Laser marking method and device

Abstract

The invention discloses a laser marking method and device. The device comprises a material conveying belt; the positioning camera is used for acquiring a target image of the material on the material conveying belt and positioning based on the target image; the positioning method comprises the following steps: converting the target image into a grayscale image; extracting the contour of the material from the processed target image through morphological operation; the mass center of the contour is calculated, the mass center serves as a marking center point, and the main direction angle of the material is calculated through principal component analysis; converting the center of mass and the main direction angle under an image coordinate system into a mechanical coordinate system of the laser; and the offset and the rotation angle of the material under the mechanical coordinate system are calculated, and affine transformation is performed on the marking path according to the offset and the rotation angle so as to realize accurate positioning and marking. According to the invention, the marking efficiency and accuracy can be greatly improved.

Description

Technical Field

[0001] This application relates to the technical field of laser marking, and particularly to a laser marking method and device. Background Art

[0002] Traditional laser marking positioning techniques typically rely on mechanical auxiliary limiting devices (such as fixed jigs, guiding baffles, etc.) to achieve position constraint and correction of workpieces. Such methods have significant limitations: Firstly, mechanical limiting devices need to be customized for different specifications of marking objects. When the product size, shape, or placement angle changes, the fixture needs to be frequently adjusted or replaced, resulting in poor equipment compatibility and high line change costs; Secondly, mechanical mechanisms are limited by the physical contact-based positioning principle, making it difficult to meet the precise positioning requirements of flexible materials, curved structures, or micro workpieces, and are prone to introducing cumulative deviations due to mechanical wear or assembly errors, affecting the marking accuracy. In addition, traditional methods rely on manual intervention to complete position calibration, with low automation and difficulty in meeting the requirements of high-tempo, multi-variety flexible production. Summary of the Invention

[0003] In view of the above problems, this application provides a laser marking method for solving the technical problems of manual leveling and low positioning accuracy in the above-mentioned transmission marking.

[0004] To achieve the above object, this application provides a laser marking method, including the following steps:

[0005] The material to be marked is transported to the laser marking module by a material conveyor belt. The laser marking module is arranged above the material conveyor belt and includes a positioning camera, a scanning galvanometer, and a laser;

[0006] The positioning camera obtains a target image of the material on the material conveyor belt;

[0007] The target image is converted into a grayscale image, and then Gaussian filtering denoising, contrast enhancement, and binarization processing are performed;

[0008] The contour of the material is extracted from the processed target image through morphological operations;

[0009] The centroid of the contour is calculated, and the centroid is used as the marking center point, and the main direction angle of the material is calculated through principal component analysis;

[0010] The centroid and the main direction angle in the image coordinate system are converted into the mechanical coordinate system of the laser;

[0011] The offset and rotation angle of the material in the mechanical coordinate system are calculated, and the marking path is affine-transformed according to the offset and the rotation angle to achieve precise positioning and marking.

[0012] Further, the laser marking method further includes visually inspecting the marked material, and the visual inspection includes the following steps:

[0013] Obtaining an image of the material to be inspected on the material conveyor belt through an inspection camera to obtain an image to be inspected;

[0014] Converting the image to be inspected into a grayscale image, and then performing Gaussian filtering for noise reduction, contrast enhancement, and binarization processing;

[0015] Performing image matching on the processed image to be inspected based on the normalized cross-correlation matching algorithm, then finely adjusting the position using the SIFT / SURF feature matching algorithm to obtain an affine transformation matrix, and processing the image to be inspected based on the affine transformation matrix, and the processing includes any one or more of translation, rotation, and scaling;

[0016] Differencing the processed image to be inspected from a template, and extracting abnormal regions in the image to be inspected through threshold processing, and the abnormal regions include any one or more of missing regions, redundant regions, geometric deviation regions, and blurred / insufficient contrast regions;

[0017] Detecting holes or protrusions in the image to be inspected through opening / closing operations, and after edge detection by the Canny method, counting the edge continuity;

[0018] Qualitatively evaluating the marking quality according to the abnormal regions, the holes or protrusions, and the edge continuity.

[0019] Further, after the qualitative evaluation of the marking quality, the method further includes the steps of:

[0020] Judging the clarity of the image by calculating the variance of the gradient magnitude of the image to be inspected;

[0021] Judging the contrast of the image to be inspected by the standard deviation of the gray level in the ROI region;

[0022] Measuring the error between the key dimensions in the image to be inspected and the dimensions at the corresponding positions in the template to judge the geometric accuracy of the marked image;

[0023] Quantitatively evaluating the marking quality through the clarity, the contrast, and the geometric accuracy.

[0024] Further, after the visual inspection, the method further includes the step of sorting out the marked unqualified materials and marked qualified materials through a sorting component.

[0025] To solve the above technical problems, the present application also provides another technical solution:

[0026] A laser marking device, comprising:

[0027] The material conveyor belt is used to transport the object to be marked to the laser marking module for marking. The laser marking module is arranged above the material conveyor belt and includes a positioning camera, a scanning galvanometer, and a laser;

[0028] The positioning camera is used to obtain the target image of the material on the material conveyor belt and perform positioning based on the target image. The positioning includes the following steps:

[0029] Convert the target image into a grayscale image, and then perform Gaussian filtering denoising, contrast enhancement, and binarization processing;

[0030] Extract the contour of the material from the processed target image through morphological operations;

[0031] Calculate the centroid of the contour, use the centroid as the center point of marking, and calculate the main direction angle of the material through principal component analysis;

[0032] Convert the centroid and the main direction angle in the image coordinate system to the mechanical coordinate system of the laser;

[0033] Calculate the offset and rotation angle of the material in the mechanical coordinate system, and perform affine transformation on the marking path according to the offset and the rotation angle to achieve precise positioning and marking.

[0034] Furthermore, the laser marking device further includes a vision quality inspection camera. The vision quality inspection camera is used to obtain the image of the material to be inspected on the material conveyor belt, obtain the image to be inspected, and detect the marking quality based on the image to be inspected. The detecting the marking quality based on the image to be inspected includes:

[0035] Convert the image to be inspected into a grayscale image, and then perform Gaussian filtering denoising, contrast enhancement, and binarization processing;

[0036] Perform image matching on the processed image to be inspected based on the normalized cross-correlation matching algorithm, then finely adjust the position using the SIFT / SURF feature matching algorithm to obtain the affine transformation matrix, and process the image to be inspected based on the affine transformation matrix. The processing includes any one or more of translation, rotation, and scaling;

[0037] Differentiate the processed image to be inspected from the template, and extract the abnormal area in the image to be inspected through threshold processing. The abnormal area includes any one or more of missing area, redundant area, geometric deviation area, and blurred / insufficient contrast area;

[0038] Detect holes or protrusions in the image to be inspected through opening / closing operations, and after edge detection by the Canny method, count the edge continuity;

[0039] Qualitatively mark the quality according to the abnormal area, the hole or protrusion, and the edge continuity.

[0040] Further: after the qualitative marking of the quality, the following steps are also included:

[0041] Judge the clarity of the image to be inspected by calculating the variance of the gradient amplitude of the image to be inspected;

[0042] Judge the contrast of the image to be inspected by the standard deviation of the gray level in the ROI area;

[0043] Measure the error between the key dimensions in the image to be inspected and the dimensions at the corresponding positions in the template, and judge the geometric accuracy of the marked image;

[0044] Quantitatively evaluate the marking quality through the clarity, the contrast, and the geometric accuracy.

[0045] Further: it also includes a sorting component, which is arranged beside the material conveyor belt and is used to sort out the materials with unqualified markings and the materials with qualified markings obtained from visual quality inspection.

[0046] Different from the prior art, the above technical solution proposes a laser marking method and device, and this technical solution is based on a laser marking algorithm for non-contact visual positioning and dynamic deviation correction. By integrating a high-resolution industrial camera and an image processing module, the system can capture the surface features of the workpiece in real time and extract the coordinates of the key positioning points, calculate the offset between the target position and the preset calibration position in combination with the affine transformation matrix, and then drive the motion control module to complete the dynamic compensation with sub-pixel accuracy. This solution abandons the traditional mechanical limit device and can adapt to the workpiece postures of different structures (such as flat surfaces, curved surfaces, special-shaped parts) and different orientations (such as inclination, rotation, misalignment), significantly improving the universality and marking efficiency of the equipment, and is especially suitable for small-batch and customized production scenarios.

[0047] The relevant records in the above invention content are only an overview of the technical solution of this application. In order to enable those of ordinary skill in the art to more clearly understand the technical solution of this application, and then can be implemented according to the content recorded in the text of the specification and the drawings, and in order to make the above objects, other objects, features, and advantages of this application more easily understood, the following is described in conjunction with the specific implementation manners and drawings of this application. Description of the Drawings

[0048] The drawings are only used to show the principles, implementation methods, applications, features, and effects of the specific implementation manners of the present invention and other related contents, and should not be considered as a limitation to this application.

[0049] In the accompanying drawings of the specification:

[0050] Figure 1 It is a schematic structural diagram of the laser marking device described in the specific embodiment;

[0051] Figure 2 It is a circuit module diagram of the laser marking device described in the specific embodiment;

[0052] Figure 3 It is a flowchart of material positioning in the laser marking method described in the specific embodiment;

[0053] Figure 4 It is a flowchart of visual quality inspection in the laser marking method described in the specific embodiment;

[0054] Figure 5 It is a complete flowchart of visual quality inspection in the laser marking method described in the specific embodiment;

[0055] The reference numerals involved in the above-mentioned accompanying drawings are explained as follows:

[0056] 1. Frame; 2. Adjustable material trough; 3. Material conveyor belt; 31. Material limiting strip;

[0057] 4. Marking scanning galvanometer; 5. Mounting rod; 6. Laser; 7. Sorting push rod;

[0058] 8. Visual quality inspection camera; 9. First receiving trough; 10. Second receiving trough; 11. Display;

[0059] 12. Control host; Specific embodiment

[0060] To illustrate in detail the possible application scenarios, technical principles, specific implementable solutions, achievable purposes and effects, etc. of the present application, the following will be described in detail with reference to the specific examples listed and in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, so they are only examples and cannot be used to limit the protection scope of the present application.

[0061] Referring to "embodiment" herein means that the specific features, structures or characteristics described in connection with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing at various positions in the specification does not necessarily refer to the same embodiment, nor is it particularly limited to the independence or relevance with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the technical features mentioned in each embodiment can be combined in any way to form the corresponding implementable technical solution.

[0062] Unless otherwise defined, the meanings of technical terms used herein are the same as those commonly understood by those skilled in the technical field to which this application belongs; the use of relevant terms herein is only for describing specific embodiments and is not intended to limit this application.

[0063] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: the existence of A, the existence of B, and the simultaneous existence of both A and B. Additionally, the character " / " in this text generally represents an "or" logical relationship between the associated objects before and after.

[0064] In this application, terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual quantitative, primary-secondary, or sequential relationships between these entities or operations.

[0065] Without further limitations, in this application, the open-ended expressions such as "include", "comprise", "have", or other similar expressions used in statements are intended to cover non-exclusive inclusion. These expressions do not exclude the possibility that there may be additional elements in the process, method, or product that includes the described elements. Thus, a process, method, or product that includes a series of elements may not only include those defined elements, but also include other elements that are not explicitly listed, or elements that are inherent to such a process, method, or product.

[0066] Similar to the understanding in the "Examination Guidelines", in this application, expressions such as "greater than", "less than", "exceeding", etc. are understood not to include the number itself; expressions such as "above", "below", "within", etc. are understood to include the number itself. In addition, in the description of the embodiments of this application, the meaning of "multiple" is two or more (including two). Similar expressions related to "many", such as "multiple groups", "multiple times", etc., are understood in the same way, unless otherwise specifically defined.

[0067] In the description of the embodiments of this application, the spatially related expressions used, such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "perpendicular", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the specific embodiment or the accompanying drawings. This is only for the convenience of describing the specific embodiments of this application or facilitating the reader's understanding, and does not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, it should not be construed as a limitation on the embodiments of this application.

[0068] Unless otherwise clearly specified or limited, in the description of the embodiments of the present application, terms such as "installation", "connection", "fixation", "setting", etc. used shall be understood in a broad sense. For example, the "connection" may be a fixed connection, a detachable connection, or an integral setting; it may be a mechanical connection, an electrical connection, or a communication connection; it may be a direct connection or an indirect connection through an intermediate medium; it may be the communication inside two components or the interaction relationship between two components. For those skilled in the art to which the present application pertains, the specific meanings of the above terms in the embodiments of the present application can be understood according to specific circumstances.

[0069] Please refer to Figures 1 to 5 , this embodiment provides a laser marking device and a laser marking method. As Figure 1 shown, it is a schematic structural diagram of the laser marking device. The laser marking device includes: a frame 1, a material tank, a material conveyor belt 3, a marking scanning galvanometer 4, a mounting rod 5, a laser 6 (i.e., Figure 2 the laser generator in

[0070] ), a sorting push rod 7, a vision quality inspection camera 8, a first receiving tank 9, a second receiving tank 10, a display 11, and a control host 12.

[0071] A positioning camera is also provided at the position where the marking scanning galvanometer 4 is located. The positioning camera is used to obtain the target image of the material on the material conveyor belt 3 and perform positioning based on the target image.

[0072] As Figure 2 shown, it is a circuit module block diagram of the laser marking device in this embodiment. Among them, the control system in the laser marking device is installed in the control host 12. The camera 1 is a positioning camera, the camera 2 is the vision quality inspection camera 8, and the sorting pneumatic push rod corresponds to the sorting push rod 7, that is, the sorting push includes a cylinder and is driven by compressed gas to work. The conveyor belt drive motor is used to drive the material conveyor belt 3 to rotate and run.

[0073] When performing laser marking, the material is stored in the material tank and is pushed into the material conveyor belt by the material pushing pneumatic device. The conveyor belt drive motor starts and times. When the material reaches the area below the positioning camera and the marking scanning galvanometer 4, it stops. The positioning camera visually identifies the position and direction of the material, and the laser 6 corrects according to the identified position and direction, and accurately marks at the corresponding position and direction. After marking, the material continues to advance and enters the area below the vision quality inspection camera 8. The vision quality inspection camera 8 identifies its marking pattern and compares it with the pattern to be marked through the system. If it is correct (i.e., the marked material is qualified), it continues to move forward and enters the finished product tank; if it is incorrect (i.e., the marked material is unqualified), the sorting push rod 7 is activated to push the material vertically into the second receiving tank 10 (i.e., the unqualified product material tank), and the qualified marked material is conveyed by the material conveyor belt 3 to the first receiving tank 9 at the end. Therefore, through this laser marking device, material marking, vision quality inspection and sorting can be realized.

[0074] As Figure 3 shown, the positioning of the material during the laser marking process includes the following steps:

[0075] S101. The material to be marked is transported by the material conveyor belt to the laser marking module. The laser marking module is arranged above the material conveyor belt. As Figure 1 shown, the laser marking module includes a positioning camera, a scanning galvanometer and a laser;

[0076] S102. The positioning camera obtains the target image of the material on the material conveyor belt, converts the target image into a grayscale image, and then performs Gaussian filtering for noise reduction, contrast enhancement and binarization processing;

[0077] S103. Extract the contour of the material from the processed target image through morphological operations; calculate the centroid of the contour, use the centroid as the center point of marking, and calculate the main direction angle of the material through principal component analysis;

[0078] S104. Convert the centroid and the principal direction angle in the image coordinate system into the mechanical coordinate system of the laser.

[0079] S105. Calculate the offset and rotation angle of the material in the mechanical coordinate system, and perform an affine transformation on the marking path according to the offset and the rotation angle to achieve precise positioning and marking.

[0080] In the traditional marking positioning, a mechanical auxiliary limiting device is used to achieve it, with a complex structure and poor adaptability to different marking objects. In this embodiment, the material is transported by a material conveyor belt, and precise positioning is performed through the visual positioning step. Therefore, a laser marking algorithm for contactless visual positioning and dynamic deviation correction can be used. By integrating a high-resolution industrial camera and an image processing module, the system can capture the surface features of the workpiece in real time and extract the coordinates of key positioning points. Combining with the affine transformation matrix, the offset between the target position and the preset calibration position is calculated, and then the motion control module is driven to complete the dynamic compensation with sub-pixel-level accuracy. This solution abandons the traditional mechanical limiting device and can adapt to the workpiece postures of different structures (such as planes, curved surfaces, and special-shaped parts) and different orientations (such as tilting, rotating, and misalignment), significantly improving the universality and marking efficiency of the equipment, and is especially suitable for small-batch and customized production scenarios.

[0081] As Figure 4 shown, the laser marking method further includes visually inspecting the marked material, which is based on the analysis of the image captured by the visual inspection camera. The visual inspection includes the following steps:

[0082] S201. Obtain the image of the material to be inspected on the material conveyor belt through the inspection camera to obtain the to-be-inspected image; convert the to-be-inspected image into a grayscale image, and then perform Gaussian filtering for noise reduction, contrast enhancement, and binarization processing.

[0083] S202. Perform image matching on the processed to-be-inspected image based on the normalized cross-correlation matching algorithm, and then finely adjust the position using the SIFT / SURF feature matching algorithm to obtain an affine transformation matrix. Process the to-be-inspected image based on the affine transformation matrix, and this processing includes any one or more of translation, rotation, and scaling.

[0084] S203. Differentiate the processed to-be-inspected image from the template, and extract the abnormal regions in the to-be-inspected image through threshold processing. The abnormal regions include any one or more of missing regions, redundant regions, geometric deviation regions, and blurred / contrast-insufficient regions.

[0085] The missing region is the part that exists in the template but is actually missing in the marking (such as broken lines and missed marking).

[0086] The redundant area refers to the part that does not exist in the template but is extra in actual marking (such as burrs and splashes).

[0087] The geometric deviation area means that the size, shape or angle of the marked pattern is inconsistent with the template (such as scaling error and rotation offset).

[0088] The blurred / insufficient contrast area means that the pattern edge is unclear or the gray value is quite different from the template.

[0089] S204. Detect holes or protrusions in the image to be inspected through opening / closing operations, and after edge detection by the Canny method, count the edge continuity;

[0090] S205. Qualitatively evaluate the marking quality according to the abnormal area, the holes or protrusions, and the edge continuity.

[0091] In this embodiment, the marking quality is qualitatively detected from aspects such as abnormal area, hole protrusion, and edge continuity. The qualitative detection is to judge whether the marking is qualified, so as to distinguish qualified marked materials from unqualified marked materials.

[0092] In addition to qualitative detection, this embodiment can also quantitatively evaluate the marking quality. The quantitative evaluation includes:

[0093] Judge the clarity of the image by calculating the variance of the gradient amplitude of the image to be inspected;

[0094] Judge the contrast of the image to be inspected by the standard deviation of the gray level in the ROI area;

[0095] Measure the error between the key dimensions in the image to be inspected and the corresponding dimensions in the template to judge the geometric accuracy of the marked image;

[0096] Quantitatively evaluate the marking quality through the clarity, the contrast, and the geometric accuracy.

[0097] As Figure 5 shown, it is a complete flowchart of visual quality inspection combining qualitative detection and quantitative evaluation.

[0098] Finally, it should be noted that although the above embodiments have been described in the text and drawings of the specification of this application, the patent protection scope of this application cannot be limited thereby. Any technical solutions obtained by equivalent structure or equivalent process substitution or modification based on the essential concept of this application and using the content recorded in the text and drawings of the specification of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, etc., are all included in the patent protection scope of this application.

Claims

1. A laser marking method, characterized in that: The following steps are involved: The material to be marked is transported from the material conveyor belt to the laser marking module, which is arranged above the material conveyor belt and includes a positioning camera, a scanning galvanometer and a laser; The positioning camera obtains a target image of the material on the material conveyor belt, converts the target image into a grayscale image, and then performs Gaussian filtering, denoising, contrast enhancement and binarization processing; Extracting the outline of the material from the processed target image through morphological operations; calculating the centroid of the outline, taking the centroid as the center point of marking, and calculating the main direction angle of the material through principal component analysis; Convert the centroid and the main direction angle in the image coordinate system to the mechanical coordinate system of the laser; The offset and rotation angle of the material in the mechanical coordinate system are calculated, and according to the offset and the rotation angle, an affine transformation is performed on the marking path to achieve precise positioning and marking.

2. The laser marking method according to claim 1, characterized in that: The method also includes performing a visual quality inspection on the marked material, wherein the visual quality inspection includes the following steps: The image of the material to be inspected on the material conveyor belt is acquired by a quality inspection camera to obtain an image to be inspected; the image to be inspected is converted into a grayscale image, and then subjected to Gaussian filtering, denoising, contrast enhancement and binarization processing; Performing image matching on the processed image to be inspected based on a normalized cross-correlation matching algorithm, and then fine-tuning the position using a SIFT / SURF feature matching algorithm to obtain an affine transformation matrix, and processing the image to be inspected based on the affine transformation matrix, the processing including: any one or more of translation, rotation, and scaling; Differentiating the processed image to be inspected from the template, and extracting abnormal areas in the image to be inspected by threshold processing, wherein the abnormal areas include any one or more of missing areas, redundant areas, geometric deviation areas, and blurred / inadequate contrast areas; Detect holes or protrusions in the image to be inspected by opening / closing operations, and after edge detection by the Canny method, count the edge continuity; The marking quality is qualitatively evaluated based on the abnormal area, the holes or protrusions, and the edge continuity.

3. The laser marking method according to claim 2, characterized in that: After the qualitative marking quality is described, the following steps are also included: The clarity of the image is determined by calculating the variance of the gradient amplitude of the image to be tested; The contrast of the image to be inspected is determined by the grayscale standard deviation of the ROI area; Measure the error between the key dimensions in the image to be inspected and the corresponding position dimensions in the template to determine the geometric accuracy of the marked image; The marking quality is quantitatively evaluated by the clarity, the contrast and the geometric accuracy.

4. The laser marking method according to claim 2, characterized in that: After the visual quality inspection, the method further includes the step of sorting out the unqualified marking materials and the qualified marking materials obtained through the visual quality inspection by means of a sorting component.

5. A laser marking device, characterized in that: include: A material conveyor belt is used to convey the object to be marked to the laser marking module for marking. The laser marking module is arranged above the material conveyor belt and includes a positioning camera, a scanning galvanometer and a laser; The positioning camera is used to obtain a target image of the material on the material conveyor belt and perform positioning based on the target image; positioning includes the following steps: The target image is converted into a grayscale image, and then subjected to Gaussian filtering, denoising, contrast enhancement and binarization processing; Extract the outline of the material from the processed target image through morphological operations; Calculate the centroid of the contour, use the centroid as the center point of marking, and calculate the main direction angle of the material through principal component analysis; Convert the centroid and the main direction angle in the image coordinate system to the mechanical coordinate system of the laser; The offset and rotation angle of the material in the mechanical coordinate system are calculated, and according to the offset and the rotation angle, an affine transformation is performed on the marking path to achieve precise positioning and marking.

6. The laser marking device according to claim 5, characterized in that: It also includes a visual quality inspection camera, which is used to obtain an image of the material to be inspected on the material conveyor belt, obtain the image to be inspected, and detect the marking quality based on the image to be inspected. The marking quality detection based on the image to be inspected includes: Convert the image to be inspected into a grayscale image, and then perform Gaussian filtering, denoising, contrast enhancement and binarization processing; Performing image matching on the processed image to be inspected based on a normalized cross-correlation matching algorithm, and then fine-tuning the position using a SIFT / SURF feature matching algorithm to obtain an affine transformation matrix, and processing the image to be inspected based on the affine transformation matrix, the processing including: any one or more of translation, rotation, and scaling; Differentiating the processed image to be inspected from the template, and extracting abnormal areas in the image to be inspected by threshold processing, wherein the abnormal areas include any one or more of missing areas, redundant areas, geometric deviation areas, and blurred / inadequate contrast areas; Detect holes or protrusions in the image to be inspected by opening / closing operations, and after edge detection by the Canny method, count the edge continuity; The marking quality is qualitatively evaluated based on the abnormal area, the holes or protrusions, and the edge continuity.

7. The laser marking device according to claim 6, characterized in that: After the qualitative marking quality is described, the following steps are also included: The clarity of the image is determined by calculating the variance of the gradient amplitude of the image to be tested; The contrast of the image to be inspected is determined by the grayscale standard deviation of the ROI area; Measure the error between the key dimensions in the image to be inspected and the corresponding position dimensions in the template to determine the geometric accuracy of the marked image; The marking quality is quantitatively evaluated by the clarity, the contrast and the geometric accuracy.

8. The laser marking device according to claim 6, characterized in that: Also includes: The sorting component is arranged on the side of the material conveyor belt and is used to sort out the unqualified marking materials and the qualified marking materials obtained by the visual quality inspection.

Images