images containing cutting edges from those historical second images. During training, the historical second images are used as input to the first model, and the local images containing cutting edges are used as its output. The local images containing cutting edges represent the sensitive processing region R.

[0107] In a preferred embodiment of the present invention, a substrate cutting system is also provided, employing any of the substrate cutting methods described above, such as... Figure 6 As shown, the substrate cutting system includes:

[0108] The first processing module 1 is used to acquire images of the substrate to be cut, obtain a first image containing calibration points, and acquire the first image coordinates of the calibration points on the first image.

[0109] The second processing module 2 is connected to the first processing module 1 and is used to extract features from the substrate drawing image to obtain a preset cutting path. It obtains the second image coordinates of multiple feature points forming the preset cutting path in the substrate drawing image and the third image coordinates of the reference point in the substrate drawing image, and adds each second image coordinate to a theoretical coordinate set.

[0110] The calibration module 3 is connected to the second processing module 2 and is used to process the first image coordinates and the third image coordinates to obtain a first calibration value between the calibration point and the reference point, and to calibrate each second image coordinate in the theoretical coordinate set according to the first calibration value to obtain a calibration coordinate set.

[0111] The third processing module 4 is connected to the calibration module 3 and is used to process the calibration coordinate set to obtain an actual cutting path.

[0112] The cutting device 5 is connected to the third processing module 4 and is used to cut the substrate to be cut according to an externally input execution command and the actual cutting path.

[0113] In a preferred embodiment of the present invention, the substrate cutting system further includes a quality identification module 6 connected to the third processing module 4. The quality identification module 6 includes:

[0114] Acquisition unit 61 is used to acquire images of the cut substrate to obtain a second image;

[0115] The judgment unit 62 is connected to the acquisition unit 61 and is used to perform a manual quality inspection on the cut substrate when the second image indicates that the cut substrate does not meet a preset cutting standard.

[0116] If the results of manual quality inspection indicate that the cut substrate meets a preset quality inspection standard, then the cut substrate is output as a qualified product.

[0117] If the results of manual quality inspection indicate that the cut substrate does not meet the quality inspection standards, then the cut substrate will be output as a defective product.

[0118] Specifically, in this embodiment, during manual quality inspection, the process by which the user manually determines whether the substrate to be cut meets the quality inspection standards is as follows:

[0119] Users review the cut substrates according to pre-specified quality inspection standards.

[0120] When the manual review results indicate that the cut substrate is a qualified product, the cut substrate is returned to a production line for further processing.

[0121] When the manual review result indicates that the cut substrate is a defective product, the cut substrate will be treated as a defective product according to the pre-set defective product handling method.

[0122] In summary, by calibrating the second image coordinates contained in the theoretical coordinate set according to the first calibration value, the workload of manually calibrating the cutting path before cutting the substrate is reduced.

[0123] After the substrate to be cut is completed, the cut edges are inspected for quality. If the cut substrate meets the cutting standards, it is a qualified product and can proceed to the next step of processing, which improves the efficiency of quality identification of the cut substrate and increases production capacity. If the cut substrate does not meet the cutting standards, it is manually inspected. If the cut substrate meets the inspection standards, it is a qualified product, which improves the reliability of quality identification.

[0124] The above description is merely a preferred embodiment of the present invention and does not limit the implementation and protection scope of the present invention. Those skilled in the art should realize that any equivalent substitutions and obvious changes made using the content of this specification and illustrations should be included within the protection scope of the present invention.

Claims

1. A substrate cutting method characterized by, The application relates to an automatic cutting method for a to-be-cut substrate based on a substrate drawing image, wherein the to-be-cut substrate is provided with a calibration point, and the substrate drawing image comprises a reference point corresponding to the calibration point and a preset cutting path. The substrate cutting comprises: Step S1: image acquisition of the to-be-cut substrate to obtain a first image comprising the calibration point and to acquire first image coordinates of the calibration point on the first image; Step S2: feature extraction of the substrate drawing image to obtain the preset cutting path, second image coordinates of a plurality of feature points forming the preset cutting path in the substrate drawing image and third image coordinates of the reference point in the substrate drawing image, and addition of each second image coordinate into a theoretical coordinate set; Step S3: processing of a first calibration amount between the calibration point and the reference point based on the first image coordinates and the third image coordinates, and calibration of each second image coordinate in the theoretical coordinate set based on the first calibration amount to obtain a calibration coordinate set; Step S4: processing of an actual cutting path based on the calibration coordinate set; The cutting device cuts the to-be-cut substrate based on an execution instruction input from outside and the actual cutting path.

2. The substrate cutting method according to claim 1, wherein The step S3 further comprises: Step S31: calculation of a coordinate difference value between the first image coordinates and the third image coordinates as the first calibration amount; Step S32: calibration of each second image coordinate in the theoretical coordinate set based on the first calibration amount to generate the calibration coordinate set, and subsequent execution of the step S4.

3. The substrate cutting method according to claim 1, wherein The cutting device comprises an encoder, a servo motor connected to the encoder and a blade driven by the servo motor. In the step S4, the encoder converts each second image coordinate in the calibration coordinate set into a corresponding pulse signal, and the servo motor controls the blade to cut the to-be-cut substrate along the actual cutting path based on the pulse signal.

4. The substrate cutting method according to claim 1, wherein The cutting device cuts the to-be-cut substrate based on the actual cutting path to obtain a cut substrate, and after the step S4, a quality identification process is further included, which comprises: Step A1: image acquisition of the cut substrate to obtain a second image; Step A2: judgment of whether the cut substrate meets a preset cutting standard based on the second image; If yes, the cut substrate is output as a qualified product, and then the step S4 is returned to; If no, an artificial quality inspection is performed on the cut substrate, and then the step S4 is returned to; The artificial quality inspection judges whether the cut substrate meets a preset quality inspection standard; If yes, the cut substrate is the qualified product; If no, the cut substrate is an unqualified product.

5. The substrate cutting method according to claim 4, wherein The cut substrate has a plurality of cutting edges formed after being cut by the cutting device, and the second image comprises all the cutting edges, and the step A2 comprises: Step A21: feature extraction of the second image to obtain edge image information of each cutting edge; Step A22, processing the deviation between each cutting edge in the edge image information and the actual cutting path according to the edge image information; Step A23, judging whether each deviation is within a preset specification range; If yes, outputting a result that the cut substrate meets the cutting standard, and according to the result that the cut substrate meets the cutting standard, outputting the cut substrate as a qualified product, and then turning to the step S4; If no, outputting a result that the cut substrate does not meet the cutting standard, and according to the result that the cut substrate does not meet the cutting standard, performing the artificial quality inspection on the cut substrate, and then turning to the step S4.

6. The substrate cutting method according to claim 5, wherein The step A21 comprises: Step A211, obtaining a preprocessed image according to the second image preprocessing; Step A212, performing edge recognition according to the preprocessed image to obtain the edge image information.

7. A substrate cutting system, characterized by, The substrate cutting system comprises: A first processing module, configured to perform image acquisition on the substrate to be cut to obtain a first image containing the calibration point, and acquire a first image coordinate of the calibration point on the first image; A second processing module, connected to the first processing module, configured to perform feature extraction on the substrate image to obtain the preset cutting path, acquire a second image coordinate of each feature point forming the preset cutting path in the substrate image and a third image coordinate of the reference point in the substrate image, and add each second image coordinate to a theoretical coordinate set; A calibration module, connected to the second processing module, configured to process a first calibration amount between the calibration point and the reference point according to the first image coordinate and the third image coordinate, and calibrate each second image coordinate in the theoretical coordinate set according to the first calibration amount to obtain a calibrated coordinate set; A third processing module, connected to the calibration module, configured to process an actual cutting path according to the calibrated coordinate set; A cutting device, connected to the third processing module, configured to cut the substrate to be cut according to an external input execution instruction and the actual cutting path.

8. The substrate cutting system of claim 7, wherein, The substrate cutting system further comprises a quality identification module connected to the third processing module, and the quality identification module comprises: An acquisition unit, configured to perform image acquisition on the cut substrate to obtain a second image; A judgment unit, connected to the acquisition unit, configured to perform artificial quality inspection on the cut substrate when the second image indicates that the cut substrate does not meet a preset cutting standard; The result of the artificial quality inspection indicates that the cut substrate meets a preset quality inspection standard, and the cut substrate is a qualified product; The result of the artificial quality inspection indicates that the cut substrate does not meet the quality inspection standard, and the cut substrate is an unqualified product.

Images