A light guide film cutting and positioning system based on machine vision

Abstract

The present invention relates to the technical field of light-guiding films, and specifically to a light-guiding film cutting and positioning system based on machine vision, the system comprising a light-guiding film image processing module, an edge feature extraction module, a tool adjustment module, and a cutting effect evaluation module. The present invention significantly improves the accuracy and efficiency of light-guiding film cutting through real-time image data acquisition and edge detection and feature extraction of convolutional neural networks, allowing the system to accurately identify the edge position of the light-guiding film, reduce errors and optimize cutting quality. The real-time feedback mechanism allows the system to make immediate adjustments based on the cutting effect, improving the adaptability and continuity of the cutting operation. The convolutional neural network is optimized in combination with the cutting history data of the light-guiding film, further enhancing the intelligence and self-learning ability of the system, making the cutting process closer to an ideal state. These improvements not only improve production efficiency, but also reduce material waste and ensure the accuracy of cutting and positioning of the light-guiding film.

Description

Technical Field

[0001] The present invention relates to the technical field of light guide films, and particularly to a light guide film cutting and positioning system based on machine vision. Background Art

[0002] The light guide film technology involves using special thin films to evenly disperse light, mainly applied in liquid crystal display (LCD) backlights and lighting systems. A light guide film is an optical-grade material that, through specific pattern designs and light management techniques, effectively controls the light propagation path to achieve uniform light output. This material is commonly used in tablet computers, smartphones, televisions, and other display devices. The key lies in how to design the thin film to achieve high-efficiency light transmission and dispersion in as thin a form as possible, improving the light efficiency and energy efficiency of the overall device.

[0003] Among them, the light guide film cutting and positioning system based on machine vision is a system that uses machine vision technology to optimize the light guide film production process. Machine vision is used to accurately identify the position and orientation of the light guide film for precise cutting. Its purpose is to improve the automation level and accuracy of the cutting process, reduce material waste, and ensure that each light guide film meets strict quality standards. Through machine vision, real-time adjustment of the cutting line can be achieved, optimizing production efficiency, and it is applicable to high-volume industrial environments.

[0004] The existing technologies show obvious limitations in high-efficiency and high-precision production environments. Especially in high-volume industrial applications, traditional technologies have limited capabilities in real-time data processing and dynamic adjustment, often resulting in insufficient cutting accuracy and material waste. They lack the ability to adjust the tool position or pressure in real time. When dealing with light guide films with complex edge designs, multiple adjustments and repeated cutting are required, increasing production costs and time consumption. In addition, traditional systems have limited edge recognition and error correction capabilities and cannot effectively respond to rapidly changing production requirements, resulting in inconsistent finished product quality and affecting the light efficiency and energy efficiency of display devices. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art and propose a light guide film cutting and positioning system based on machine vision.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: A light guide film cutting and positioning system based on machine vision, the system includes:

[0007] The light guide film image processing module collects real-time image data of the light guide film, performs preliminary image format conversion, adjusts the image clarity parameters to match the processing requirements, and conducts key frame screening to optimize the image contrast and color saturation, obtaining image quality enhanced data;

[0008] Based on the image quality enhancement data, the edge feature extraction module uses a convolutional neural network to perform image edge detection, identify the edge features of the light guide film, extract the sharpness and continuity features of the edge, calculate the edge error value, and adjust the feature extraction threshold to generate an edge feature dataset;

[0009] Based on the edge feature dataset, the tool adjustment module calculates the optimal angle and pressure of the cutting tool, adjusts the position of the robotic arm according to the real-time cutting feedback information, and dynamically optimizes the tool parameters, including repeatedly adjusting the tool angle and pressure, to generate cutting dynamic adjustment parameters;

[0010] Based on the cutting dynamic adjustment parameters, the cutting effect evaluation module monitors the current cutting effect, compares it with the preset cutting standard, executes the backpropagation algorithm according to the deviation, and optimizes the convolutional neural network in combination with the cutting historical data of the light guide film to generate a cutting effect optimization result.

[0011] The improvement of the present invention is that the step of matching the processing requirements is specifically as follows:

[0012] Collect the real-time image data of the light guide film, perform preliminary format conversion of the image data, convert the original image data into a standard processing format to obtain formatted image data;

[0013] Analyze the formatted image data, adjust the image sharpness parameter, and use the formula:

[0014] ;

[0015] Obtain the adjusted sharpness , matching the image processing requirements, where is the original sharpness, is the sharpness adjustment coefficient, is the adjustment coefficient of the baseline brightness of the image.

[0016] The improvement of the present invention is that the step of obtaining the image quality enhancement data is specifically as follows:

[0017] According to the motion characteristics and information content of the image, perform the key frame screening to obtain key frame data;

[0018] Based on the key frame data, process the image quality, including optimizing the contrast and color saturation, and using the formula:

[0019] ;

[0020] Obtain the image quality enhancement data, where is the enhanced image quality, is the original image quality of the key frame, and They are the contrast and saturation adjustment coefficients respectively.

[0021] The improvement of the present invention is that the recognition step of the edge features of the light guide film is specifically as follows:

[0022] Based on the image quality enhancement data, using a convolutional neural network, set the network layer parameters that match the characteristics of the light guide film, including the number of network layers, filter size, and activation function parameters, to obtain network configuration data;

[0023] Based on the network configuration data, perform an image edge detection operation, using the formula:

[0024] ;

[0025] Identify the edge position of the light guide film in the image to obtain an edge detection result, where is the edge detection result at position in the image, is the gradient of the image in the direction of at position in the image, is the gradient of the image in the direction of at position in the image;

[0026] Analyze the edge detection result, extract key edge features, including the clarity and continuity features of the edge, to obtain the edge shape of the light guide film.

[0027] The improvement of the present invention is that the acquisition step of the edge feature dataset is specifically as follows:

[0028] Calculate the edge error value, using the formula:

[0029] ;

[0030] Obtain the total edge error value , where is the number of edge points, is the th detected edge point position, is the th expected edge point position, is the absolute difference between the th edge point position and the expected position;

[0031] Based on the total edge error value, adjust the feature extraction threshold to reduce the edge error, using the formula:

[0032] ;

[0033] Obtain the new feature extraction threshold , where is the original feature extraction threshold, is the adjustment coefficient, is the edge error value;

[0034] Re-evaluate the edge features according to the new feature extraction threshold to obtain an edge feature dataset.

[0035] The improvement of the present invention is that the step of adjusting the position of the robotic arm is specifically:

[0036] Based on the edge feature dataset, calculate the optimal angle and pressure of the cutting tool, and collect sensor data during the real-time cutting process, including the current position, speed, cutting angle and pressure of the robotic arm, to form a cutting feedback dataset;

[0037] Analyze the cutting feedback dataset and use the formula:

[0038] ;

[0039] Calculate the new position of the robotic arm , where is the current position, is the expected gap between the target position and the current position, is the gap between the measured position and the current position, is the adjustment coefficient;

[0040] Feed back the new position of the robotic arm to the control system, update the operation parameters of the robotic arm in real time, optimize the alignment and motion control during cutting, and obtain the optimized result of the robotic arm position.

[0041] The improvement of the present invention is that the step of obtaining the cutting dynamic adjustment parameters is specifically:

[0042] Collect sensor data from the real-time cutting process, perform data integration, and establish a cutting process dataset;

[0043] Based on the cutting process dataset, predict the optimal tool angle and pressure required for each cutting, and dynamically optimize the tool parameters according to the historical cutting effect and the feedback information of the current light guide film to obtain the optimized tool parameters;

[0044] Apply the optimized tool parameters to the cutting process, and repeatedly adjust the tool angle and pressure through the control system to obtain the cutting dynamic adjustment parameters.

[0045] The improvement of the present invention is that the step of obtaining the cutting effect optimization result is specifically:

[0046] Based on the cutting dynamic adjustment parameters, collect real-time monitoring data of the cutting operation, including tool speed, accuracy and motion trajectory, to form a real-time cutting monitoring dataset;

[0047] Based on the real-time cutting monitoring data set, compare it with the preset cutting standard, and use the formula:

[0048] ;

[0049] Calculate the overall cutting error value , where is the th current measurement value, is the preset standard value of the th parameter, is the weight factor of the th parameter, is the total number of cutting parameters;

[0050] Based on the overall cutting error value, execute the backpropagation algorithm, combine the historical cutting data of the light guide film, adjust the parameters of the convolutional neural network, and obtain the optimized result of the cutting effect.

[0051] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0052] In the present invention, through real-time image data acquisition and edge detection and feature extraction of the convolutional neural network, the accuracy and efficiency of the light guide film cutting are significantly improved, allowing the system to accurately identify the edge position of the light guide film, reducing errors and optimizing the cutting quality. The real-time feedback mechanism allows the system to make immediate adjustments according to the cutting effect, improving the adaptability and continuity of the cutting operation. Optimizing the convolutional neural network in combination with the cutting historical data of the light guide film further enhances the intelligence and self-learning ability of the system, making the cutting process closer to the ideal state. These improvements not only improve production efficiency but also reduce material waste and ensure the cutting positioning accuracy of the light guide film. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is the system flow chart of the present invention;

[0054] Figure 2 is the flow chart of matching processing requirements in the present invention;

[0055] Figure 3 is the flow chart of obtaining image quality enhancement data in the present invention;

[0056] Figure 4 is the flow chart of identifying the edge features of the light guide film in the present invention;

[0057] Figure 5 is the flow chart of obtaining the edge feature data set in the present invention;

[0058] Figure 6 is the flow chart of adjusting the position of the robotic arm in the present invention;

[0059] Figure 7 This is the flowchart for obtaining the dynamic adjustment parameters for cutting in the present invention;

[0060] Figure 8 This is the flowchart for obtaining the optimized results of the cutting effect in the present invention. Detailed implementation manners

[0061] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0062] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, in the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0063] Embodiment: Please refer to Figure 1 , the present invention provides a technical solution: A cutting and positioning system for a light guide film based on machine vision includes:

[0064] The light guide film image processing module collects real-time image data of the light guide film, performs preliminary image format conversion, adjusts the image clarity parameters to match the processing requirements, and performs key frame screening, optimizes the image contrast and color saturation, and obtains image quality enhancement data;

[0065] The edge feature extraction module, based on the image quality enhancement data, uses a convolutional neural network to perform image edge detection, identifies the edge features of the light guide film, extracts the clarity and continuity features of the edge, calculates the edge error value, and adjusts the feature extraction threshold to generate an edge feature dataset;

[0066] The tool adjustment module, based on the edge feature dataset, calculates the optimal angle and pressure of the cutting tool, adjusts the position of the robotic arm according to the real-time cutting feedback information, and dynamically optimizes the tool parameters, including repeatedly adjusting the tool angle and pressure, to generate dynamic adjustment parameters for cutting;

[0067] The cutting effect evaluation module, based on the dynamic adjustment parameters for cutting, monitors the current cutting effect, compares it with the preset cutting standard, performs a backpropagation algorithm according to the deviation, and optimizes the convolutional neural network in combination with the cutting historical data of the light guide film to generate optimized results for the cutting effect.

[0068] The image quality enhancement data includes the resolution improvement result, the dynamic range increase result, and the signal-to-noise ratio improvement result. The edge feature dataset specifically includes the edge positioning accuracy, the edge smoothness index, and the edge contrast intensity. The cutting dynamic adjustment parameters include the angle fine-tuning accuracy, the pressure adjustment sensitivity, and the position calibration accuracy. The cutting effect optimization result specifically refers to the cutting accuracy improvement rate, the error range reduction rate, and the response time optimization information.

[0069] Please refer to Figure 2 , and the steps to match the processing requirements are specifically as follows:

[0070] Collect the real-time image data of the light guide film, perform the preliminary format conversion of the image data, convert the original image data into the standard processing format, and obtain the formatted image data;

[0071] By using a camera to capture the surface details of the light guide film, high-definition image acquisition is achieved. The captured image data is in the original data format before formatting, and the original data needs to be format-converted to meet the requirements of subsequent processing. During the formatting process, the image data is compressed and transcoded, and converted into the standard processing format such as JPEG or PNG. The conversion not only optimizes the data storage efficiency but also facilitates subsequent image analysis and processing. The formatted image data is the converted standard image, and the standard image data will be used for further image sharpness adjustment and quality analysis.

[0072] Analyze the formatted image data, adjust the image sharpness parameters, and use the formula:

[0073] ;

[0074] Obtain the adjusted sharpness , which matches the image processing requirements. Among them, is the original sharpness, is the sharpness adjustment coefficient, which enhances the visibility of image details, is the adjustment coefficient of the image baseline brightness, which is used to improve the overall visual effect of the image;

[0075] By adjusting the parameters and , the sharpness of the image can be flexibly adjusted according to different image processing requirements, thereby improving the image quality and adapting to different monitoring and analysis conditions. If the original image sharpness is 0.5, the sharpness adjustment coefficient is 2.0, and the adjustment coefficient of the image baseline brightness is 0.1, then the adjusted sharpness is calculated as follows:

[0076] ;

[0077] This result indicates that through appropriate parameter adjustment, the clarity has been improved from 0.5 to 1.1, significantly enhancing the visibility of image details and meeting more complex image processing requirements.

[0078] Please refer to Figure 3 , the steps for obtaining image quality enhancement data are specifically as follows:

[0079] Based on the motion characteristics and information content of the image, key frames are screened to obtain key frame data;

[0080] Design the key frame screening process. By calculating the motion vectors of each frame, the displacement and degree of change between frames are obtained, and the motion characteristics of the frame are extracted. Combining the uniformity of pixel distribution and local gradient changes in the frame, the richness of content in each frame is analyzed. Using this as an index to measure the information content in the frame, the motion feature value and content richness value are weighted and combined to determine the importance of the frame. Frames with obvious motion characteristics and a relatively high degree of content richness are selected as key frames. The key frame data is stored through numbers and indexes to form structured data convenient for subsequent calls.

[0081] Based on the key frame data, process the image quality, including optimizing the contrast and color saturation, using the formula:

[0082] ;

[0083] Obtain the image quality enhancement data, where is the enhanced image quality, is the original image quality of the key frame, and are the contrast and saturation adjustment coefficients respectively;

[0084] The following data is collected. The original image quality of the key frame is 0.6, the contrast adjustment coefficient is 1.5, and the saturation adjustment coefficient is 0.05. Calculate:

[0085] ;

[0086] This result indicates that through appropriate adjustment coefficients, the quality of the image has been significantly improved, from 0.6 to 0.95, indicating that the image is visually clearer and more vivid, suitable for high-quality display and analysis.

[0087] Please refer to Figure 4 , the steps for identifying the edge features of the light guide film are specifically as follows:

[0088] Based on the image quality enhancement data, using a convolutional neural network, set the network layer parameters that match the characteristics of the light guide film, including the number of network layers, filter size, and activation function parameters, to obtain network configuration data;

[0089] Based on the image quality enhancement data, match the characteristics of the light guide film by adjusting the configuration of the convolutional neural network layer parameters. This includes optimizing the number of network layers to adapt to the extraction of high-dimensional image features, adjusting the filter size according to the image characteristics to ensure the retention of details and the prominence of features. Specifically, select an appropriate kernel size (such as 3×3 or 5×5 kernel) according to the image resolution for feature extraction. The activation function parameters need to be selected as values that perform excellently in nonlinear feature learning, such as ReLU (Rectified Linear Unit) to ensure avoiding gradient vanishing in feature learning. After verifying the optimal parameter configuration through experiments, generate network configuration data, which provides an efficient and reliable basis for the edge detection task.

[0090] Based on the network configuration data, perform image edge detection operations using the formula:

[0091] ;

[0092] Identify the edge position of the light guide film in the image to obtain the edge detection result. Among them, is the edge detection result at position in the image, is the gradient of the image in the direction of at position in the image, is the gradient of the image in the direction of at position in the image, which is used to obtain the total edge intensity from the combination of gradients in the x and y directions;

[0093] By synthesizing the gradients of the image in the x and y directions, effectively enhance the accuracy of edge recognition, making the edges more obvious, which is helpful for subsequent feature analysis and image processing tasks. The following data is collected. If the gradient of the image in the x direction at the point (x, y) is 150 and the gradient in the y direction is 100, then:

[0094] ;

[0095] This result shows that the edge intensity at the point (x, y) is 180.28, indicating that this point has high edge characteristics and is a significant edge point in the image.

[0096] Analyze the edge detection result and extract key edge features, including the clarity and continuity features of the edge, to obtain the edge shape of the light guide film;

[0097] Analyze the edge detection results. By extracting the clarity and continuity features of the edge of the light guide film to describe the edge shape, the specific steps include calculating the gradient magnitude of each edge point to measure the clarity, using a normalization method to compare the clarity levels based on the gradient calculation results to ensure consistency. The continuity feature extraction is to judge the connectivity of the edge by calculating the Euclidean distance between adjacent points. Pairs of points with too large a distance will be marked as break points and repaired by an interpolation algorithm. The final processing result includes the clarity value of each edge point and the overall connectivity information of the edge line, generating the complete edge shape of the light guide film.

[0098] Please refer to Figure 5 , the steps for obtaining the edge feature dataset are specifically as follows:

[0099] Calculate the edge error value using the formula:

[0100] ;

[0101] Obtain the total edge error value , where is the number of edge points, is the th detected edge point position, is the th expected edge point position, is the th absolute difference between the edge point position and the expected position;

[0102] By quantifying the difference between the actually detected edge and the preset ideal edge, a method for directly measuring the error is provided, enabling the quantitative evaluation of the accuracy of the edge detection algorithm. When there are 3 edge points, the expected edge point positions are 10, 20, and 30 respectively, and the detected edge positions are 12, 18, and 33 respectively. Substitute into the formula for calculation:

[0103] ;

[0104] ;

[0105] The result shows that the total edge error value is 7, indicating a small deviation between the detection system and the ideal model, suggesting that the edge detection needs to be fine-tuned to reduce the error.

[0106] Based on the total edge error value, adjust the feature extraction threshold to reduce the edge error, using the formula:

[0107] ;

[0108] Obtain the new feature extraction threshold , where is the original feature extraction threshold, is an adjustment coefficient, a scale factor used to adjust the threshold according to the edge error, is the edge error value;

[0109] Based on the calculated total edge error value 7, the feature extraction threshold is adjusted through a formula. If the original threshold is 50 and the adjustment coefficient is 0.1, the new threshold is calculated through the formula:

[0110] ;

[0111] The adjustment reduces the edge error and improves the accuracy of edge detection. The new threshold will be used for further image processing to ensure higher-quality edge recognition.

[0112] Re-evaluate the edge features according to the new feature extraction threshold to obtain an edge feature dataset;

[0113] Re-evaluate the edge features according to the adjusted feature extraction threshold. First, compare the edge detection results with the new threshold for matching, extract the edge information that meets the new threshold criteria, mark it as valid edges, and further analyze the marked edge information by calculating the clarity and continuity indexes of each edge to ensure the integrity and consistency of the edge features. During the analysis process, group the edges based on the edge clarity value, record the positions of the edge points in each group and their connection methods, evaluate the length, direction, and continuity of the edges one by one, remove the edge points that do not meet the clarity criteria at the same time, and regenerate the connection relationships of the edges. Finally, organize the recalculated and optimized edge features into a complete edge feature dataset.

[0114] Please refer to Figure 6 for the specific steps to adjust the position of the robotic arm:

[0115] Based on the edge feature dataset, calculate the optimal angle and pressure of the cutting tool, and collect the sensor data during the real-time cutting process, including the current position, speed, cutting angle, and pressure of the robotic arm, to form a cutting feedback dataset;

[0116] Based on the edge feature dataset, first call the physical property parameters such as the edge length, thickness, and material hardness recorded in the dataset, normalize the parameters respectively to calculate the theoretical ranges of the cutting pressure and cutting angle, calculate the expected value of the cutting angle through the normalized edge length, calculate the required cutting pressure range by combining the normalized material hardness with the edge thickness, and add a weight coefficient to adjust the dynamic sensitivity of the actual cutting pressure after normalization. Finally, select the optimal angle and pressure as the cutting parameters for the actual cutting task to form a cutting feedback dataset.

[0117] Analyze the cutting feedback data set and use the formula:

[0118] ;

[0119] Calculate the new position of the robotic arm , where is the current position, is the expected gap between the target position and the current position, which is the expected difference between the target position and the current position set in the optimal cutting path planning, is the gap between the measured position and the current position, which is the actual difference between the current position and the theoretical target position measured during the actual cutting process, is the adjustment coefficient used to adjust the position of the robotic arm according to the position error;

[0120] By adjusting the position of the robotic arm in real time and dynamically responding to the deviation during the cutting process, the cutting accuracy and the mechanical response speed are enhanced, enabling the robotic arm to more accurately align with the target cutting position, and the current position is 5.0, the target position deviation is 0.5, the current measured position deviation is 0.3, and the adjustment coefficient is set to 1.2. Calculate according to the formula:

[0121] ;

[0122] The result shows that the new position of the robotic arm is adjusted to 5.24 to meet the actual cutting requirements and reduce the cutting error.

[0123] Feed back the new position of the robotic arm to the control system (the control system is mainly used to control the robotic arm and the tool), update the operation parameters of the robotic arm in real time, optimize the alignment and motion control during the cutting process, and obtain the optimized result of the robotic arm position;

[0124] By calling the real-time position, pressure and speed recorded in the sensor data, and combining with the new position parameters calculated by the feedback, the motion trajectory of the robotic arm is optimized in real time. Call the current position and the calculated new position of the robotic arm respectively for path planning to ensure smooth and error-free speed change during the path adjustment process. At the same time, according to the real-time feedback, calculate the correlation between the cutting pressure change range and the actual pressure adjustment, and perform pressure adjustment compensation on the motion control. Finally, output the optimized cutting motion parameters and feedback them to the control system to update the operation instructions in real time, and obtain the optimized result of the robotic arm position.

[0125] Please refer to Figure 7 , and the specific steps for obtaining the cutting dynamic adjustment parameters are as follows:

[0126] Collect sensor data from the real-time cutting process, integrate the data, and establish a cutting process data set;

[0127] The extracted sensor data includes the current position, cutting pressure and speed of the robot arm. By aligning the data with a unified timestamp and standardizing the data format, the data at each moment in the cutting process is integrated into a complete cutting process data set. At the same time, abnormal data that obviously deviates from the cutting range is eliminated, and the robot arm movement path and actual cutting force at each moment are marked as a separate parameter set.

[0128] Based on the cutting process data set, the optimal tool angle and pressure required for each cutting are predicted, and according to the historical cutting effect and the feedback information of the current light guide film, the tool parameters are dynamically optimized to obtain the optimized tool parameters;

[0129] Based on the cutting process data set, by calling the actual cutting effect and material feedback parameters in the historical cutting data, the parameters are associated with the cutting force and cutting path in the current data, and the difference between the actual cutting path and the ideal cutting trajectory is matched through the dynamic calculation model. According to the cutting response characteristics of different materials, the optimization range of the tool angle and the adjustment range of the pressure are calculated one by one. Finally, the optimization range is reduced in combination with the cutting accuracy requirements, and the optimized tool parameters are finally obtained.

[0130] Apply the optimized tool parameters to the cutting process, and repeatedly adjust the tool angle and pressure through the control system to obtain the dynamic adjustment parameters of cutting;

[0131] Apply the optimized tool parameters to the cutting process, load the optimized cutting parameters through the real-time control system, dynamically adjust the motion trajectory of the robot arm, and monitor the fluctuation of the cutting pressure in real time. Compare the tool angle adjustment range at each moment with the cutting effect fed back in real time. When the pressure or cutting angle deviates from the optimized range, adjust the corresponding parameters immediately. Repeat the iteration until the cutting is completed to obtain the dynamic adjustment parameters for cutting.

[0132] Please refer to Figure 8 , the specific steps for obtaining the cutting effect optimization results are:

[0133] Based on the dynamic adjustment parameters of cutting, collect real-time monitoring data of cutting operations, including tool speed, accuracy and motion trajectory, to form a real-time cutting monitoring data set;

[0134] ​A framework for dynamically adjusting parameters based on cutting, which collects cutting operation data in real time, captures information on the speed, accuracy, and motion trajectory of the cutting tool through sensors, synchronizes timestamps and denoises the collected raw data, eliminates abnormal data, reorganizes it into a unified data structure according to the time series, and at the same time records the corresponding cutting position and trajectory deviation at each moment, and classifies and groups according to the cutting parameters to form a real-time monitoring dataset of cutting operations. The data provides a basis for subsequent cutting quality assessment and adjustment.

[0135] Based on the real-time cutting monitoring dataset, compare it with the preset cutting standard, and use the formula:

[0136] ;

[0137] Calculate the overall cutting error value , where is the th current measurement value, that is, the cutting parameter value actually recorded during the cutting process, is the preset standard value of the th parameter, that is, the ideal or standard parameter value set before the cutting operation, is the weight factor of the th parameter, indicating the importance of each parameter in the error calculation, is the total number of cutting parameters;

[0138] There are three parameters, which are 50, 55, and 60 respectively, which are 48, 53, and 58 respectively, The weight factors are 0.5, 1.0, and 1.5 respectively. Substitute them into the formula for calculation:

[0139] ;

[0140] ;

[0141] The result shows that the calculated overall cutting error value is 11.0, indicating the degree of deviation between the actual operation and the preset standard, and thus providing a quantitative basis for the adjustment of cutting parameters.

[0142] Based on the overall cutting error value, execute the backpropagation algorithm, combine the historical cutting data of the light guide film, and adjust the parameters of the convolutional neural network to obtain the optimized result of the cutting effect;

[0143] Based on the overall cutting error value, by comparing the real-time feedback during the cutting process with the preset cutting standard, clustering and analyzing each set of error data, taking the parameters with larger cutting deviations as the optimization targets, training a convolutional neural network using the historical cutting data of the light guide film, adjusting the weights and bias values in the neural network through backpropagation, ensuring that the calculation of the cutting parameters is highly consistent with the current feedback, and generating an optimized cutting effect result after re-iterative optimization, which plays a dynamic adjustment role in subsequent cutting operations.

[0144] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A light guide film cutting and positioning system based on machine vision, characterized in that: The system comprises: The light guide film image processing module collects real-time image data of the light guide film, performs preliminary image format conversion, adjusts image clarity parameters to match processing requirements, and performs key frame screening to optimize image contrast and color saturation to obtain image quality enhancement data; The edge feature extraction module performs image edge detection based on the image quality enhancement data using a convolutional neural network, identifies edge features of the light guide film, extracts edge clarity and continuity features, calculates edge error values, and adjusts feature extraction thresholds to generate edge feature data sets; The steps for obtaining the edge feature data set are specifically as follows: The edge error value is calculated using the formula: ； Get the total edge error value ,in, is the number of edge points, It is The detected edge point positions, It is The expected edge point locations, It is The absolute difference between the position of an edge point and the expected position; Based on the total edge error value, the feature extraction threshold is adjusted to reduce the edge error, using the formula: ； Get a new feature extraction threshold ,in, is the original feature extraction threshold, is the adjustment factor, is the edge error value; Re-evaluate edge features according to the new feature extraction threshold to obtain an edge feature data set; The tool adjustment module calculates the optimal angle and pressure of the cutting tool based on the edge characteristic data set, adjusts the position of the robot arm according to the real-time cutting feedback information, and dynamically optimizes the tool parameters, including repeatedly adjusting the tool angle and pressure to generate dynamic adjustment parameters for cutting; The cutting effect evaluation module dynamically adjusts the cutting parameters based on the cutting, monitors the current cutting effect, compares it with the preset cutting standard, executes the back propagation algorithm according to the deviation, optimizes the convolutional neural network in combination with the cutting history data of the light guide film, and generates a cutting effect optimization result.

2. The light guide film cutting and positioning system based on machine vision according to claim 1, characterized in that: The steps of matching processing requirements are specifically as follows: Collecting real-time image data of the light-guiding film, performing preliminary format conversion of the image data, converting the original image data into a standard processing format, and obtaining formatted image data; The formatted image data is analyzed and image definition parameters are adjusted using the formula: ； Get the adjusted clarity , matching the image processing requirements, where is the original clarity, is the clarity adjustment factor, is the adjustment factor for the image baseline brightness.

3. The light guide film cutting and positioning system based on machine vision according to claim 1, characterized in that: The steps of acquiring the image quality enhancement data are specifically as follows: According to the motion characteristics and information content of the image, the key frame is screened to obtain key frame data; Based on the key frame data, the image quality is processed, including optimizing contrast and color saturation, using the formula: ； Get image quality enhancement data, where: To enhance the image quality, is the original image quality of the key frame, and They are contrast and saturation adjustment coefficients respectively.

4. The machine vision-based light guide film cutting and positioning system according to claim 1, characterized in that: The steps for identifying the edge features of the light guide film are specifically as follows: Based on the image quality enhancement data, using a convolutional neural network, setting network layer parameters that match the characteristics of the light guide film, including the number of network layers, filter size, and activation function parameters, to obtain network configuration data; Based on the network configuration data, an image edge detection operation is performed using the formula: ； Identify the edge position of the light guide film in the image and obtain the edge detection result, where: is the position in the image The edge detection result is is the image at position along The gradient of the direction, is the image at position along Directional gradient; The edge detection result is analyzed to extract key edge features, including edge clarity and continuity features, to obtain the edge shape of the light guide film.

5. The light guide film cutting and positioning system based on machine vision according to claim 1, characterized in that: The steps of adjusting the position of the robotic arm are specifically as follows: Based on the edge characteristic data set, the optimal angle and pressure of the cutting tool are calculated, and sensor data in the real-time cutting process, including the current position, speed, cutting angle and pressure of the robot arm, are collected to form a cutting feedback data set; The cropping feedback dataset is analyzed using the formula: ； Calculate the new position of the robot arm ,in, is the current location, is the expected distance between the target position and the current position, is the difference between the measured position and the current position, is the adjustment factor; The new position of the robot arm is fed back to the control system, the operating parameters of the robot arm are updated in real time, the alignment and motion control during the cutting process are optimized, and the robot arm position optimization result is obtained.

6. The light guide film cutting and positioning system based on machine vision according to claim 1, characterized in that: The steps for obtaining the dynamic adjustment parameters of cutting are specifically as follows: Collect sensor data from the real-time cutting process, integrate the data, and build a cutting process data set; Based on the cutting process data set, the optimal tool angle and pressure required for each cutting are predicted, and according to the historical cutting effect and the feedback information of the current light guide film, the tool parameters are dynamically optimized to obtain the optimized tool parameters; The optimized tool parameters are applied to the cutting process, and the tool angle and pressure are repeatedly adjusted through the control system to obtain the dynamic adjustment parameters for cutting.

7. The light guide film cutting and positioning system based on machine vision according to claim 1, characterized in that: The steps for obtaining the cutting effect optimization result are specifically as follows: Based on the cutting dynamic adjustment parameters, real-time monitoring data of the cutting operation is collected, including tool speed, accuracy and motion trajectory, to form a real-time cutting monitoring data set; Based on the real-time cutting monitoring data set, compared with the preset cutting standard, the formula is used: ； Calculate the overall cutting error value ,in, It is The current measured value, It is The preset standard values ​​of the parameters, It is The weight factor of the parameter, is the total number of cutting parameters; Based on the overall cutting error value, a back propagation algorithm is executed, and the convolutional neural network parameters are adjusted in combination with the historical cutting data of the light-guiding film to obtain a cutting effect optimization result.

Images