Automatic recognition method and system for defects of goggles based on machine vision

Abstract

The invention discloses a machine vision-based goggle defect automatic identification method and system, and relates to the technical field of machine vision, and the method comprises the steps: obtaining the surface defect data, structure defect data and optical defect data of goggles based on a goggle picture, the defect degree of the goggles is analyzed based on the surface defect data, the structure defect data and the optical defect data, the damage degree of the goggles under the comprehensive influence is obtained based on the environment data and the historical use data of the customer location, and the matching degree of the face and the goggles is analyzed based on the face data of the target customer; based on the defect degree of the goggles, the damage degree of the goggles and the matching degree of the human face and the goggles, the damage degree of the goggles in actual use is predicted, and whether the goggles meet the use standard of the region where the customer is located or not is judged. Damage conditions of the goggles in different areas during actual use are predicted, and the accuracy of automatic recognition of the defects of the goggles is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision, and in particular to a method and system for automatically identifying goggles defects based on machine vision. Background Art

[0002] Goggles are widely used in high-risk scenarios such as industry, medical care, and laboratories. Their quality is directly related to the safety of users. Traditional defect detection relies on manual labor, which has problems such as low efficiency and easy missed detection. The addition of automated recognition technologies, such as machine vision and deep learning, can significantly improve detection efficiency and accuracy, reduce human errors, and thus ensure product quality and safety.

[0003] However, existing technologies for automated goggles recognition mostly utilize image acquisition modules to automatically detect surface defects of goggles, such as scratches and bubbles. They lack the ability to combine the degree of goggles’ defects, the degree of damage to the goggles, and the degree of matching between the human face and the goggles to jointly predict the damage of each area of ​​the goggles during actual use. This results in the quality of the goggles not being consistent with the test conditions during actual use, thereby affecting safety in use.

[0004] It can be seen that how to improve the accuracy of automatic identification of goggles defects is a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a method and system for automatically identifying goggles defects based on machine vision. The present invention takes into account the customer's own characteristics and usage scenarios, predicts the damage of different areas of the goggles during actual use, and improves the accuracy of automatic identification of goggles defects.

[0006] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for automatically identifying goggles defects based on machine vision, comprising the following specific steps: Step 1: Collecting images of the goggles, obtaining surface defect data, structural defect data, and optical defect data of the goggles based on the images of the goggles, and analyzing the degree of defects of the goggles based on the surface defect data, structural defect data, and optical defect data; Step 2: Collect environmental data and historical usage data at the customer's location, and obtain the degree of damage to the goggles under the combined influence based on the environmental data and historical usage data at the customer's location; Step 3: Collect the target customer's facial data and analyze the degree of match between the face and the goggles based on the target customer's facial data; Step 4: Predict the degree of damage to the goggles during actual use based on the degree of defects in the goggles, the degree of damage to the goggles under comprehensive influence, and the degree of matching between the face and the goggles; Step 5: Determine whether the goggles meet the usage standards in the customer's area based on the degree of damage to the goggles during actual use.

[0007] Optionally, the step 1 includes the following specific steps: Collect pictures of the goggles to be tested; Acquire surface defect data, structural defect data, and optical defect data of the goggles based on the image of the goggles to be inspected, wherein the surface defect data includes scratches and bubbles, the structural defect data includes edge burrs and dimensional deviations, and the optical defect data includes refractive index and distortion rate; Construct a goggles defect model, input the surface defect data, structural defect data and optical defect data of each positioning point of the goggles, and output the defect degree of the goggles positioning point.

[0008] Optionally, the step 2 includes the following specific steps: Collecting environmental data at the target customer's location and historical usage data of the target customer, such as temperature, humidity, and particulate matter concentration; and historical usage data including wearing duration, removal frequency, and storage habits; Based on the environmental data of the target customer's location and the target customer's historical usage data, the damage degree of each positioning point of the goggles under the comprehensive influence is obtained.

[0009] Optionally, step three includes the following specific steps: Using a 3D scanner to collect facial data of the target customer, the facial data including the radius of curvature of the nose bridge, the width of the temples, and the convexity of the brow bones; Collecting goggles parameters, including frame depth, nose pad curvature radius, and temple clamping force; Based on the target customer's facial data and goggles' contour data, the matching degree between the face and each positioning point of the goggles is obtained.

[0010] Optionally, the step 4 includes the following specific steps: The defect degree impact value is obtained by multiplying the defect degree impact weight of the goggles. The comprehensive damage degree impact value is obtained by multiplying the damage degree of the goggles under the comprehensive influence by the comprehensive damage degree impact weight. The matching degree impact value is obtained by multiplying the matching degree between the face and the goggles by the matching degree impact weight. The damage prediction value of each positioning point of the goggles in actual use is obtained based on the sum of the defect degree impact value, comprehensive damage degree impact value and matching degree impact value of each positioning point of the goggles.

[0011] Optionally, step five includes the following specific steps: A damage threshold is obtained. If the damage threshold is greater than or equal to the damage prediction value of the goggles during actual use, the goggles are judged to meet the usage standards in the target customer's area. If the damage threshold is less than the damage prediction value of the goggles during actual use, the goggles are judged to not meet the usage standards in the target customer's area.

[0012] In a second aspect, the present invention provides a system for automatically identifying goggles defects based on machine vision, which is used to implement a method for automatically identifying goggles defects based on machine vision, comprising: A defect degree analysis module is used to collect images of goggles, obtain surface defect data, structural defect data, and optical defect data of the goggles based on the images of the goggles, and analyze the defect degree of the goggles based on the surface defect data, structural defect data, and optical defect data; A damage degree analysis module is used to collect environmental data and historical usage data at the customer's location, and to determine the degree of damage to the goggles under the combined influence of these data. A matching degree analysis module is used to collect facial data of target customers and analyze the matching degree between the face and the goggles based on the facial data of the target customers; The actual damage prediction module is used to predict the degree of damage to the goggles during actual use based on the degree of defects in the goggles, the degree of damage to the goggles under comprehensive influence, and the degree of matching between the face and the goggles; The compliance judgment module is used to determine whether the goggles meet the usage standards in the customer's region based on the degree of damage to the goggles during actual use; The control module is used to control the operation of the defect degree analysis module, the damage degree analysis module, the matching degree analysis module, the actual damage prediction module and the compliance judgment module.

[0013] In a third aspect, the present invention provides an electronic device comprising: a memory for storing a computer program, and a processor for executing the computer program to implement the steps of the above-mentioned method for automatic identification of goggles defects based on machine vision.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned method for automatically identifying defects in goggles based on machine vision are implemented.

[0015] Compared with the prior art, the present invention has the following beneficial effects: Collect pictures of goggles, obtain surface defect data, structural defect data and optical defect data of the goggles based on the pictures of the goggles, analyze the degree of defects of the goggles based on the surface defect data, structural defect data and optical defect data, collect environmental data and historical usage data of the customer's location, obtain the degree of damage to the goggles under the combined influence based on the environmental data and historical usage data of the customer's location, collect facial data of the target customer, analyze the degree of matching between the face and the goggles based on the facial data of the target customer, predict the degree of damage to the goggles in actual use based on the degree of defects of the goggles, the degree of damage to the goggles under the combined influence and the degree of matching between the face and the goggles, judge whether the goggles meet the usage standards in the customer's area based on the degree of damage to the goggles in actual use, the present invention takes into account the customer's own characteristics and usage scenarios, predicts the damage of different areas of the goggles in actual use, and improves the accuracy of automatic identification of goggles defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 A schematic flow chart of a method for automatically identifying goggles defects based on machine vision provided by an embodiment of the present invention; Figure 2 A flowchart of step 1 of the method for automatically identifying goggles defects based on machine vision provided by an embodiment of the present invention; Figure 3 A schematic flow chart of step three of the method for automatically identifying goggles defects based on machine vision provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a machine vision-based automatic goggle defect recognition system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field are within the scope of protection of the present invention.

[0019] The terms "including" and "having" in the description of the present invention and the above-mentioned drawings, as well as any variations related to "including" and "having", are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may include steps or units that are not listed.

[0020] In order to enable those skilled in the art to better understand the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0021] See also Figure 1 The present invention provides an embodiment of a method for automatically identifying goggles defects based on machine vision, which includes the following specific steps: Step 1: Collect a picture of the goggles, obtain surface defect data, structural defect data, and optical defect data of the goggles based on the picture of the goggles, and analyze the degree of defects of the goggles based on the surface defect data, structural defect data, and optical defect data; See also Figure 2 In this embodiment, step 1 includes the following specific steps: The automated robotic arm places the goggles to be inspected at the designated shooting position. Once the goggles are stably placed, the sensor senses and activates the camera to capture images of the goggles to be inspected. The captured images are stored in a designated directory, and filtering algorithms such as Gaussian filtering and median filtering are applied to remove noise from the images. Enhancement techniques such as histogram equalization and contrast stretching are applied to improve the contrast of the images. Acquire surface defect data, structural defect data, and optical defect data of the goggles based on the image of the goggles to be inspected, wherein the surface defect data includes scratches and bubbles, the structural defect data includes edge burrs and dimensional deviations, and the optical defect data includes refractive index and distortion rate; Optionally, set the size of surface defect data, structural defect data and optical defect data, for example, the length of scratches is greater than or equal to 2mm, the width is greater than or equal to 0.1mm, the diameter of bubbles is greater than or equal to 0.5mm, the height of edge burrs is greater than or equal to 0.2mm, the width is greater than or equal to 0.5mm, the allowable deviation range of the width, height and lens spacing of the goggles is ±0.5mm, the allowable deviation of the refractive index is 0.01, and the allowable deviation of the distortion rate is 1%. Use threshold segmentation to separate scratches and bubbles from the surface of the goggles, perform feature extraction on the segmented area, collect the length, width and curvature of the scratches, collect the diameter, area and centroid position of the bubbles, use Canny, Sobel and other edge detection operators to extract the contour of the goggles edge, fit the extracted contour, detect the raised part on the contour, collect its height and width, and compare them with the set size, and record the area that reaches the set size. The system detects edge burrs of small sizes and uses template matching methods to accurately locate key feature points of the goggles, such as corners, lens centers, and nose pad positions. The conversion relationship from pixels to physical dimensions obtained by camera calibration is used, where the pixel size is obtained by dividing the physical size by the number of pixels and multiplying it by the calibration ratio. The distances between key points, such as total width, total height, and lens spacing, are measured. The measured dimensions are compared with the design specifications, the deviation values ​​are calculated, and the dimensional deviations that exceed the allowable range are recorded. Images of goggles imaging specific patterns at different angles are collected, and the degree of curvature of parallel lines at different positions on the lens or the change in the position of the focal point is measured. The refractive index is calculated based on the measurement results. A grid pattern is used as input to detect the curvature of the grid lines or the offset of the grid point positions in the image. The radial distortion and tangential distortion coefficients, that is, the additional distortion introduced by the lens, are calculated. The deviation ratio between the actual pixel position and the ideal pixel position is calculated to obtain the distortion rate. Build a goggles defect model, collect a large number of goggles samples, including defect-free goggles and goggles with various defects, record the type, location, size and severity of the defects of each goggles sample, perform data cleaning, standardization and normalization on the collected data, extract goggles defect features from the preprocessed data, select a machine learning algorithm to build a goggles defect model, use the preprocessed and feature-extracted data to train the model, minimize the prediction error by adjusting the model parameters and optimizer, and use the test set to evaluate the trained model. Estimate, calculate the model's accuracy, recall rate, F1 score and other indicators, input the goggles sample to be tested into the trained model, and obtain the prediction result of the defect value; input the surface defect data, structural defect data and optical defect data of each positioning point of the goggles, and output the defect degree of the goggles positioning point. By building an accurate and efficient goggles defect model and inputting parameters such as scratches, bubbles, burrs, dimensional deviation, refractive index and distortion rate to output the defect value of the goggles, it helps to realize automatic detection and evaluation of goggles quality, and improve production efficiency and product quality.

[0022] Step 2: Collect environmental data and historical usage data of the customer's location, and obtain the degree of damage to the goggles under the comprehensive influence based on the environmental data and historical usage data of the customer's location; In this embodiment, step 2 includes the following specific steps: Collect environmental data at the target customer's location and historical usage data of the target customer. The environmental data includes temperature, humidity, and particulate matter concentration. High temperature can accelerate material aging, causing lenses to turn yellow and brittle, and seals to deform. High humidity can cause lenses to fog, coating peeling, and metal parts to rust. Particulate matter can scratch lenses. The historical usage data includes wearing time, frequency of wearing and removing glasses, and storage habits. Historical usage data is obtained through surveys of target customers. Prolonged wearing time can cause material fatigue to accumulate, lens transmittance to decrease, headband elasticity to decay, and hinges to loosen. Frequent wearing and removing glasses can cause headband breakage and hinge deformation due to frequent pulling. Improper removal can cause temple bending. Random storage can cause lenses to be scratched or deformed under pressure. Optionally, environmental data and usage habits can cause damage to different parts of the goggles. The key factors affecting damage to key parts are shown in the following table: Part Injury type Key influencing factors lens Scratches, fogging, aging Particles, humidity, temperature, wearing time Frame Deformation, cracking, and decreased elasticity Temperature, humidity, frequency of wearing and removing nose pads Indentation, adhesion, material degradation Humidity, temperature, wearing time Mirror strap Loose, broken Frequency of wearing and removing, storage temperature Sealing edges Seal failure and edge lift Temperature, storage humidity Based on the environmental data of the target customer's location and the target customer's historical usage data, the degree of damage at each location point of the goggles under the combined influence is obtained. Analyzing the joint impact of the environment and usage habits on the goggles can more accurately predict areas that are more prone to damage during actual use.

[0023] For example, the lens damage can be obtained by the lens damage value calculation formula, which is: ,in, is the wearing time of goggles, is the standard daily usage time of goggles, which is 8h in this embodiment. is the particle concentration, is the standard particle concentration, which is 50 μg / m 3 , is the temperature, The standard temperature is 25°C in this embodiment. For humidity, The standard humidity is 45%RH in this embodiment. is the weight of the impact of particles on the lens, is the weight of the influence of temperature on the lens, is the weight of the effect of humidity on the lens, ; The frame damage can be obtained through the frame damage value calculation formula, which is: ,in, The number of times it is taken off and put on, is the stress sensitivity coefficient of the frame material. For example, when the frame is pure titanium, the stress sensitivity coefficient of the frame material is 28.5±1.2; when the frame is titanium alloy, the stress sensitivity coefficient of the frame material is 18.7±0.9; when the frame is cellulose acetate, the stress sensitivity coefficient of the frame material is 7.2±0.5. is the weight of the influence of temperature on the frame, is the weight of the effect of humidity on the frame, .

[0024] Step 3: Collect the target customer's facial data, and analyze the degree of match between the face and the goggles based on the target customer's facial data; See also Figure 3 In this embodiment, step three includes the following specific steps: Use a 3D scanner to collect facial data of the target customer, including the radius of curvature of the nose bridge, temple width, and brow bone convexity. The facial deformation of the customer when performing basic expressions such as smiling, frowning, and opening the mouth is collected. The skin displacement of the customer when performing basic expressions, such as the movement of the cheekbones when speaking, is obtained. The scan data is converted into a NURBS surface model with a precision of 0.1mm, and pressure-sensitive areas such as the nose bridge point, cheekbone point, temple, and ear point are marked; Collect goggles parameters, including frame depth, nose pad curvature radius, and temple clamping force. The frame depth can be obtained by a laser rangefinder. The temple clamping force can be obtained by installing a force sensor at the contact position between the temple and the frame, measuring the squeezing force when the temple is fully closed, changing the opening and closing angles of the temple, recording the clamping force data at different angles, and drawing an angle-force curve. The nose pad curvature radius can be measured by using a laser interferometer to test interference fringes, determine the deviation of the nose pad surface from the ideal sphere, and calculate the curvature radius; Based on the target customer's facial data and goggles' contour data, the matching degree between the face and each positioning point of the goggles is obtained. By accurately analyzing the adaptation of the goggles to each part of the face, the gap or pressure between the goggles and the face can be determined, so as to quickly locate possible defects, judge the fit and comfort of wearing, identify the weak links in the adaptation between the goggles and the face, and facilitate the prediction of potential safety hazards.

[0025] For example, the nose pad matching degree can be obtained by the nose pad area matching degree calculation formula, which is: ,in, is the curvature radius of the nose pad of the goggles, is the curvature radius of the nose bridge of the human face; The matching degree between the frame and the brow bone can be obtained by the frame area matching calculation formula, which is: ,in, is the frame depth of the goggles, The convexity of the brow bone of the human face; The matching degree between the temple and the temple can be obtained by the temple area matching degree calculation formula, which is: ,in, Temple clamping force, is the width of the temple, For ideal clamping force, the average thickness of the temple soft tissue is 4-6mm (including skin + temporalis muscle + fascia), the maximum allowable pressure threshold during dynamic movement is 8kPa, and the contact area of ​​the temple is approximately 15×3mm 2 , then the ideal clamping force is the pressure threshold multiplied by the contact area to get 4.5N, and the target customer's temple width is 150mm, so the unit width clamping force is 0.15N / mm.

[0026] Step 4: predicting the degree of damage to the goggles during actual use based on the degree of defects in the goggles, the degree of damage to the goggles under comprehensive influence, and the degree of matching between the face and the goggles; In this embodiment, step 4 includes the following specific steps: The defect degree impact value is obtained by multiplying the defect degree impact weight of the goggles. The comprehensive damage degree impact value is obtained by multiplying the damage degree of the goggles under the comprehensive influence by the comprehensive damage degree impact weight. The matching degree impact value is obtained by multiplying the matching degree between the face and the goggles by the matching degree impact weight. The damage prediction value of each positioning point of the goggles in actual use is obtained based on the sum of the defect degree impact value, comprehensive damage degree impact value and matching degree impact value of each positioning point of the goggles.

[0027] The weights and thresholds in this embodiment are obtained by collecting several pictures of goggles sold in the past, collecting environmental data of the usage area, customer usage data, and customer facial data, collecting and analyzing the actual damage values ​​of each part after the customer finishes using the goggles, and importing the above data into each step of this embodiment to obtain the damage prediction value of each positioning point of the goggles during actual use, and importing the actual damage value and the damage prediction value of each positioning point of the goggles during actual use obtained in this embodiment into the matlab fitting software for fitting, and obtaining the weight and threshold values ​​of the group with the highest judgment accuracy.

[0028] Step 5: Determine whether the goggles meet the usage standards in the customer's area based on the degree of damage to the goggles during actual use.

[0029] In this embodiment, step five includes the following specific steps: A damage threshold is obtained. If the damage threshold is greater than or equal to the damage prediction value of the goggles during actual use, the goggles are judged to meet the usage standards in the target customer's area. If the damage threshold is less than the damage prediction value of the goggles during actual use, the goggles are judged to not meet the usage standards in the target customer's area.

[0030] This embodiment predicts the damage of different areas of the goggles during actual use by taking into account the customer's own characteristics and usage scenarios, thereby improving the accuracy of automatic identification of goggles defects.

[0031] See also Figure 4 The automatic goggle defect recognition system based on machine vision is implemented based on the above-mentioned automatic goggle defect recognition method based on machine vision, including: A defect degree analysis module is used to collect images of goggles, obtain surface defect data, structural defect data, and optical defect data of the goggles based on the images of the goggles, and analyze the defect degree of the goggles based on the surface defect data, structural defect data, and optical defect data; A damage degree analysis module is used to collect environmental data and historical usage data at the customer's location, and to determine the degree of damage to the goggles under the combined influence of these data. A matching degree analysis module is used to collect facial data of target customers and analyze the matching degree between the face and the goggles based on the facial data of the target customers; The actual damage prediction module is used to predict the degree of damage to the goggles during actual use based on the degree of defects in the goggles, the degree of damage to the goggles under comprehensive influence, and the degree of matching between the face and the goggles; The compliance judgment module is used to determine whether the goggles meet the usage standards in the customer's region based on the degree of damage to the goggles during actual use; The control module is used to control the operation of the defect degree analysis module, the damage degree analysis module, the matching degree analysis module, the actual damage prediction module and the compliance judgment module.

[0032] This embodiment provides an electronic device, including: a memory for storing a computer program, and a processor for executing the computer program to implement the steps of the above-mentioned method for automatic identification of goggles defects based on machine vision.

[0033] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the automatic identification method of goggles defects based on machine vision provided by the above-mentioned method embodiment. The electronic device may also include other components for realizing the functions of the device. For example, the electronic device may also have components such as wired or wireless network interfaces and input and output interfaces for data input and output, which will not be described in detail in this embodiment.

[0034] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for automatic identification of goggles defects based on machine vision are implemented.

[0035] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device.

[0036] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the methods.

[0037] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0038] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0039] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include," "comprise," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or apparatus that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or includes elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "includes a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0040] The technical solution provided by the present invention is introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. The automatic identification method of goggles defects based on machine vision is characterized by: The specific steps include: Step 1: Collecting images of the goggles, obtaining surface defect data, structural defect data, and optical defect data of the goggles based on the images of the goggles, and analyzing the degree of defects of the goggles based on the surface defect data, structural defect data, and optical defect data; Step 2: Collect environmental data and historical usage data at the customer's location, and obtain the degree of damage to the goggles under the combined influence based on the environmental data and historical usage data at the customer's location; Step 3: Collect the target customer's facial data and analyze the degree of match between the face and the goggles based on the target customer's facial data; Step 4: Predict the degree of damage to the goggles during actual use based on the degree of defects in the goggles, the degree of damage to the goggles under comprehensive influence, and the degree of matching between the face and the goggles; Step 5: Determine whether the goggles meet the usage standards in the customer's area based on the degree of damage to the goggles during actual use.

2. The method for automatically identifying goggles defects based on machine vision according to claim 1, characterized in that: The step 1 includes the following specific steps: Collect pictures of the goggles to be tested; Acquire surface defect data, structural defect data, and optical defect data of the goggles based on the image of the goggles to be inspected, wherein the surface defect data includes scratches and bubbles, the structural defect data includes edge burrs and dimensional deviations, and the optical defect data includes refractive index and distortion rate; Construct a goggles defect model, input the surface defect data, structural defect data and optical defect data of each positioning point of the goggles, and output the defect degree of the goggles positioning point.

3. The method for automatically identifying goggles defects based on machine vision according to claim 2, characterized in that: The step 2 includes the following specific steps: Collecting environmental data at the target customer's location and historical usage data of the target customer, such as temperature, humidity, and particulate matter concentration; and historical usage data including wearing duration, removal frequency, and storage habits; Based on the environmental data of the target customer's location and the target customer's historical usage data, the damage degree of each positioning point of the goggles under the comprehensive influence is obtained.

4. The method for automatically identifying goggles defects based on machine vision according to claim 3, characterized in that: The step three includes the following specific steps: Using a 3D scanner to collect facial data of the target customer, the facial data including the radius of curvature of the nose bridge, the width of the temples, and the convexity of the brow bones; Collecting goggles parameters, including frame depth, nose pad curvature radius, and temple clamping force; Based on the target customer's facial data and goggles' contour data, the matching degree between the face and each positioning point of the goggles is obtained.

5. The method for automatically identifying goggles defects based on machine vision according to claim 4, characterized in that: The step 4 includes the following specific steps: The defect degree impact value is obtained by multiplying the defect degree impact weight of the goggles. The comprehensive damage degree impact value is obtained by multiplying the damage degree of the goggles under the comprehensive influence by the comprehensive damage degree impact weight. The matching degree impact value is obtained by multiplying the matching degree between the face and the goggles by the matching degree impact weight. The damage prediction value of each positioning point of the goggles in actual use is obtained based on the sum of the defect degree impact value, comprehensive damage degree impact value and matching degree impact value of each positioning point of the goggles.

6. The method for automatically identifying goggles defects based on machine vision according to claim 5, characterized in that: The step five includes the following specific steps: A damage threshold is obtained. If the damage threshold is greater than or equal to the damage prediction value of the goggles during actual use, the goggles are judged to meet the usage standards in the target customer's area. If the damage threshold is less than the damage prediction value of the goggles during actual use, the goggles are judged to not meet the usage standards in the target customer's area.

7. A system for automatically identifying goggles defects based on machine vision, for implementing the method for automatically identifying goggles defects based on machine vision according to any one of claims 1 to 6, characterized in that: include: A defect degree analysis module is used to collect images of goggles, obtain surface defect data, structural defect data, and optical defect data of the goggles based on the images of the goggles, and analyze the defect degree of the goggles based on the surface defect data, structural defect data, and optical defect data; A damage degree analysis module is used to collect environmental data and historical usage data at the customer's location, and to determine the degree of damage to the goggles under the combined influence of these data. A matching degree analysis module is used to collect facial data of target customers and analyze the matching degree between the face and the goggles based on the facial data of the target customers; The actual damage prediction module is used to predict the degree of damage to the goggles during actual use based on the degree of defects in the goggles, the degree of damage to the goggles under comprehensive influence, and the degree of matching between the face and the goggles; The compliance judgment module is used to determine whether the goggles meet the usage standards in the customer's region based on the degree of damage to the goggles during actual use; The control module is used to control the operation of the defect degree analysis module, the damage degree analysis module, the matching degree analysis module, the actual damage prediction module and the compliance judgment module.

8. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program to implement the steps of the method for automatically identifying goggles defects based on machine vision as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for automatically identifying goggles defects based on machine vision as described in any one of claims 1 to 6.

Images