Laser energy evaluation method and device based on image processing

Abstract

The application discloses a laser energy evaluation method and device based on image processing, and relates to the technical field of lasers.The method comprises the following steps: capturing a first image set, a second image set and a third image set; using an edge algorithm to perform edge extraction on the second image set, obtaining an irradiation area, and collecting light intensity distribution information of the irradiation area; performing pixel matrix processing on the first image set and the third image set, and outputting a similarity probability distribution of a first pixel matrix and a third pixel matrix; inputting a laser energy evaluation model according to the light intensity distribution information and the similarity probability distribution, and obtaining a first laser energy evaluation result; and feeding back and optimizing parameters of a measured laser according to the first laser energy evaluation result.The technical problem that laser energy is difficult to be accurately evaluated in the prior art is solved, the technical effect that laser energy is accurately evaluated is achieved by comparing the pixel matrix similarity of the target material surface before and after irradiation and combining the laser energy evaluation model.

Description

Technical Field

[0001] This invention relates to the field of laser technology, and more specifically to a laser energy assessment method and apparatus based on image processing. Background Technology

[0002] In today's rapidly developing technological era, laser technology, as a cutting-edge and widely applied technology, has penetrated into various fields such as industrial manufacturing, medical health, and scientific research. With its high energy density, high directionality, and high monochromaticity, lasers have demonstrated enormous potential and value in materials processing, medical surgery, and information transmission. However, with the continuous popularization of laser technology and the increasing demand for its applications, how to accurately assess laser energy and ensure the stable and reliable performance of laser equipment has become a crucial problem that urgently needs to be solved in the field of laser technology. Traditional laser energy assessment methods often rely on complex physical measurement equipment and cumbersome data processing procedures, which are not only costly but also complex to operate, making it difficult to meet the needs of modern industry for efficient and accurate assessment. Summary of the Invention

[0003] This application provides a laser energy assessment method and apparatus based on image processing, which solves the technical problem of difficulty in accurately assessing laser energy in the prior art.

[0004] In view of the above problems, this application provides a laser energy evaluation method and apparatus based on image processing.

[0005] A first aspect of this application provides a laser energy estimation method based on image processing, the method comprising:

[0006] According to the image acquisition device, a first image set, a second image set, and a third image set are captured. The first image set is a surface image of the test target material before laser irradiation by the laser under test; the second image set is an image generated when the laser under test irradiates the test target material; and the third image set is a surface image of the test target material after laser irradiation by the laser under test. An edge detection algorithm is used to extract edges from the second image set to obtain the irradiated area, and the light intensity distribution information of the irradiated area is collected. The first and third image sets are processed into pixel matrices of the irradiated area, and a similarity probability distribution of the first and third pixel matrices is output. The light intensity distribution information and the similarity probability distribution are input into a laser energy assessment model. The laser energy assessment model uses the similarity probability distribution as an adjustment factor and analyzes the light intensity distribution information to obtain a first laser energy assessment result. The parameters of the laser under test are optimized based on the first laser energy assessment result.

[0007] A second aspect of this application provides a laser energy assessment device based on image processing, the device comprising:

[0008] The system includes: an image acquisition module for capturing a first image set, a second image set, and a third image set using an image acquisition device; the first image set being surface images of the test target material before laser irradiation; the second image set being images generated by the laser under test irradiating the test target material; and the third image set being surface images of the test target material after laser irradiation; an information acquisition module for extracting edges from the second image set using an edge algorithm to obtain the irradiated area and acquiring light intensity distribution information of the irradiated area; a matrix processing module for performing pixel matrix processing on the first and third image sets to output a similarity probability distribution of the first and third pixel matrices; an energy evaluation module for inputting the light intensity distribution information and the similarity probability distribution into a laser energy evaluation model, where the laser energy evaluation model uses the similarity probability distribution as an adjustment factor and analyzes the light intensity distribution information to obtain a first laser energy evaluation result; and an optimization module for performing feedback optimization of the parameters of the laser under test based on the first laser energy evaluation result.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, an image acquisition device captures a first image set, a second image set, and a third image set. The first image set represents the surface image of the test target before laser irradiation; the second image set represents the image generated when the laser under test irradiates the test target; and the third image set represents the surface image of the test target after laser irradiation. Next, an edge detection algorithm is used to extract edges from the second image set to obtain the irradiated area and collect the light intensity distribution information of the irradiated area. Simultaneously, the first and third image sets are processed into pixel matrices of the irradiated area, outputting the similarity probability distribution of the first and third pixel matrices. Then, the light intensity distribution information and the similarity probability distribution are input into a laser energy assessment model. The laser energy assessment model uses the similarity probability distribution as an adjustment factor and analyzes the light intensity distribution information to obtain a first laser energy assessment result. Finally, the parameters of the laser under test are optimized based on the first laser energy assessment result. This solves the technical problem of accurately assessing laser energy in existing technologies. By comparing the pixel matrix similarity of the target surface before and after irradiation, combined with the laser energy assessment model, a precise laser energy assessment effect is achieved. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic flowchart of a laser energy assessment method based on image processing provided in an embodiment of this application.

[0013] Figure 2 This is a schematic diagram of the structure of a laser energy assessment device based on image processing provided in an embodiment of this application.

[0014] Figure labeling: Image acquisition module 11, Information acquisition module 12, Matrix processing module 13, Energy assessment module 14, Optimization module 15. Detailed Implementation

[0015] This application solves the technical problem of accurately evaluating laser energy in the prior art by providing a laser energy evaluation method and apparatus based on image processing.

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0017] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0018] Example 1, as Figure 1 As shown, this application provides a laser energy evaluation method based on image processing, wherein the method includes:

[0019] According to the image acquisition device, a first image set, a second image set, and a third image set are captured. The first image set is a surface image of the test target material before the laser under test is irradiated with laser light. The second image set is an image generated by the laser under test irradiating the test target material. The third image set is a surface image of the test target material after the laser under test is irradiated with laser light.

[0020] Before the laser under test irradiates the test target, an image acquisition device (such as a high-resolution camera) is used to capture an initial surface image of the test target, forming a first image set, which serves as a benchmark reference for subsequent analysis. The laser under test is then activated to irradiate the test target, and the image acquisition device continuously captures real-time images during the laser irradiation process, forming a second image set. The second image set illustrates the dynamic process of the interaction between the laser and the target. After the laser under test completes the laser irradiation, the laser output is immediately stopped, and a waiting period is allowed (depending on the target material and laser characteristics) to ensure that the surface changes of the target stabilize. The image acquisition device is then restarted to capture surface images of the test target after irradiation, forming a third image set. The third image set is used to evaluate the long-term effects of laser irradiation on the target.

[0021] An edge detection algorithm is used to extract edges from the second image set to obtain the illumination area, and the light intensity distribution information of the illumination area is collected.

[0022] During laser energy assessment, edge extraction is performed on the second image set to identify locations where significant changes in brightness or color occur. These locations typically correspond to the boundaries of objects or regions; in the context of laser irradiation, these are the boundaries of the areas where the laser interacts with the target. Specifically, edge detection algorithms, such as the Sobel operator, Canny edge detector, Prewitt operator, and Roberts operator, are used to perform edge detection on each image in the second image set. These algorithms analyze the changes in pixel values ​​and their neighborhood pixels, identifying edges through mathematical methods such as gradient calculation or second derivative calculation. After edge detection, a series of discrete edge points or line segments may be obtained. These discrete edge points or line segments need to be connected into a continuous contour line using an edge connection algorithm to identify the complete irradiated area. Within the irradiated area, the brightness value of each pixel is measured and converted into a light intensity value to obtain the light intensity distribution information of the irradiated area.

[0023] The first image set and the third image set are processed into pixel matrices of the illumination area, and the similarity probability distribution of the first pixel matrix and the third pixel matrix is ​​output.

[0024] Based on the defined illumination area, for each image in the first and third image sets, the pixel values ​​of its illumination area are converted into a two-dimensional matrix (i.e., a pixel matrix). Each element in the matrix corresponds to a pixel in the image, and its value can be the grayscale value of the pixel. A suitable similarity metric (such as Euclidean distance, Manhattan distance, cosine similarity, Pearson correlation coefficient, etc.) is selected to calculate the similarity between the first and third pixel matrices. The similarity calculation results are then converted into a probability distribution, i.e., a similarity probability distribution. This probability distribution reflects the overall similarity between the illumination areas in the first and third image sets and is used to evaluate the changes in the target material before and after laser irradiation.

[0025] Furthermore, the similarity probability distribution between the first pixel matrix and the third pixel matrix is ​​calculated using a structural similarity index. The method includes:

[0026] Structural similarity index is a metric used to evaluate the similarity between two images, taking into account the brightness, contrast, and structural information of the images. Where SSIM is the similarity probability distribution between the first pixel matrix and the third pixel matrix, μ M1 It is the average pixel value of the first pixel matrix M1, μ M3 It is the average pixel value of the third pixel matrix M3, σ M1 It is the variance of the first pixel matrix M1, σ M3 It is the variance of the third pixel matrix M3, σ M1M3 It is the covariance of the first pixel matrix M1 and the third pixel matrix M3, and c1 and c2 are small constants used for calculating the stable probability, c1=(k1L) 2 c2=(k2L) 2 L is the maximum value of the image bit depth within the dynamic range [0, 255].

[0027] use Calculate the similarity probability distribution between the first pixel matrix and the third pixel matrix, where μ M1 It is the average pixel value of the first pixel matrix M1, μ M3 σ is the average pixel value of the third pixel matrix M3, reflecting the brightness information of the image; M1 It is the variance of the first pixel matrix M1, σ M3 σ is the variance of the third pixel matrix M3, used to represent the contrast information of the image; M1M3is the covariance of the first pixel matrix M1 and the third pixel matrix M3, reflecting the common changes in pixel values ​​of the two matrices, i.e., structural information; c1 and c2 are small constants used for calculating the stable probability to avoid the case where the denominator is zero. c1 and c2 are usually calculated based on the dynamic range of the image and parameters k1 and k2, where L is the dynamic range of the image pixel values ​​(for an 8-bit image, L = 255), and k1 and k2 are default constants, such as k1 = 0.01 and k2 = 0.03.

[0028] The laser energy assessment model is input based on the light intensity distribution information and the similarity probability distribution. The laser energy assessment model uses the similarity probability distribution as an adjustment factor and analyzes the light intensity distribution information to obtain the first laser energy assessment result.

[0029] In the process of laser energy assessment, the light intensity distribution information and similarity probability distribution are input into the laser energy assessment model. The laser energy assessment model uses the similarity probability distribution as an adjustment factor, analyzes the light intensity distribution information, and outputs the first laser energy assessment result.

[0030] Furthermore, the laser energy assessment model uses the similarity probability distribution as an adjustment factor and analyzes the light intensity distribution information to obtain a first laser energy assessment result. The method includes:

[0031] The light intensity distribution information is obtained, wherein the light intensity distribution information includes the light intensity distribution area and the light intensity distribution shape of the irradiated area; the laser energy assessment model performs energy conversion analysis on the light intensity distribution information, and outputs the energy value of each pixel, the cumulative energy value of all pixels, the cumulative energy value of edge pixels, and the energy density per unit area; the energy value of each pixel, the cumulative energy value of all pixels, the cumulative energy value of edge pixels, and the energy density per unit area are calculated using the similarity probability distribution as an adjustment factor to obtain the first laser energy assessment result.

[0032] The light intensity distribution information includes the area and shape of the light intensity distribution in the irradiated region. The area refers to the specific region on the target material illuminated by the laser, i.e., the pixel area occupied by the light intensity distribution. The shape refers to the shape characteristics of the light intensity distribution area, such as circular, elliptical, or irregular. The acquired light intensity distribution information is input into the laser energy assessment model for energy conversion analysis. The model outputs the energy value of each pixel, the cumulative energy value of all pixels, the cumulative energy value of edge pixels, and the energy density per unit area. Using the similarity probability distribution as an adjustment factor, the energy values ​​of each pixel, the cumulative energy value of all pixels, the cumulative energy value of edge pixels, and the energy density per unit area are calculated to obtain the first laser energy assessment result.

[0033] Furthermore, the output includes the energy value of each pixel, the cumulative energy value of all pixels, the cumulative energy value of edge pixels, and the energy density per unit area.

[0034] Where E(x,y)=I(x,y)×C, E(x,y) is the energy value at pixel coordinates (x,y), and C is the conversion coefficient for converting light intensity value to energy value; E total =∑ (x,y)∈S I(x,y)×C,E total S is the accumulated energy value of all pixels, and S is the set of pixel coordinates after pixel matrix processing of the irradiated area; E edge S1 is the accumulated energy value of the edge pixels, and S1 is the set of edge pixel coordinates, where S1∈S; D is the energy density per unit area, A is the area of ​​each pixel, and N is the total number of pixels in the pixel coordinate set.

[0035] The energy value of each pixel can be calculated using E(x,y) = I(x,y) × C, where E(x,y) is the energy value at pixel coordinates (x,y), I(x,y) is the light intensity value of the pixel, and C is the conversion coefficient for converting the light intensity value to the energy value. The conversion coefficient depends on the specific parameters of the laser and the experimental conditions. The cumulative energy value of all pixels can be calculated using E... total =∑ (x,y)∈S E is obtained by calculating I(x,y)×C. total The accumulated energy value for all pixels is obtained by summing the energy values ​​of all pixels within the illumination area, where S is the set of pixel coordinates after pixel matrix processing of the illumination area; the accumulated energy value of edge pixels can be obtained through... E edge Calculations show that E edge The accumulated energy value for edge pixels is obtained by accumulating the energy of only the pixels in the edge pixel set S1, where S1 is the set of edge pixel coordinates, S1∈S; the energy density per unit area can be obtained through... The calculated energy density per unit area, D, is obtained by dividing the accumulated energy value of all pixels by the area of ​​the illuminated region. Since the illuminated region is discretized into a pixel matrix, its area can be approximated as the total number of pixels N multiplied by the area A of each pixel.

[0036] Furthermore, the expression for obtaining the first laser energy assessment result includes:

[0037]

[0038] Where k and λ are weighting factors used to adjust the importance of the cumulative energy value of edge pixels and the similarity probability distribution in the overall evaluation, and (1-SSIM) represents the inverse of similarity, which is used to strengthen the evaluation index when the image changes significantly. The greater the change in similarity, the greater its contribution to obtaining the first laser energy evaluation result.

[0039] First laser energy assessment result expression The cumulative energy value E of all pixels is combined. total The accumulated energy value E of edge pixels edge The laser energy is comprehensively evaluated using the similarity probability distribution SSIM and two weighting factors k and λ. This expression aims to more accurately reflect the impact of laser energy on the target material by adjusting the weights of different factors in the overall evaluation, i.e., the first laser energy evaluation result Energy.

[0040] The parameters of the laser under test are optimized based on the first laser energy assessment result.

[0041] Based on the first laser energy assessment results, the parameters of the laser under test, such as power, irradiation time, and focal size, are optimized through feedback. In turn, the performance of the laser is improved by adjusting various parameters to achieve higher energy efficiency, more stable output, or energy distribution that better meets the needs of specific applications.

[0042] Furthermore, the methods also include:

[0043] The initial control parameters of the laser under test are obtained, including laser power, irradiation time and focal size; the parameters of the laser under test are optimized based on the difference between the first laser energy assessment result and the preset laser energy assessment result, and the optimized control parameters are obtained.

[0044] Preferably, the initial control parameters of the laser under test are obtained, including laser power, irradiation time, and focal size. Laser power indicates the energy intensity output by the laser, irradiation time indicates the length of time the laser beam irradiates the target, and focal size refers to the size of the focal point formed by the laser beam on the target surface. The first laser energy assessment result is compared with the preset laser energy assessment result, which is set based on experimental requirements and industry standards. Based on the difference between the first laser energy assessment result and the preset laser energy assessment result, the parameters of the laser under test are adjusted, such as increasing laser power, extending irradiation time, and decreasing focal size. The control parameters are adjusted through multiple iterations until the difference between the first laser energy assessment result and the preset target reaches an acceptable range, and the optimized control parameters are obtained.

[0045] Furthermore, the methods also include:

[0046] A beam fitter is set up and disposed at the output end of the laser under test; the beam fitter is driven to re-evaluate the laser energy of the laser under test and obtain a second laser energy evaluation result; the parameters of the laser under test are optimized based on the first laser energy evaluation result and the second laser energy evaluation result.

[0047] Preferably, based on the characteristics of the laser under test and the evaluation requirements, a suitable beam fitter is selected and installed on the output end of the laser under test to ensure that it can effectively receive and adjust the laser beam. The laser beam is adjusted by driving the beam fitter (e.g., changing the beam shape, size, or direction), and then the adjusted laser beam is allowed to irradiate the target, and a second laser energy assessment result is obtained. The second laser energy assessment result can reflect the influence of the beam fitter on the laser energy distribution. The first laser energy assessment result and the second laser energy assessment result are compared and analyzed. Based on the comparison analysis result, i.e., the difference between the first laser energy assessment result and the second laser energy assessment result, the parameters of the laser under test are adjusted and optimized. The control parameters are adjusted through multiple iterations until the difference between the first laser energy assessment result and the second laser energy assessment result reaches an acceptable range, and the optimized control parameters are obtained.

[0048] In summary, the embodiments of this application have at least the following technical effects:

[0049] First, an image acquisition device captures a first image set, a second image set, and a third image set. The first image set represents the surface image of the test target before laser irradiation; the second image set represents the image generated when the laser under test irradiates the test target; and the third image set represents the surface image of the test target after laser irradiation. Next, an edge detection algorithm is used to extract edges from the second image set to obtain the irradiated area and collect the light intensity distribution information of the irradiated area. Simultaneously, the first and third image sets are processed into pixel matrices of the irradiated area, outputting the similarity probability distribution of the first and third pixel matrices. Then, the light intensity distribution information and the similarity probability distribution are input into a laser energy assessment model. The laser energy assessment model uses the similarity probability distribution as an adjustment factor and analyzes the light intensity distribution information to obtain a first laser energy assessment result. Finally, the parameters of the laser under test are optimized based on the first laser energy assessment result. This solves the technical problem of accurately assessing laser energy in existing technologies. By comparing the pixel matrix similarity of the target surface before and after irradiation, combined with the laser energy assessment model, a precise laser energy assessment effect is achieved.

[0050] Example 2, based on the same inventive concept as the image processing-based laser energy assessment method in the foregoing examples, such as... Figure 2 As shown, this application provides a laser energy assessment device based on image processing, wherein the device includes:

[0051] Image acquisition module 11, configured to capture a first image set, a second image set, and a third image set according to an image acquisition device, wherein the first image set is a surface image of the test target material before laser irradiation by the laser under test, the second image set is an image generated by the laser under test irradiating the test target material, and the third image set is a surface image of the test target material after laser irradiation by the laser under test; information acquisition module 12, configured to perform edge extraction on the second image set using an edge algorithm to obtain the irradiation area and acquire the light intensity distribution information of the irradiation area; matrix processing module. 13. The matrix processing module 13 is used to perform pixel matrix processing on the first image set and the third image set for the illumination area, and output the similarity probability distribution of the first pixel matrix and the third pixel matrix; the energy evaluation module 14 is used to input the laser energy evaluation model according to the light intensity distribution information and the similarity probability distribution, the laser energy evaluation model uses the similarity probability distribution as an adjustment factor and analyzes the light intensity distribution information to obtain the first laser energy evaluation result; the optimization module 15 is used to perform feedback optimization on the parameters of the laser under test according to the first laser energy evaluation result.

[0052] Furthermore, the matrix processing module 13 is used to perform the following method:

[0053] Where SSIM is the similarity probability distribution between the first pixel matrix and the third pixel matrix, μ M1 It is the average pixel value of the first pixel matrix M1, μ M3 It is the average pixel value of the third pixel matrix M3, σ M1 It is the variance of the first pixel matrix M1, σ M3 It is the variance of the third pixel matrix M3, σ M1M3 It is the covariance of the first pixel matrix M1 and the third pixel matrix M3, and c1 and c2 are small constants used for calculating the stable probability, c1=(k1L) 2 c2=(k2L) 2 L is the maximum value of the image bit depth within the dynamic range [0, 255].

[0054] Furthermore, the energy assessment module 14 is used to perform the following method:

[0055] The light intensity distribution information is obtained, wherein the light intensity distribution information includes the light intensity distribution area and the light intensity distribution shape of the irradiated area; the laser energy assessment model performs energy conversion analysis on the light intensity distribution information, and outputs the energy value of each pixel, the cumulative energy value of all pixels, the cumulative energy value of edge pixels, and the energy density per unit area; the energy value of each pixel, the cumulative energy value of all pixels, the cumulative energy value of edge pixels, and the energy density per unit area are calculated using the similarity probability distribution as an adjustment factor to obtain the first laser energy assessment result.

[0056] Furthermore, the energy assessment module 14 is used to perform the following method:

[0057] Where E(x,y)=I(x,y)×C, E(x,y) is the energy value at pixel coordinates (x,y), and C is the conversion coefficient for converting light intensity value to energy value; E total =∑ (x,y)∈S I(x,y)×C,E total S is the accumulated energy value of all pixels, and S is the set of pixel coordinates after pixel matrix processing of the irradiated area; E edge S1 is the accumulated energy value of the edge pixels, and S1 is the set of edge pixel coordinates, where S1∈S; D is the energy density per unit area, A is the area of ​​each pixel, and N is the total number of pixels in the pixel coordinate set.

[0058] Furthermore, the energy assessment module 14 is used to perform the following method:

[0059] The expression for the first laser energy assessment result: Where k and λ are weighting factors used to adjust the importance of the cumulative energy value of edge pixels and the similarity probability distribution in the overall evaluation, and (1-SSIM) represents the inverse of similarity, which is used to strengthen the evaluation index when the image changes significantly. The greater the change in similarity, the greater its contribution to obtaining the first laser energy evaluation result.

[0060] Furthermore, the optimization module 15 is used to perform the following method:

[0061] The initial control parameters of the laser under test are obtained, including laser power, irradiation time and focal size; the parameters of the laser under test are optimized based on the difference between the first laser energy assessment result and the preset laser energy assessment result, and the optimized control parameters are obtained.

[0062] Furthermore, the optimization module 15 is used to perform the following method:

[0063] A beam fitter is set up and disposed at the output end of the laser under test; the beam fitter is driven to re-evaluate the laser energy of the laser under test and obtain a second laser energy evaluation result; the parameters of the laser under test are optimized based on the first laser energy evaluation result and the second laser energy evaluation result.

[0064] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0065] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0066] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A laser energy assessment method based on image processing, characterized in that, The method includes: According to the image acquisition device, a first image set, a second image set, and a third image set are captured. The first image set is a surface image of the test target material before the laser under test is irradiated with laser light. The second image set is an image generated by the laser under test irradiating the test target material. The third image set is a surface image of the test target material after the laser under test is irradiated with laser light. An edge algorithm is used to extract edges from the second image set to obtain the illuminated area, and the light intensity distribution information of the illuminated area is collected. The first image set and the third image set are processed into pixel matrix representations of the illumination regions, and the similarity probability distributions of the first pixel matrix and the third pixel matrix are output. The laser energy assessment model is input based on the light intensity distribution information and the similarity probability distribution. The laser energy assessment model uses the similarity probability distribution as an adjustment factor and analyzes the light intensity distribution information to obtain the first laser energy assessment result. The parameters of the laser under test are optimized based on the first laser energy assessment result. The laser energy assessment model uses the similarity probability distribution as an adjustment factor and analyzes the light intensity distribution information to obtain a first laser energy assessment result. The method includes: The light intensity distribution information is obtained, wherein the light intensity distribution information includes the light intensity distribution area and the light intensity distribution shape of the irradiated area; The laser energy assessment model performs energy conversion analysis on the light intensity distribution information and outputs the energy value of each pixel, the cumulative energy value of all pixels, the cumulative energy value of edge pixels, and the energy density per unit area. Using the similarity probability distribution as an adjustment factor, the energy value of each pixel, the cumulative energy value of all pixels, the cumulative energy value of edge pixels, and the energy density per unit area are calculated to obtain the first laser energy assessment result.

2. The laser energy assessment method based on image processing as described in claim 1, characterized in that, The similarity probability distribution between the first pixel matrix and the third pixel matrix is ​​calculated using a structural similarity index. The method includes: in, It is the similarity probability distribution between the first pixel matrix and the third pixel matrix. It is the first pixel matrix The average pixel value, It is the third pixel matrix The average pixel value, It is the first pixel matrix variance It is the third pixel matrix variance It is the first pixel matrix and the third pixel matrix covariance, and It is a small constant used for calculating stable probability. , It is based on the maximum value of the image bit depth within the dynamic range [0, 255].

3. The laser energy assessment method based on image processing as described in claim 1, characterized in that, Output the energy value of each pixel, the cumulative energy value of all pixels, the cumulative energy value of edge pixels, and the energy density per unit area; in, In pixel coordinates Energy value, This is the conversion factor for converting light intensity values ​​into energy values; The cumulative energy value for all pixels. This is the set of pixel coordinates after pixel matrixing of the irradiated area; This represents the accumulated energy value of the edge pixels. The set of edge pixel coordinates ; Energy density per unit area The area of ​​each pixel, It is the total number of pixels in the set of pixel coordinates.

4. The laser energy assessment method based on image processing as described in claim 3, characterized in that, The expressions for obtaining the first laser energy assessment result include: ； in, The weighting factor is used to adjust the cumulative energy value of edge pixels and the influence of similarity probability distribution on the overall evaluation. It represents the inverse of similarity and is used to enhance the evaluation index when the image changes significantly. The greater the change in similarity, the greater its contribution to obtaining the first laser energy evaluation result.

5. The laser energy assessment method based on image processing as described in claim 1, characterized in that, The method further includes: Obtain the initialization control parameters of the laser under test, including laser power, irradiation time, and focal size; The parameters of the laser under test are optimized by feedback based on the difference between the first laser energy assessment result and the preset laser energy assessment result, and the optimized control parameters are obtained.

6. The laser energy assessment method based on image processing as described in claim 1, characterized in that, The method further includes: A beam fitter is provided, which is located at the output end of the laser under test; The beam fitter is driven to re-evaluate the laser energy of the laser under test, and a second laser energy evaluation result is obtained. The parameters of the laser under test are optimized based on the first laser energy assessment result and the second laser energy assessment result.

7. A laser energy assessment device based on image processing, characterized in that, The apparatus for implementing the image processing-based laser energy assessment method according to any one of claims 1-6, the apparatus comprising: An image acquisition module is used to capture a first image set, a second image set, and a third image set according to an image acquisition device. The first image set is a surface image of the test target material before the laser under test is irradiated by the laser. The second image set is an image generated by the laser under test irradiating the test target material. The third image set is a surface image of the test target material after the laser under test is irradiated by the laser. The information acquisition module is used to extract edges from the second image set using an edge algorithm, obtain the illumination area, and acquire the light intensity distribution information of the illumination area; A matrix processing module is used to perform pixel matrix processing on the first image set and the third image set for the illumination area, and output the similarity probability distribution of the first pixel matrix and the third pixel matrix. An energy assessment module is used to input the light intensity distribution information and the similarity probability distribution into a laser energy assessment model. The laser energy assessment model uses the similarity probability distribution as an adjustment factor and analyzes the light intensity distribution information to obtain a first laser energy assessment result. An optimization module is used to perform feedback optimization on the parameters of the laser under test based on the first laser energy assessment result.

Images