Laser etching label paper surface flaw detection method based on machine vision

Abstract

The invention relates to the technical field of image processing, in particular to a laser etching label paper surface flaw detection method based on machine vision. The method comprises the following steps: acquiring a laser etching label paper surface image set A acquired in a historical etching time period; acquiring a defect identification result of each laser etching label paper surface image in A; for the defect identification result of any image in A, if the defect identification result comprises defects, comparing the identified defects with corresponding real defects, and obtaining the defects which are different from the corresponding real defects in the identified defects; if the ratio of the number of the different flaws corresponding to all the images in A to the number of the real flaws is larger than or equal to a preset proportion threshold value, the movement speed adjusting amount of the laser etching equipment is obtained according to the different flaws, and the target movement speed of the laser etching equipment in the current time period is obtained in combination with V0. According to the invention, the laser etching speed matched with the parameters of the image acquisition equipment can be determined.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a method for detecting surface defects of laser-etched label paper based on machine vision. Background Art

[0002] Due to the characteristics of high precision and non-contact processing, laser etching technology is widely used in the mass production of graphics and texts on the surface of label paper. Surface defects of label paper (such as incomplete etching, rough edges, trailing deformation, etc.) directly affect the readability and reliability of product identification. Therefore, higher requirements are put forward for real-time defect detection in the etching process and adjustment of equipment parameters. Traditional manual visual inspection has low efficiency and strong subjectivity, and it is difficult to adapt to high-speed automated production lines. Although the detection technology based on machine vision has realized the automation of defect identification, there are the following problems: it only focuses on defect identification, but does not consider the problem of image distortion caused by the mismatch between the image acquisition device and the laser etching speed, and thus the detection result of defects based on the distorted image is unreliable. How to determine the laser etching speed that matches the parameters of the image acquisition device and avoid image distortion in the images collected by the image acquisition device is an urgent problem to be solved. Summary of the Invention

[0003] The object of the present invention is to provide a method for detecting surface defects of laser-etched label paper based on machine vision to determine the laser etching speed that matches the parameters of the image acquisition device and avoid image distortion in the images collected by the image acquisition device.

[0004] According to the present invention, there is provided a method for detecting surface defects of laser-etched label paper based on machine vision, including the following steps: S100, obtaining a set of surface images A of laser-etched label paper collected during a historical etching time period; the historical etching time period includes several image acquisition moments, A includes the surface images of laser-etched label paper collected at each image acquisition moment, and the moving speed of the laser etching device during the historical etching time period is V0.

[0005] S200, respectively inputting the surface images of laser-etched label paper in A into a trained target defect recognition model to obtain the defect recognition results of each surface image of laser-etched label paper in A.

[0006] S300, for the defect recognition result of any surface image of laser-etched label paper in A, if the defect recognition result includes defects, comparing the defects recognized by the target defect recognition model with the corresponding real defects to obtain the defects in the defects recognized by the target defect recognition model that are different from the corresponding real defects; the real defects are the defects existing in the surface images of laser-etched label paper obtained by using a static shooting method corresponding thereto.

[0007] S400. If the ratio of the number of defective marks with differences corresponding to the surface images of all laser-etched label papers in A to the number of actual defective marks is greater than or equal to a preset ratio threshold, then obtain the adjustment amount of the movement speed of the laser-etching device according to the defective marks with differences, and obtain the target movement speed of the laser-etching device within the current time period according to the adjustment amount of the movement speed and V0.

[0008] The present invention has at least the following beneficial effects compared with the prior art: The present invention obtains a set of surface images of laser-etched label papers collected during a historical etching time period. These images are collected when the movement speed of the laser-etching device is V0. By comparing the defective marks in these images with the defective marks existing in the surface images of the laser-etched label papers obtained by using a static shooting method, it can be determined whether the images collected when the movement speed of the laser-etching device is V0 are distorted. For example, if the ratio of the number of defective marks with differences corresponding to the surface images of all laser-etched label papers in A to the number of actual defective marks is greater than or equal to a preset ratio threshold, then it is determined that the images collected when the movement speed of the laser-etching device is V0 are distorted. In this case, obtain the adjustment amount of the movement speed of the laser-etching device according to the defective marks with differences to adjust V0 and obtain the movement speed of the laser-etching device that matches the parameters of the image acquisition device. Thus, the present invention improves the matching between the laser-etching speed and the parameters of the image acquisition device, can avoid the problem of distortion of the images collected by the image acquisition device caused by the mismatch between the laser-etching speed and the parameters of the image acquisition device, and is beneficial to accurately detecting defects based on the images collected by the image acquisition device. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0010] Figure 1 It is a flowchart of a method for detecting surface defects of laser-etched label papers based on machine vision provided by an embodiment of the present invention; Figure 2 It is a flowchart of the process of V0 provided by an embodiment of the present invention; Figure 3 It is a flowchart of the process of obtaining the adjustment amount of the movement speed of the laser-etching device according to the defective marks with differences provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the protection scope of the present invention.

[0012] According to this embodiment, as Figure 1 shown, a method for detecting surface defects of laser-etched label paper based on machine vision is provided, including the following steps: S100, obtaining a set of surface images A of the laser-etched label paper collected during the historical etching time period; the historical etching time period includes several image acquisition moments, A includes the surface images of the laser-etched label paper collected at each image acquisition moment, and the moving speed of the laser etching equipment during the historical etching time period is V0.

[0013] As an optional specific implementation manner, the laser etching equipment is a roll-to-roll system, the material is PET label paper, the thickness is 0.1 mm, and the width is 100 mm; the image collector is a line array camera, the line frequency is 200 kHz, the pixel resolution is 2048, the pixel size is 5 μm, and the optical magnification is 1:1.

[0014] As an optional specific implementation manner, during the historical time period, images are collected at fixed intervals and saved as the image set A = {A1, A2,..., A j ,..., A m}; among them, except for the different acquisition moments, other variables are the same. For example, the label paper materials are the same, the relevant parameters of the image acquisition device (such as the exposure time, etc.) are the same, and the relevant parameters of the laser etching equipment (such as the laser frequency and vibration conditions, etc.) are also the same.

[0015] As an optional specific implementation manner, V0 is an empirical value; as a preferred specific implementation manner, as Figure 2 shown, the acquisition process of V0 includes: S110, obtaining the first condition satisfied by the moving speed of the laser etching equipment according to the line frequency, pixel resolution, and single-line field of view width of the image collector; the first condition includes: V ≤ f × W / p, where V is the moving speed of the laser etching equipment, f is the line frequency of the image collector, W is the single-line field of view width, and p is the pixel resolution.

[0016] In this embodiment, the line frequency, pixel resolution, and single-line field of view width of the image collector are known and unchanged. Based on the above first condition, the first value range of the moving speed of the laser etching equipment can be obtained.

[0017] S120. Obtain the second condition that the movement speed of the laser etching device satisfies according to the exposure time, pixel size, and optical magnification of the image collector; the second condition includes: V ≤ s / (T×M), where s is the pixel size, T is the exposure time of the image collector, and M is the optical magnification.

[0018] In this embodiment, the exposure time, pixel size, and optical magnification of the image collector are known and unchanged. Based on the above second condition, the second value range of the movement speed of the laser etching device can be obtained.

[0019] S130. Obtain the third condition that the movement speed of the laser etching device satisfies according to the minimum detectable defect size, the exposure time of the image collector, and the minimum number of pixels that the defect spans; the third condition includes: V ≤ d / (T×q), where d is the minimum detectable defect size and q is the minimum number of pixels that the defect spans.

[0020] In this embodiment, the minimum detectable defect size, the exposure time of the image collector, and the minimum number of pixels that the defect spans are known and unchanged. Based on the above third condition, the third value range of the movement speed of the laser etching device can be obtained.

[0021] S140. Determine a movement speed that satisfies the first condition, the second condition, and the third condition as V0.

[0022] In this embodiment, V0 > 0, and a movement speed that satisfies the first condition, the second condition, and the third condition is a value in the intersection of the above first value range, second value range, and third value range. Optionally, V0 is the maximum movement speed that satisfies the first condition, the second condition, and the third condition.

[0023] Based on S110 - S140, the movement speed of the laser etching device that is relatively matched with the parameters of the image collector can be obtained, which is beneficial to reducing the workload of the subsequent adjustment process of the movement speed of the laser etching device.

[0024] S200. Input the surface images of the laser - etched label paper in A into the trained target defect recognition model respectively, and obtain the defect recognition results of each surface image of the laser - etched label paper in A.

[0025] As an optional specific implementation manner, the target defect recognition model adopts an existing target detection model to detect the following defects in the image: excessive ablation (abnormal area), trailing trace (abnormal length), and edge deformation (abnormal shape). The output of the target defect recognition model (i.e., the recognition result) includes the category of each defect, the position coordinates of each defect, the area (number of pixels) of each defect, the trailing length of each defect, and the contour perimeter of each defect.

[0026] Those skilled in the art are aware that the process of training a target detection model is prior art and will not be elaborated here.

[0027] S300. For the defect recognition result of any surface image of the laser-etched label paper in A, if the defect recognition result includes defects, compare the defects recognized by the target defect recognition model with the corresponding real defects to obtain the defects that are different from the corresponding real defects among the defects recognized by the target defect recognition model; the real defects are the defects existing in the surface image of the laser-etched label paper obtained by the corresponding static shooting method.

[0028] As an optional specific implementation manner, for any surface image of the laser-etched label paper in A (i.e., the dynamically acquired image), use its corresponding static shooting image as the real defect benchmark (when shooting, the label paper is stationary, the moving speed of the laser etching device is 0, and the shooting object is the same as that in dynamic shooting). There is no distortion problem in the static shooting image. Align the dynamically acquired image with the corresponding static benchmark through the image registration algorithm, and calculate the geometric difference between the recognized defect and the corresponding real defect.

[0029] As an optional specific implementation manner, the geometric difference includes area difference, trailing length difference, and image deformation amount. Among them, the area difference is |recognized area - real area| / real area × 100%. If the area difference is greater than or equal to the preset area ratio threshold (for example, 5%), it is determined that there is an area difference; the trailing length difference is the difference between the extension length of the defect recognized in the dynamic image along the etching direction and the extension length of the real defect along the etching direction. If the difference is greater than or equal to the preset trailing length difference threshold (for example, 2 pixels), it is determined that there is a trailing length difference; the image deformation amount is |recognized contour perimeter - real contour perimeter| / real contour perimeter × 100%. If the graphic deformation amount is greater than or equal to the preset image deformation amount threshold (for example, 2%), it is determined that there is image deformation.

[0030] As an optional specific implementation manner, if there is no area difference, trailing length difference, and image deformation between the detected defect and the corresponding real defect, it is determined that there is no difference between the recognized defect and the corresponding real defect; otherwise, it is determined that there is a difference between the recognized defect and the corresponding real defect.

[0031] S400. If the ratio of the number of defective defects corresponding to all surface images of the laser-etched label paper in A to the number of real defects is greater than or equal to the preset ratio threshold, obtain the movement speed adjustment amount of the laser etching device according to the defective defects, and obtain the target movement speed of the laser etching device in the current time period according to the movement speed adjustment amount and V0.

[0032] Optionally, the preset ratio threshold is an empirical value. For example, the preset ratio threshold is 10%. If the ratio of the number of defective spots with differences in the surface images of all laser-etched label papers in A to the number of actual defective spots is less than the preset ratio threshold, the movement speed of the laser etching equipment is no longer adjusted, and it is determined that the laser etching speed matches the parameters of the image acquisition device.

[0033] As a preferred specific embodiment, as Figure 3 shown, obtaining the movement speed adjustment amount of the laser etching equipment according to the defective spots with differences includes: S410. For the i-th defective spot D i , obtain the area difference between D i and the corresponding actual defective spot, and substitute the area difference into the first preset model to obtain the first movement speed adjustment amount ΔV i corresponding to D i,1 ; the first preset model includes the relationship between the area difference and the movement speed adjustment amount; the value range of i is from 1 to n, and n is the number of defective spots with differences.

[0034] In this embodiment, n is also the number of defective spots with differences in the surface images of all laser-etched label papers in A.

[0035] In this embodiment, if the movement speed of the laser etching equipment does not match the parameters of the image collector, then there is an area difference between D i and the corresponding actual defective spot. As an optional specific embodiment, the first preset model is obtained based on experience. As an optional specific embodiment, the obtaining process of the first preset model includes: S411. Obtain the areas of the defective spots in the surface images of the laser-etched label papers corresponding to different sample speeds.

[0036] Optionally, the number of different sample speeds is large enough to cover the full speed range of the laser etching equipment, so as to improve the generalization and accuracy of the subsequent obtained first preset model; and except for the different speeds, other variables are the same as the variables corresponding to the above historical etching time period. For example, the label paper materials are the same, the relevant parameters of the image acquisition device (such as the exposure time, etc.) are the same, and the relevant parameters of the laser etching equipment (such as the laser frequency and vibration conditions, etc.) are also the same.

[0037] S412. Obtain the areas of the defective spots in the surface images of the laser-etched label papers obtained by static shooting corresponding to different sample speeds.

[0038] S413. Obtain the area difference of defects in the surface images of the laser-etched label paper corresponding to different sample speeds and the corresponding speed adjustment amounts. The area difference of defects in the surface images of the laser-etched label paper corresponding to the adjusted speed corresponding to any sample speed is less than or equal to the preset area difference threshold, and the adjusted speed corresponding to any sample speed is the sum of the sample speed and the corresponding speed adjustment amount.

[0039] In this embodiment, the area difference of any defect in the surface image of the laser-etched label paper corresponding to any sample speed is |the area of the defect - the true area| / the true area × 100%, and the true area is the area of the corresponding defect in the surface image of the laser-etched label paper obtained by the static shooting method corresponding to the sample speed.

[0040] Optionally, the speed adjustment amounts corresponding to different sample speeds are obtained through experiments.

[0041] S414. Obtain the relationship between the area difference of defects and the speed adjustment amount through data fitting, and obtain the first preset model.

[0042] Those skilled in the art know that the process of data fitting is a prior art and will not be elaborated here.

[0043] Based on S411 - S414, a relatively accurate second preset model can be obtained.

[0044] S420. Obtain D i The trailing length difference compared to the corresponding true defect, and substitute the trailing length difference into the second preset model to obtain D i The corresponding second movement speed adjustment amount ΔV i,2 ; The second preset model includes the relationship between the trailing length difference and the movement speed adjustment amount.

[0045] In this embodiment, if the movement speed of the laser etching equipment does not match the parameters of the image collector, then D i There is a trailing length difference from the corresponding true defect. As an optional specific implementation, the second preset model is obtained based on experience; as an optional specific implementation, the process of obtaining the second preset model includes: S421. Obtain the trailing lengths of defects in the surface images of the laser-etched label paper corresponding to different sample speeds.

[0046] Optionally, the number of different sample speeds is relatively large, which can cover the full speed range of the laser etching equipment to improve the generalization and accuracy of the first preset model obtained subsequently; and except for the different speeds, other variables are the same as those corresponding to the above historical etching time periods. For example, the label paper materials are the same, the relevant parameters of the image acquisition device (such as exposure time, etc.) are the same, and the relevant parameters of the laser etching equipment (such as laser frequency and vibration conditions, etc.) are also the same.

[0047] S422. Obtain the trailing length of the defects in the surface image of the laser-etched label paper obtained by the static shooting method corresponding to different sample speeds.

[0048] S423. Obtain the trailing length difference of the defects in the surface image of the laser-etched label paper corresponding to different sample speeds and the corresponding speed adjustment amount; the trailing length difference of the defects in the surface image of the laser-etched label paper corresponding to any sample speed is the difference between the trailing length of the defects in the surface image of the laser-etched label paper corresponding to this sample speed and the trailing length of the defects in the surface image of the laser-etched label paper obtained by the corresponding static shooting method; the trailing length difference of the defects in the surface image of the laser-etched label paper corresponding to the adjusted speed corresponding to any sample speed is less than or equal to the preset trailing length difference threshold, and the adjusted speed corresponding to any sample speed is the sum of this sample speed and the corresponding speed adjustment amount.

[0049] Optionally, the speed adjustment amounts corresponding to different sample speeds are obtained by experiments.

[0050] S424. Obtain the relationship between the trailing length difference of the defects and the speed adjustment amount by data fitting to obtain the second preset model.

[0051] Those skilled in the art know that the process of data fitting is a prior art and will not be elaborated here.

[0052] Based on S421 - S424, a relatively accurate second preset model can be obtained.

[0053] S430. Obtain D i Compared with the image deformation amount of the corresponding real defect, and substitute this image deformation amount into the third preset model to obtain D i The corresponding third motion speed adjustment amount ΔV i,3 ; the third preset model includes the relationship between the image deformation amount and the motion speed adjustment amount.

[0054] In this embodiment, if the motion speed of the laser etching equipment does not match the parameters of the image collector, then D iThere is an image deformation amount with respect to the corresponding true defect. As an optional specific implementation manner, the third preset model is obtained based on experience; as an optional specific implementation manner, the obtaining process of the third preset model includes: S431. Obtain the image deformation amount of the surface image of the laser-etched label paper corresponding to different sample speeds with respect to the surface image of the laser-etched label paper obtained by using a static shooting method.

[0055] Optionally, the number of different sample speeds is large, which can cover the full speed range of the laser etching equipment to improve the generalization and accuracy of the subsequent obtained first preset model; and except for the different speeds, other variables are the same as the variables corresponding to the above historical etching time period. For example, the label paper materials are the same, the relevant parameters of the image acquisition device (such as the exposure time, etc.) are the same, and the relevant parameters of the laser etching equipment (such as the laser frequency and vibration conditions, etc.) are also the same.

[0056] S432. Obtain the speed adjustment amount corresponding to different sample speeds; the image deformation amount of the surface image of the laser-etched label paper corresponding to the adjusted speed corresponding to any sample speed with respect to the surface image of the laser-etched label paper obtained by using a static shooting method is less than or equal to the preset image deformation amount threshold, and the adjusted speed corresponding to any sample speed is the sum of the sample speed and the corresponding speed adjustment amount.

[0057] Optionally, the speed adjustment amounts corresponding to different sample speeds are obtained through experiments.

[0058] S433. Obtain the relationship between the image deformation amount difference and the speed adjustment amount through data fitting to obtain the third preset model.

[0059] Those skilled in the art know that the process of data fitting is a prior art and will not be elaborated here.

[0060] Based on S431 - S433, a relatively accurate third preset model can be obtained.

[0061] S440. Obtain the corresponding motion speed adjustment amount ΔV i,1 、ΔV i,2 and ΔV i,3 for D i . i .

[0062] Optionally, obtain ΔV i through a weighted summation formula, where the weights corresponding to ΔV i,1 , ΔV i,2 and ΔV i,3 are empirical values. Optionally, ΔV i,1 , ΔV i,2 and ΔV i,3The corresponding weights are all 1 / 3, or ΔV i,2 The corresponding weight is 1 / 2, ΔV i,1 and ΔV i,3 The corresponding weights are all 1 / 4.

[0063] S450, according to {ΔV1, ΔV2, …, ΔV i , …, ΔV n} to obtain the motion speed adjustment amount ΔV of the laser etching equipment.

[0064] Optionally, ΔV = ∑ n i=1 ΔV i / n.

[0065] Based on S410 - S450, it is possible to obtain a relatively accurate motion speed adjustment amount ΔV of the laser etching equipment.

[0066] In this embodiment, after obtaining the target motion speed of the laser etching equipment in the current time period, the motion speed of the laser etching equipment is updated, and it is again determined whether there is a difference between the defects identified by the updated target defect recognition model and the corresponding real defects in a manner similar to S100 - S200. If the ratio of the number of defective defects to the number of corresponding real defects is greater than or equal to the preset ratio threshold, the motion speed of the laser etching equipment is continuously updated until the ratio of the number of defective defects to the number of corresponding real defects is less than the preset ratio threshold, so as to achieve the matching of the laser etching speed and the parameters of the image acquisition device.

[0067] This embodiment obtains a set of surface images of the laser etching label paper collected during the historical etching time period. These images are collected when the motion speed of the laser etching equipment is V0. By comparing the defects in these images with the defects existing in the surface images of the laser etching label paper obtained by the static shooting method, it can be determined whether the images collected when the motion speed of the laser etching equipment is V0 are distorted; for example, if the ratio of the number of defective defects corresponding to all the surface images of the laser etching label paper in A to the number of real defects is greater than or equal to the preset ratio threshold, then it is determined that the images collected when the motion speed of the laser etching equipment is V0 are distorted. In this case, the motion speed adjustment amount of the laser etching equipment is obtained according to the defective defects to adjust V0 to obtain the motion speed of the laser etching equipment that matches the parameters of the image acquisition device. Thus, this embodiment improves the matching of the laser etching speed and the parameters of the image acquisition device, and can avoid the problem of image distortion in the images collected by the image acquisition device caused by the mismatch between the laser etching speed and the parameters of the image acquisition device, which is beneficial to accurately detecting defects based on the images collected by the image acquisition device.

[0068] Although some specific embodiments of the present invention have been described in detail by way of examples, those skilled in the art should understand that the above examples are for illustrative purposes only and not for limiting the scope of the present invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for detecting surface defects of laser-etched label paper based on machine vision, characterized in that, It includes the following steps: S100. Obtain a set of surface images A of the laser-etched label paper collected during the historical etching time period; the historical etching time period includes several image acquisition moments, A includes the surface images of the laser-etched label paper collected at each image acquisition moment, and the moving speed of the laser etching equipment during the historical etching time period is V0; S200. Input the surface images of the laser-etched label paper in A into the trained target defect recognition model respectively to obtain the defect recognition results of each surface image of the laser-etched label paper in A; S300. For the defect recognition result of any surface image of the laser-etched label paper in A, if the defect recognition result includes defects, compare the defects recognized by the target defect recognition model with the corresponding real defects to obtain the defects in the defects recognized by the target defect recognition model that are different from the corresponding real defects; the real defects are the defects existing in the surface image of the laser-etched label paper obtained by the corresponding static shooting method; S400. If the ratio of the number of different defects corresponding to all surface images of the laser-etched label paper in A to the number of real defects is greater than or equal to the preset ratio threshold, obtain the moving speed adjustment amount of the laser etching equipment according to the different defects, and obtain the target moving speed of the laser etching equipment in the current time period according to the moving speed adjustment amount and V0.

2. The method for detecting surface defects of laser-etched label paper based on machine vision according to claim 1, wherein Obtaining the moving speed adjustment amount of the laser etching equipment according to the different defects includes: S410. For the i-th defective flaw D with a difference i , obtain D i the area difference compared to the corresponding true defective flaw, and substitute this area difference into the first preset model to obtain D i the corresponding first motion speed adjustment amount ΔV i,1 ; the first preset model includes the relationship between the area difference and the motion speed adjustment amount; the value range of i is from 1 to n, where n is the number of defective flaws with differences; S420, obtain D i Obtain the trailing length difference compared with the corresponding true defect, and substitute the trailing length difference into the second preset model to obtain D i The corresponding second motion speed adjustment amount ΔV i,2 ; The second preset model includes the relationship between the trailing length difference and the motion speed adjustment amount; S430, Obtain D i Compared with the image deformation amount of the corresponding real defect, substitute the image deformation amount into the third preset model to obtain D i The corresponding third motion speed adjustment amount ΔV i,3 ; The third preset model includes the relationship between the image deformation amount and the motion speed adjustment amount; S440, according to ΔV i,1 , ΔV i,2 and ΔV i,3 obtain D i corresponding motion speed adjustment amount ΔV i ; S450, obtain the motion speed adjustment amount ΔV of the laser etching equipment according to {ΔV1, ΔV2, …, ΔV i , …, ΔV n}.

3. The method for detecting surface defects of laser-etched label paper based on machine vision according to claim 1, wherein The obtaining process of V0 includes: S110. Obtain the first condition that the moving speed of the laser etching equipment satisfies according to the line frequency, pixel resolution and single-line field of view width of the image collector; the first condition includes: V ≤ f×W / p, where V is the moving speed of the laser etching equipment, f is the line frequency of the image collector, W is the single-line field of view width, and p is the pixel resolution; S120. Obtain the second condition that the moving speed of the laser etching equipment satisfies according to the exposure time, pixel size and optical magnification of the image collector; the second condition includes: V ≤ s / (T×M), where s is the pixel size, T is the exposure time of the image collector, and M is the optical magnification; S130. Obtain the third condition that the moving speed of the laser etching equipment satisfies according to the minimum detected defect size, the exposure time of the image collector and the minimum number of pixels that the defect spans; the third condition includes: V ≤ d / (T×q), where d is the minimum detected defect size and q is the minimum number of pixels that the defect spans; S140. Determine a moving speed that satisfies the first condition, the second condition and the third condition as V0.

4. The method for detecting surface defects of laser-etched label paper based on machine vision according to claim 2, wherein The obtaining process of the first preset model includes: S411. Obtain the areas of the defects in the surface images of the laser-etched label paper corresponding to different sample speeds; S412. Obtain the areas of the defects in the surface images of the laser-etched label paper obtained by the static shooting method corresponding to different sample speeds; S413. Obtain the area difference of defects in the surface image of the laser-etched label paper corresponding to different sample speeds and the corresponding speed adjustment amounts; the area difference of defects in the surface image of the laser-etched label paper corresponding to the adjusted speed for any sample speed is less than or equal to the preset area difference threshold, and the adjusted speed corresponding to any sample speed is the sum of the sample speed and the corresponding speed adjustment amount. S414. Obtain the relationship between the area difference of defects and the speed adjustment amount by data fitting to obtain the first preset model.

5. The method for detecting surface defects of laser-etched label paper based on machine vision according to claim 2, wherein The process of obtaining the second preset model includes: S421. Obtain the trailing length of defects in the surface image of the laser-etched label paper corresponding to different sample speeds. S422. Obtain the trailing length of defects in the surface image of the laser-etched label paper obtained by static shooting corresponding to different sample speeds. S423. Obtain the trailing length difference of defects in the surface image of the laser-etched label paper corresponding to different sample speeds and the corresponding speed adjustment amounts; the trailing length difference of defects in the surface image of the laser-etched label paper corresponding to any sample speed is the difference between the trailing length of defects in the surface image of the laser-etched label paper corresponding to the sample speed and the trailing length of defects in the surface image of the laser-etched label paper obtained by static shooting corresponding thereto; the trailing length difference of defects in the surface image of the laser-etched label paper corresponding to the adjusted speed for any sample speed is less than or equal to the preset trailing length difference threshold, and the adjusted speed corresponding to any sample speed is the sum of the sample speed and the corresponding speed adjustment amount. S424. Obtain the relationship between the trailing length difference of defects and the speed adjustment amount by data fitting to obtain the second preset model.

6. The method for detecting surface defects of laser-etched label paper based on machine vision according to claim 2, wherein The process of obtaining the third preset model includes: S431. Obtain the image deformation amount of the surface image of the laser-etched label paper corresponding to different sample speeds compared with the surface image of the laser-etched label paper obtained by static shooting corresponding thereto. S432. Obtain the speed adjustment amounts corresponding to different sample speeds; the image deformation amount of the surface image of the laser-etched label paper corresponding to the adjusted speed for any sample speed compared with the surface image of the laser-etched label paper obtained by static shooting corresponding thereto is less than or equal to the preset image deformation amount threshold, and the adjusted speed corresponding to any sample speed is the sum of the sample speed and the corresponding speed adjustment amount. S433. Obtain the relationship between the image deformation amount difference and the speed adjustment amount by data fitting to obtain the third preset model.

7. The method for detecting surface defects of laser-etched label paper based on machine vision according to claim 2, wherein Obtain ΔV through the weighted summation formula i .

8. The method for detecting surface defects of laser-etched label paper based on machine vision according to claim 2, wherein ΔV = ∑ n i=1 ΔV i / n.

Images