CN117853480A - Material correction method, equipment and storage medium based on machine vision - Google Patents

Abstract

The invention relates to the field of industrial automation, and discloses a material correction method, equipment and a storage medium based on machine vision. The method comprises the following steps: when the machine detects the material to be processed, detecting the relative coordinates of the material to be processed on the machine; according to the relative coordinates and a preset process instruction document, processing operation is carried out on the material to be processed, and the material to be rechecked is obtained; scanning the material to be rechecked to obtain a target hub; comparing the target profile with a preset profile to obtain a comparison result; judging whether the material to be rechecked is qualified or not according to the comparison result; if the material to be rechecked is unqualified, executing the generation operation of the correction coefficient according to the comparison result; and performing secondary processing operation on the material to be re-inspected according to the correction coefficient to obtain the target material. In the embodiment of the invention, the yield of material processing is improved.

Description

Material correction method, device and storage medium based on machine vision

Technical Field

The present invention relates to the field of industrial automation, and in particular to a material correction method, device and storage medium based on machine vision.

Background technique

In the manufacturing and processing industry, after the CNC technician gets the program, he clamps the raw material onto the machine, uses a centering rod to find the four sides of the raw material to determine the relative size of the raw material on the machine, and manually inputs it into the machine operation panel to complete the parameter setting.

After the product is processed, the size is measured manually. If the product is not processed in place after high-precision size measurement, the tool compensation is turned on and it is processed again. Once the product is taken off the machine, it is processed again, and the positioning and processing benchmark are repeated. The size is difficult to guarantee, and the debugging time is very long, there will be a risk of scrapping, which reduces the yield of production and processing.

Summary of the invention

The main purpose of the invention is to solve the technical problem of low yield rate in production and processing.

A first aspect of the present invention provides a material correction method based on machine vision, the material correction method based on machine vision comprising:

When the machine platform detects the material to be processed, detecting the relative coordinates of the material to be processed on the machine platform;

According to the relative coordinates and the preset process instruction document, a processing operation is performed on the material to be processed to obtain a material to be re-inspected;

Scanning the material to be re-inspected to obtain a target wheel hub;

Comparing the target contour with a preset contour to obtain a comparison result;

According to the comparison result, judging whether the material to be re-inspected is qualified;

If the material to be re-inspected is unqualified, a correction coefficient generation operation is performed according to the comparison result;

According to the correction coefficient, a secondary processing operation is performed on the material to be re-inspected to obtain a target material.

Optionally, in a first implementation of the first aspect of the present invention, the step of performing a processing operation on the material to be processed according to the relative coordinates and a preset process instruction document to obtain the material to be re-inspected includes:

Scan the material to be processed to obtain a material hub, and determine whether the material profile is symmetrical;

If the material contour is symmetrical, a processing operation is performed on the material to be processed according to the relative coordinates and a preset process instruction document to obtain a material to be re-inspected.

Optionally, in a second implementation of the first aspect of the present invention, after the step of scanning the material to be processed to obtain a material hub and determining whether the material profile is symmetrical, the step further includes:

If the material profile is asymmetrical, a prompt message is output indicating that the material to be processed needs fine-tuning.

Optionally, in a third implementation of the first aspect of the present invention, the step of performing a processing operation on the material to be processed according to the relative coordinates and a preset process instruction document to obtain the material to be re-inspected includes:

Extract processing information from process instruction documents;

According to the relative coordinates and the processing steps in the processing information, a processing tool corresponding to the processing step is called to perform a processing operation on the material to be processed to obtain the material to be re-inspected.

Optionally, in a fourth implementation of the first aspect of the present invention, if the material to be processed does not need fine-tuning, the step of performing a processing operation on the material to be processed according to the relative coordinates and a preset process instruction document to obtain the material to be re-inspected includes:

If the material to be processed does not require fine-tuning, extract processing information from the process instruction document;

According to the relative coordinates and the processing steps in the processing information, a processing tool corresponding to the processing step is called to perform a processing operation on the material to be processed to obtain the material to be re-inspected.

Optionally, in a fifth implementation manner of the first aspect of the present invention, the step of comparing the target contour with the preset contour to obtain a comparison result includes:

The contour difference between the target contour and the preset contour is calculated to obtain a comparison result.

Optionally, in a sixth implementation manner of the first aspect of the present invention, the step of calculating a contour difference between the target contour and the preset contour to obtain a comparison result includes:

Performing a 3D comparison between the target contour and the preset contour to obtain a 3D comparison result, and performing a dimensional tolerance comparison between the target contour and the preset contour to obtain a dimensional deviation;

According to the 3D comparison result and the size deviation, a difference area and a difference parameter corresponding to the difference area are calculated to obtain a contour difference, and the contour difference is used as the comparison result.

Optionally, in a seventh implementation manner of the first aspect of the present invention, before the step of calculating the difference area and the difference parameters corresponding to the difference area according to the 3D comparison result and the size deviation to obtain the contour difference, and taking the contour difference as the comparison result, the method further includes:

Performing a 3D comparison between the target contour and the preset contour to obtain a 3D comparison result, and performing a dimensional tolerance comparison between the target contour and the preset contour to obtain a dimensional deviation;

Integrate the 3D comparison result and the size deviation into prompt information and output it;

When a processing instruction in response to the prompt information is detected within a preset time, executing the processing instruction;

When no processing instruction in response to the prompt information is detected within a preset time, a step of calculating a difference area and a difference parameter corresponding to the difference area according to the 3D comparison result and the size deviation is performed.

The second aspect of the present invention provides a material correction device based on machine vision, comprising: a memory and at least one processor, wherein instructions are stored in the memory, and the memory and the at least one processor are interconnected via lines; the at least one processor calls the instructions in the memory so that the material correction device based on machine vision executes the above-mentioned material correction method based on machine vision.

A third aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned material correction method based on machine vision.

In an embodiment of the present invention, a material correction device based on machine vision automatically performs processing operations on the material to be processed according to relative coordinates and preset process instruction documents. After the processing is completed, the material is scanned using machine vision technology to obtain its target contour, and compared with the preset contour to quickly determine whether the material is qualified. For unqualified materials, a correction coefficient is automatically generated based on the comparison results, and a secondary processing operation is performed. Through the material correction method, problems can be discovered and adjusted in time during the processing process, avoiding the situation where the final product is unqualified, thereby reducing the risk of scrapping and improving the yield rate of material processing.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of an embodiment of a material correction method based on machine vision in an embodiment of the present invention;

FIG2 is a schematic diagram of a specific embodiment of step 103 of the material correction method based on machine vision in an embodiment of the present invention;

FIG3 is a schematic diagram of a specific embodiment of step 1061 of the material correction method based on machine vision in an embodiment of the present invention;

FIG4 is a schematic diagram of a specific embodiment of step 108 of the material correction method based on machine vision in an embodiment of the present invention;

FIG. 5 is a schematic diagram of an embodiment of a material correction device based on machine vision in an embodiment of the present invention.

Detailed ways

The embodiments of the present invention provide a material correction method, device and storage medium based on machine vision.

The embodiments disclosed in the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments disclosed in the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments disclosed in the present invention are only for exemplary purposes and are not intended to limit the scope of protection disclosed in the present invention.

In the description of the embodiments disclosed in the present invention, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

For ease of understanding, the specific process of an embodiment of the present invention is described below. Please refer to FIG1 . An embodiment of a material correction method based on machine vision in an embodiment of the present invention includes:

101. When a machine platform detects a material to be processed, detect the relative coordinates of the material to be processed on the machine platform;

Specifically, after the raw materials are clamped onto the working table of the equipment, the relative position of the raw materials needs to be input into the equipment before processing. This embodiment has the function of detecting the relative coordinates of the material to be processed on the machine table.

Furthermore, the material correction equipment based on machine vision scans the three-dimensional coordinate data of the raw material, and the three-dimensional coordinate data may include X, Y, and Z coordinate values, representing the point cloud data of the surface of the object. The acquired point cloud data is filtered and denoised to eliminate noise and redundant information in the data to improve the accuracy and reliability of the data.

Optionally, the material to be processed is scanned to obtain a material hub, and the material profile is compared with a preset profile to obtain similarity; a comparison algorithm, such as Euclidean distance, cosine similarity, etc., can be used to calculate the similarity between the material profile and the preset profile. It can be selected according to actual needs.

The similarity is compared with the set threshold. If the comparison result is within the threshold range, it is considered that the material to be processed needs fine-tuning; if it exceeds the threshold range, it is considered that the material to be processed needs fine-tuning.

Further, the extracted feature points are analyzed. For example, if the preset contour should have a certain feature point, but the comparison result shows that this feature point does not exist in the material contour or is located incorrectly, it can be determined that the material needs to be fine-tuned.

Furthermore, if the mark in the preset contour should be at a certain position, but the comparison result shows that the position of the mark is incorrect, it can be determined that the material needs to be fine-tuned.

Specifically, the comparison step also includes: determining whether the material contour is symmetrical; if the material contour is symmetrical, determining that the material does not need fine-tuning; if the material contour is asymmetrical, determining that the material to be processed needs fine-tuning.

Specifically, if the material to be processed needs fine-tuning, a prompt message indicating that the material to be processed needs fine-tuning is output.

102. Perform processing operations on the material to be processed according to the relative coordinates and a preset process instruction document to obtain a material to be re-inspected;

Specifically, according to the relative coordinates and the preset process instruction document, a processing technology suitable for the material to be processed is selected. The process instruction document usually provides detailed steps and parameter settings to guide the operator to perform processing correctly.

According to the selected processing technology, call the corresponding processing equipment. Make sure the equipment is in good condition, and carry out necessary debugging and calibration to ensure the accuracy and stability of processing.

Position and fix the material to be processed to ensure that the material remains stable during processing and does not move or deform. Choose the corresponding positioning and fixing method according to the characteristics of the material and processing requirements.

According to the parameter settings provided in the process instruction document, adjust the parameters of the processing equipment based on the relative position of the material to be processed in the machine. Including but not limited to cutting speed, feed rate, depth, etc., to ensure the smooth progress of the processing process. After setting the parameters, verify and calibrate to ensure the accuracy and effectiveness of the parameters.

After confirming that the material is positioned, fixed and the parameters are set correctly, start the processing process. Monitor the operating status of the processing equipment, observe the cutting situation, and promptly discover and handle abnormal situations.

After processing is completed, the material to be re-inspected is obtained.

Specifically, step 102 includes the following specific implementation methods:

1021. Extract processing information from process instruction documents;

1022. According to the relative coordinates and the processing steps in the processing information, call the processing tool corresponding to the processing step to perform a processing operation on the material to be processed to obtain the material to be re-inspected.

In steps 1021-1022, by using the process instruction document as the basis for extracting processing information, the standardization and normalization of the processing process is ensured. This helps to ensure the consistency of product quality and performance. By automatically extracting and executing processing information, the possibility of human intervention and human error is reduced. This helps to improve the stability and consistency of the processing process.

103. Scan the material to be re-inspected to obtain a target wheel hub;

Specifically, a 3D laser scanner is called to generate a target wheel hub.

104. Compare the target contour with the preset contour to obtain a comparison result;

Specifically, a comparison algorithm is used to calculate the difference between the material profile and the preset profile.

According to the result of the comparison algorithm, the similarity or difference between the material profile and the preset profile is evaluated to obtain the comparison result. For example, the difference is calculated using the Euclidean distance:

Normalize the target contour and the preset contour to convert them into numerical vectors of the same size and range.

Calculate the Euclidean distance between corresponding points in two contours. This can be done by calculating the straight-line distance between the two points, using the formula:

Here, A and B are corresponding points in the two contours, and (x ₁ ,x ₂ ) and (y ₁ ,y ₂ ) are their coordinates.

The total distance between two contours is obtained by adding up the Euclidean distances between all corresponding point pairs.

Finally, the total distance is divided by the number of corresponding point pairs to obtain the average Euclidean distance, which is the difference between the target contour and the preset contour.

Specifically, step 104 also includes the following specific implementation methods:

1041. Calculate a contour difference between the target contour and the preset contour to obtain a comparison result.

In step 1041, by calculating the contour difference, the similarity or difference between the target contour and the preset contour can be accurately measured, providing quantitative data on the degree of matching or deviation between the two.

Specifically, referring to FIG. 2 , FIG. 2 is a schematic diagram of a specific embodiment of step 1041 of the material correction method based on machine vision in an embodiment of the present invention, and step 1041 includes the following specific implementation methods:

10411. Perform 3D comparison on the target contour and the preset contour to obtain a 3D comparison result, and perform dimensional tolerance comparison on the target contour and the preset contour to obtain a dimensional deviation;

10412. Calculate the difference area and the difference parameters corresponding to the difference area according to the 3D comparison result and the size deviation, obtain the contour difference, and use the contour difference as the comparison result.

In steps 10411-10412, the target profile and the preset profile can be comprehensively evaluated through 3D comparison and dimensional tolerance comparison. This evaluation method considers both shape and size, providing a more comprehensive difference analysis. 3D comparison technology can provide high-precision profile matching metrics, while dimensional tolerance comparison is used to determine the deviation between the actual size and the designed size. The combination of the two can more accurately determine the difference area and difference parameters.

Specifically, referring to FIG. 3 , FIG. 3 is a schematic diagram of a specific embodiment before step 10411 of the material correction method based on machine vision in an embodiment of the present invention, and before step 10411, the following specific implementation methods are also included:

10413. Perform 3D comparison on the target contour and the preset contour to obtain a 3D comparison result, and perform dimensional tolerance comparison on the target contour and the preset contour to obtain a dimensional deviation;

Specifically, the 3D data of the target contour and the preset contour can be obtained through a scanning device.

Point cloud registration is used to compare the target contour with the 3D data of the preset contour to evaluate the similarity or difference between the two. The 3D comparison result includes the registration error, which is an indicator of the alignment accuracy between the target contour and the preset contour, expressed in terms of average distance, root mean square error (RMSE), etc. The smaller the registration error, the higher the alignment accuracy. Point cloud registration maps one point cloud to another point cloud by finding a spatial transformation so that the corresponding points in the two point clouds overlap as much as possible. The algorithms that can be used include the ICP (Iterative Closest Point) algorithm.

After obtaining the 3D comparison results, the target contour is further compared with the preset contour for dimensional tolerance. The dimensional deviation can be obtained by extracting the characteristic dimensions in the 3D data and comparing the differences between the characteristic dimensions.

10414. Integrate the 3D comparison result and the size deviation into prompt information and output it;

10415. When a processing instruction in response to the prompt information is detected within a preset time, the processing instruction is executed;

10416. When no processing instruction in response to the prompt information is detected within a preset time, a step of calculating a difference area and a difference parameter corresponding to the difference area according to the 3D comparison result and the size deviation is executed.

In steps 10413-10416, based on the 3D comparison results and dimensional deviations, feedback on the machining process is provided through data analysis and calculation. These data can provide a basis for decision making and support data-driven decision making.

105. According to the comparison result, determine whether the material to be re-inspected is qualified.

Specifically, the comparison result is analyzed. The comparison result may be an indicator of the difference or similarity between the material to be re-inspected and the preset profile.

According to the preset processing accuracy requirements, a judgment threshold is set. The judgment threshold can be used to determine whether the material to be re-inspected is within an acceptable error range.

The comparison result is compared with the set threshold. If the comparison result is within the threshold range, the material to be re-inspected is considered qualified; if it exceeds the threshold range, the material to be re-inspected is considered unqualified.

Output the judgment result. If the material to be re-inspected is qualified, it can be processed later or enter the next process; if the material to be re-inspected is unqualified, it needs to be processed again or scrapped.

106. If the material to be re-inspected is unqualified, a correction coefficient generation operation is performed according to the comparison result;

Specifically, the comparison result is analyzed, and the comparison result includes an index of the difference or similarity between the material to be re-inspected and the preset profile, such as a difference parameter corresponding to the difference area.

According to the difference parameters corresponding to the difference area, the corresponding correction coefficients are generated. These correction coefficients can include adjusting cutting parameters, optimizing machining paths, correcting positioning and fixing methods, etc.

Specifically, referring to FIG. 4 , FIG. 4 is a schematic diagram of a specific embodiment of step 106 of the material correction method based on machine vision in an embodiment of the present invention, and step 106 includes the following specific implementation methods:

1061. If the material to be re-inspected is unqualified, a distance metric calculation is performed according to the data points in the comparison result to obtain a difference result between the material to be re-inspected and the preset profile;

1062. Calculate a correction coefficient corresponding to the difference result.

In steps 1061-1062, by using distance metric calculation, the difference between the material to be re-inspected and the preset profile can be accurately measured, and multiple data points can be taken into account to provide a more comprehensive difference assessment.

107. Perform secondary processing on the material to be re-inspected according to the correction coefficient to obtain a target material.

Specifically, according to the generated correction coefficient, adjust the processing parameters and equipment parameters of the material to be re-inspected. Ensure that the correction coefficient is correctly applied in the secondary processing. Start the processing equipment and perform secondary processing on the material to be re-inspected according to the corrected parameters and settings. Monitor the operating status and cutting process of the equipment to ensure the smooth progress of the processing. During the secondary processing, adjust and control the parameters according to the actual situation. Improve the processing quality and efficiency by monitoring the processing data and observing the cutting conditions.

After the secondary processing is completed, the processing results are inspected and evaluated. The target material is compared with the preset contour to evaluate the degree of conformity. If the evaluation results show that the target material meets the requirements, the target material is considered qualified. If the evaluation results show that there are still unqualified parts, the target material is used as the first material for repeated processing until the target material is qualified.

In an embodiment of the present invention, a material correction device based on machine vision automatically performs processing operations on the material to be processed according to relative coordinates and preset process instruction documents. After the processing is completed, the material is scanned using machine vision technology to obtain its target contour, and compared with the preset contour to quickly determine whether the material is qualified. For unqualified materials, a correction coefficient is automatically generated based on the comparison results, and a secondary processing operation is performed. Through the material correction method, problems can be discovered and adjusted in time during the processing process, avoiding the situation where the final product is unqualified, thereby reducing the risk of scrapping and improving the yield rate of material processing.

FIG5 is a schematic diagram of the structure of a machine vision-based material correction device provided by an embodiment of the present invention. The machine vision-based material correction device 500 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 510 (for example, one or more processors) and a memory 520, and one or more storage media 530 (for example, one or more mass storage devices) storing application programs 533 or data 532. Among them, the memory 520 and the storage medium 530 may be temporary storage or permanent storage. The program stored in the storage medium 530 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the machine vision-based material correction device 500. Furthermore, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the machine vision-based material correction device 500.

The machine vision-based material correction device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input and output interfaces 560, and/or one or more operating systems 531, such as Windows Serve, Mac OS X, Unix, Linux, Free BSD, etc. Those skilled in the art will appreciate that the structure of the machine vision-based material correction device shown in FIG5 does not constitute a limitation on the machine vision-based material correction device, and may include more or less components than shown in the figure, or combine certain components, or arrange components differently.

The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the machine vision-based material correction method.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.

Although the subject matter has been described in language specific to structural features and/or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims (10)

1. A material correction method based on machine vision, characterized in that the material correction method based on machine vision comprises: When the machine platform detects the material to be processed, detecting the relative coordinates of the material to be processed on the machine platform; According to the relative coordinates and the preset process instruction document, a processing operation is performed on the material to be processed to obtain a material to be re-inspected; Scanning the material to be re-inspected to obtain a target wheel hub; Comparing the target contour with a preset contour to obtain a comparison result; According to the comparison result, judging whether the material to be re-inspected is qualified; If the material to be re-inspected is unqualified, a correction coefficient generation operation is performed according to the comparison result; According to the correction coefficient, a secondary processing operation is performed on the material to be re-inspected to obtain a target material. 2. The material correction method based on machine vision according to claim 1 is characterized in that if the material to be re-inspected is unqualified, the step of generating a correction coefficient according to the comparison result comprises: If the material to be re-inspected is unqualified, a distance metric calculation is performed according to the data points in the comparison result to obtain a difference result between the material to be re-inspected and the preset profile; Calculate the correction coefficient corresponding to the difference result. 3. The material correction method based on machine vision according to claim 1 is characterized in that the step of performing a processing operation on the material to be processed according to the relative coordinates and a preset process instruction document to obtain the material to be re-inspected comprises: Scan the material to be processed to obtain a material hub, and determine whether the material profile is symmetrical; If the material contour is symmetrical, a processing operation is performed on the material to be processed according to the relative coordinates and a preset process instruction document to obtain a material to be re-inspected. 4. The material correction method based on machine vision according to claim 3 is characterized in that after the step of scanning the material to be processed to obtain the material hub and judging whether the material profile is symmetrical, it also includes: If the material profile is asymmetrical, a prompt message is output indicating that the material to be processed needs fine-tuning. 5. The material correction method based on machine vision according to claim 1 is characterized in that the step of performing a processing operation on the material to be processed according to the relative coordinates and a preset process instruction document to obtain the material to be re-inspected comprises: Extract processing information from process instruction documents; According to the relative coordinates and the processing steps in the processing information, a processing tool corresponding to the processing step is called to perform a processing operation on the material to be processed to obtain the material to be re-inspected. 6. The material correction method based on machine vision according to any one of claims 1 to 5, characterized in that the step of comparing the target contour with the preset contour to obtain a comparison result comprises: The contour difference between the target contour and the preset contour is calculated to obtain a comparison result. 7. The material correction method based on machine vision according to claim 6, characterized in that the step of calculating the contour difference between the target contour and the preset contour to obtain the comparison result comprises: Performing a 3D comparison between the target contour and the preset contour to obtain a 3D comparison result, and performing a dimensional tolerance comparison between the target contour and the preset contour to obtain a dimensional deviation; According to the 3D comparison result and the size deviation, a difference area and a difference parameter corresponding to the difference area are calculated to obtain a contour difference, and the contour difference is used as the comparison result. 8. The material correction method based on machine vision according to claim 7, characterized in that before the step of calculating the difference area and the difference parameters corresponding to the difference area according to the 3D comparison result and the size deviation to obtain the contour difference and taking the contour difference as the comparison result, the method further comprises: Performing a 3D comparison between the target contour and the preset contour to obtain a 3D comparison result, and performing a dimensional tolerance comparison between the target contour and the preset contour to obtain a dimensional deviation; Integrate the 3D comparison result and the size deviation into prompt information and output it; When a processing instruction in response to the prompt information is detected within a preset time, executing the processing instruction; When no processing instruction in response to the prompt information is detected within a preset time, a step of calculating a difference area and a difference parameter corresponding to the difference area according to the 3D comparison result and the size deviation is performed. 9. A material correction device based on machine vision, characterized in that the material correction device based on machine vision comprises: a memory and at least one processor, the memory stores instructions, and the memory and the at least one processor are interconnected through a line; The at least one processor calls the instructions in the memory to enable the machine vision-based material correction device to perform the machine vision-based material correction method according to any one of claims 1 to 8. 10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the machine vision-based material correction method according to any one of claims 1 to 8 is implemented.