A rubber mold size parameter measurement method and system

Abstract

The present invention relates to the field of optical measurement technology, and discloses a rubber mold size parameter measurement method and system. The method collects rubber mold image data of different batches by installing a laser camera, and processes the rubber mold image data of different batches in a training data set based on an image processing method. At the same time, based on the processed rubber mold image data, a background separation method is used to extract the rubber mold image contour, and based on the extracted rubber mold image contours of different batches, the optimal standard size parameters of the rubber mold are determined by a genetic algorithm and the standard size parameter range of the rubber mold is set, and then the rubber mold size parameters of the current batch are determined by real-time collection of the rubber mold image data of the current batch and by contour comparison, thereby improving the efficiency of rubber mold size parameter measurement.

Description

Technical Field

[0001] The invention relates to the technical field of optical measurement, and in particular to a method and system for measuring size parameters of a rubber mould. Background Art

[0002] Due to its easy ductility and strong plasticity, rubber is currently widely used in mold manufacturing. However, due to the poor thermoplastic effect of rubber, the dimensional stability of rubber molds is insufficient, and manual measurement and modification are inefficient and ineffective, which cannot meet actual needs.

[0003] The existing Chinese patent application CN117739852A, this method determines the relative position of the processed inner surface by continuously moving the laser device; at the same time, the contour information of the first contour of the processed inner surface and the contour information of the second contour of the first surface are measured by the laser device; and the endpoint coordinates of the pattern block contour are determined according to the coordinate queue corresponding to the first contour measurement and the coordinate queue corresponding to the second contour measurement; and the size information of the pattern block is calculated according to the determined endpoint coordinates to perform laser cleaning path planning, but the rough surface of the pattern block itself is ignored, and the laser measurement is easily disturbed and has certain limitations. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides a method and system for measuring the size parameters of a rubber mold, which has the advantages of accuracy, efficiency, and real-time, and solves the problem that the size stability of the rubber mold is insufficient due to the poor thermoplastic effect of rubber, and the manual measurement and modification is inefficient and ineffective, and cannot meet actual needs.

[0006] (II) Technical solution

[0007] In order to solve the above technical problems that the dimensional stability of the rubber mold is insufficient due to the poor rubber thermoplastic effect, and the manual measurement and modification is inefficient and ineffective, and cannot meet the actual needs, the present invention provides the following technical solutions:

[0008] This embodiment discloses a method for measuring size parameters of a rubber mold, which specifically includes the following steps:

[0009] S1. Install a laser camera to collect image data of rubber molds from different batches and establish a training data set;

[0010] S2, processing different batches of rubber mold image data in the training data set based on an image processing method to obtain processed rubber mold image data;

[0011] S3, extracting the rubber mold image contour by a background separation method based on the processed rubber mold image data;

[0012] S4, based on the extracted image contours of different batches of rubber molds, determining the optimal standard size parameters of the rubber molds and setting the standard size parameter range of the rubber molds through a genetic algorithm;

[0013] S5. Collect the rubber mold image data of the current batch in real time, extract the rubber mold image contours of the rubber mold image data of the current batch, and determine the size parameters of the rubber molds of the current batch by contour comparison.

[0014] The present invention collects rubber mold image data of different batches by installing a laser camera and processes the rubber mold image data of different batches in a training data set based on an image processing method. At the same time, based on the processed rubber mold image data, a background separation method is used to extract the rubber mold image contour. Based on the extracted rubber mold image contours of different batches, the optimal standard size parameters of the rubber mold are determined by a genetic algorithm and the standard size parameter range of the rubber mold is set. Furthermore, the size parameters of the rubber mold of the current batch are determined by real-time collection of the rubber mold image data of the current batch and by contour comparison, thereby improving the efficiency of rubber mold size parameter measurement.

[0015] Preferably, the steps of installing a laser camera, collecting image data of rubber molds of different batches, and establishing a training data set include the following steps:

[0016] Set the positions of all feature points on the rubber mold and fix the relative positions of the camera and the rubber mold so that the feature points on the rubber mold are evenly distributed in the entire camera field of view;

[0017] Within the preset working range of the laser camera, according to the preset sampling interval, different batches of rubber mold images taken by the laser camera are collected, and a training data set is established.

[0018] The present invention sets the positions of all feature points on the rubber mold and fixes the relative positions of the camera and the rubber mold. It also collects rubber mold images taken by laser cameras of different batches and establishes a training data set to ensure the accuracy of rubber mold image acquisition.

[0019] Preferably, the method of processing different batches of rubber mold image data in the training data set based on the image processing method to obtain the processed rubber mold image data comprises the following steps:

[0020] S21, selecting a pixel point in the image data of the training data set, and setting a rectangular window with the pixel point as the center;

[0021] S22. Calculate the average grayscale value of all pixels in the set rectangular window by using a mean filtering algorithm.

[0022] Preferably, the step of calculating the average grayscale value of all pixels in a set rectangular window by using a mean filtering algorithm comprises the following steps:

[0023] Set the rectangular window size to n×n;

[0024] The calculation formula of the mean filter algorithm is as follows:

[0025]

[0026] in, Indicates that the selected coordinates are The gray value after mean filtering, n represents the window size, Indicates that the coordinates in the window are Gray value of

[0027] The value of the selected pixel point calculated by the mean filtering algorithm is used as the grayscale value of the pixel point, and data processing is performed on all the pixel points in the image data of the training data set to obtain the processed image data.

[0028] The present invention improves the validity of image data by selecting pixel points in the image data of the training data set, setting a rectangular window with the pixel point as the center, and filtering the image data of the training data set by calculating the average grayscale value of all pixel points in the set rectangular window through a mean filtering algorithm.

[0029] Preferably, the extracting the rubber mold image contour based on the processed rubber mold image data by a background separation method comprises the following steps:

[0030] S31, initializing fuzzy mean algorithm parameters;

[0031] Set the total number of pixels of the processed image data to N and divide it into category A. For each class’s center point, Represents about point and Class The matrix, objective function and constraint condition of the fuzzy mean algorithm are as follows:

[0032] Objective function: ;

[0033] Constraints: ;

[0034] Where m is the blur index, which is the blur degree in the captured image. Indicates The center point of the class, represents the collected feature points, Indicate point To Class center The distance, J represents the objective function;

[0035] S32, performing iterative clustering operation on similar pixel points to complete the separation of image target and background.

[0036] Preferably, the iterative clustering operation is performed on the pixels of the same type to separate the image target from the background, comprising the following steps:

[0037] Based on the initially set center point of each class, calculate the distance from the random point in the class to the center point of the class;

[0038] The center point of each class is continuously adjusted according to the constraints, and the iteration is continued until the center points of all classes no longer change and the iteration stops;

[0039] By finding the minimum value of the objective function corresponding to each feature point, the pixel points in the image are classified, thereby achieving the separation of the image target and the background;

[0040] Cluster centers updated based on clustering algorithm and matrix As shown below:

[0041] ;

[0042] ;

[0043] in, represents the center point of the kth class; Indicate point To Class center The distance Indicate point To the center point of the kth class distance;

[0044] Through continuous iterative clustering, the pixel types are converged into two categories. By setting the grayscale values ​​of the two types of pixels respectively, the rubber mold image contour is extracted and the feature points of the rubber mold image contour are recorded.

[0045] The present invention classifies the pixel points of the processed image data by initializing the fuzzy mean algorithm parameters and performs iterative clustering operation on the pixel points of the same type to complete the separation of the image target and the background. At the same time, by respectively setting the gray values ​​of the two types of pixel points, the rubber mold image contour is extracted and the rubber mold image contour feature points are recorded, thereby improving the accuracy of rubber mold image contour extraction.

[0046] Preferably, the method of determining the optimal standard size parameters of the rubber mold and setting the standard size parameter range of the rubber mold by genetic algorithm based on the extracted image contours of different batches of rubber molds comprises the following steps:

[0047] S41, set the genetic population size, number of iterations and chromosome encoding;

[0048] S42, Randomly generate initial population ;

[0049] S43, using the parameter averaging algorithm as the fitness function of the genetic algorithm, and calculating the fitness of each individual in the population;

[0050] Each individual is set to represent a set of extracted contour feature points of the rubber mold image;

[0051] Set the coordinates of the center point of the extracted rubber mold image contour, calculate the distance from each extracted rubber mold image contour feature point to the center point of the extracted rubber mold image contour, and calculate the average value of the distance from each extracted rubber mold image contour feature point to the center point of the extracted rubber mold image contour ;

[0052] The fitness calculation formula for each individual is as follows:

[0053] ;

[0054] in, represents the fitness of the tth individual;

[0055] S44, selecting the best individuals from all individuals based on the roulette wheel method;

[0056] The calculation formula for selecting the best individuals among all individuals by roulette is as follows:

[0057]

[0058] in, represents the probability of the tth individual being selected, represents probability, T represents population size;

[0059] S45. Cross the selected excellent individuals through sequential crossover to generate a new population ;

[0060] S46. Randomly select an individual in the population and perform marginalization with a set probability to generate a mutated population ;

[0061] S47. Compare the fitness difference between the initial population and the population after genetic algorithm crossover mutation ;

[0062] when <0, indicating that the fitness of the mutated population is higher than that of the initial population. Accept the population. ≥0, indicating that the fitness of the mutated population is lower than that of the initial population, and the population is rejected;

[0063] S48, judging whether the maximum number of iterations has been reached according to the number of iterations of the algorithm, outputting the optimal solution when the maximum number of iterations has been reached, and continuing to execute step S44 when the maximum number of iterations has not been reached;

[0064] A set of extracted rubber mold image contour feature points represented by the output optimal solution is set as the optimal standard size parameters of the rubber mold;

[0065] The rubber mold construction error range is set, and the rubber mold standard size parameter range of each rubber mold image contour feature point is determined based on the rubber mold optimal standard size parameter.

[0066] The present invention extracts rubber mold image contours of different batches, continuously iterates and calculates the optimal standard size parameters of the rubber mold through a genetic algorithm, and sets the standard size parameter range of the rubber mold based on the calculated optimal standard size parameters of the rubber mold, thereby improving the reliability of determining the rubber mold standard.

[0067] Preferably, the real-time acquisition of the current batch of rubber mold image data, extraction of the rubber mold image contours of the current batch of rubber mold image data, and determination of the current batch of rubber mold size parameters by contour comparison comprises the following steps:

[0068] definition It represents the optimal standard size parameters of the rubber mold. The projection image of the optimal standard size parameters of the rubber mold on the two-dimensional plane is , the contour image extracted from the projection image of the two-dimensional plane is set to ; Set the rubber mold image contour for extracting the current batch of rubber mold image data to ; Through the similarity function To judge the contour image , degree of overlap;

[0069]

[0070] in, For two outlines and The area of ​​the overlapping part, and are the areas of the corresponding contours respectively; , the larger S is, the more similar the two regions are. When the two regions overlap, ;

[0071] when When , it means that the current batch of rubber molds has the optimal standard size parameters;

[0072] when When the dissimilar feature points are selected, the distances between the dissimilar contour feature points and the optimal standard size parameters are calculated, and the size parameters of all contour feature points of the current batch of rubber molds are output.

[0073] The present invention is adopted.

[0074] This embodiment also discloses a rubber mold size parameter measurement system, including: an image acquisition module, an image processing module, a contour extraction module, a standard size determination module and a rubber mold size parameter determination module;

[0075] The image acquisition module is used to collect image data of rubber molds of different batches and transmit them to the image processing module;

[0076] The image processing module is used to process the received rubber mold image data to obtain processed rubber mold image data;

[0077] The contour extraction module is used to extract the contour of the processed rubber mold image data;

[0078] The standard size determination module is used to determine the standard size parameters of the rubber mold image contour according to the rubber mold image contours of different batches;

[0079] The rubber mold size parameter determination module is used to determine the real-time rubber mold size parameters according to the contour comparison method.

[0080] (III) Beneficial effects

[0081] Compared with the prior art, the present invention provides a method and system for measuring the size parameters of a rubber mold, which has the following beneficial effects:

[0082] 1. The invention collects rubber mold image data of different batches by installing a laser camera and processes the rubber mold image data of different batches in a training data set based on an image processing method. At the same time, based on the processed rubber mold image data, the rubber mold image contour is extracted by a background separation method. Based on the extracted rubber mold image contours of different batches, the optimal standard size parameters of the rubber mold are determined by a genetic algorithm and the standard size parameter range of the rubber mold is set. Then, the size parameters of the current batch of rubber molds are determined by real-time collection of the rubber mold image data of the current batch and by contour comparison, the efficiency of measuring the size parameters of the rubber molds is improved.

[0083] 2. The invention sets the positions of all feature points on the rubber mold and fixes the relative positions of the camera and the rubber mold. It also collects rubber mold images taken by laser cameras from different batches and establishes a training data set to ensure the accuracy of rubber mold image acquisition.

[0084] 3. The invention improves the validity of the image data by selecting pixel points in the image data of the training data set, setting a rectangular window with the pixel point as the center, and filtering the image data of the training data set by calculating the average grayscale value of all pixel points in the set rectangular window through a mean filtering algorithm.

[0085] 4. The present invention classifies the pixels of the processed image data by initializing the fuzzy mean algorithm parameters and performs iterative clustering operations on the pixels of the same type to separate the image target from the background. At the same time, by separately setting the grayscale values ​​of the two types of pixels, the rubber mold image contour is extracted and the feature points of the rubber mold image contour are recorded, thereby improving the accuracy of the rubber mold image contour extraction.

[0086] 5. The invention extracts the image contours of rubber molds from different batches, continuously iterates and calculates the optimal standard size parameters of the rubber molds through a genetic algorithm, and sets the standard size parameter range of the rubber mold based on the calculated optimal standard size parameters of the rubber mold, thereby improving the reliability of determining the rubber mold standard.

[0087] 6. The invention collects the rubber mold image data of the current batch in real time, extracts the rubber mold image contour of the current batch of rubber mold image data, and calculates the distance between the dissimilar contour feature points and the optimal standard size parameters by contour comparison, thereby improving the real-time measurement of the rubber mold size parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Figure 1 It is a schematic diagram of the structure of the rubber mold size parameter measurement process of the present invention. DETAILED DESCRIPTION

[0089] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0090] Example 1

[0091] See also Figure 1 This embodiment discloses a method for measuring the size parameters of a rubber mold, which specifically includes the following steps:

[0092] S1. Install a laser camera to collect image data of rubber molds from different batches and establish a training data set;

[0093] Installing a laser camera, collecting image data of different batches of rubber molds, and establishing a training data set include the following steps:

[0094] Set the positions of all feature points on the rubber mold and fix the relative positions of the camera and the rubber mold so that the feature points on the rubber mold are evenly distributed in the entire camera field of view;

[0095] Within the preset working range of the laser camera, according to the preset sampling interval, collect rubber mold images taken by the laser camera in different batches, and establish a training data set;

[0096] S2, processing different batches of rubber mold image data in the training data set based on an image processing method to obtain processed rubber mold image data;

[0097] Processing different batches of rubber mold image data in the training data set based on the image processing method to obtain the processed rubber mold image data includes the following steps:

[0098] S21, selecting a pixel point in the image data of the training data set, and setting a rectangular window with the pixel point as the center;

[0099] S22, calculating the average grayscale value of all pixels in the set rectangular window by using a mean filtering algorithm;

[0100] Set the rectangular window size to n×n;

[0101] The calculation formula of the mean filter algorithm is as follows:

[0102]

[0103] in, Indicates that the selected coordinates are The gray value after mean filtering, n represents the window size, Indicates that the coordinates in the window are Gray value of

[0104] The value of the selected pixel point calculated by the mean filtering algorithm is used as the grayscale value of the pixel point, and data processing is performed on all the pixel points in the image data of the determined training data set to obtain processed image data;

[0105] S3, extracting the rubber mold image contour by a background separation method based on the processed rubber mold image data;

[0106] Based on the processed rubber mold image data obtained, extracting the rubber mold image contour by a background separation method includes the following steps:

[0107] S31, initializing fuzzy mean algorithm parameters;

[0108] Set the total number of pixels of the processed image data to N and divide it into category A. For each class’s center point, Represents about point and Class The matrix, objective function and constraint condition of the fuzzy mean algorithm are as follows:

[0109] Objective function: ;

[0110] Constraints: ;

[0111] Where m is the blur index, which is the blur degree in the captured image. Indicates The center point of the class, represents the collected feature points, Indicate point To Class center The distance, J represents the objective function;

[0112] S32, performing iterative clustering operation on similar pixel points to complete the separation of image target and background;

[0113] The iterative clustering operation for similar pixels includes:

[0114] Based on the initially set center point of each class, calculate the distance from the random point in the class to the center point of the class;

[0115] The center point of each class is continuously adjusted according to the constraints, and the iteration is continued until the center points of all classes no longer change and the iteration stops;

[0116] Furthermore, by finding the minimum value of the objective function corresponding to each feature point, the pixel points in the image are classified, thereby achieving the separation of the image target and the background;

[0117] Furthermore, the cluster centers updated based on the clustering algorithm and matrix As shown below:

[0118] ;

[0119] ;

[0120] in, represents the center point of the kth class; Indicate point To Class center The distance Indicate point To the center point of the kth class distance;

[0121] Furthermore, by continuous iterative clustering, the pixel types are converged into two categories, and the rubber mold image contour is extracted by respectively setting the grayscale values ​​of the two types of pixels, and the rubber mold image contour feature points are recorded;

[0122] S4, based on the extracted image contours of different batches of rubber molds, determining the optimal standard size parameters of the rubber molds and setting the standard size parameter range of the rubber molds through a genetic algorithm;

[0123] Based on the extracted rubber mold image contours of different batches, determining the optimal standard size parameters of the rubber mold and setting the standard size parameter range of the rubber mold by genetic algorithm includes the following steps:

[0124] S41, set the genetic population size, number of iterations and chromosome encoding;

[0125] S42, Randomly generate initial population ;

[0126] S43, using the parameter averaging algorithm as the fitness function of the genetic algorithm, and calculating the fitness of each individual in the population;

[0127] Each individual is set to represent a set of extracted contour feature points of the rubber mold image;

[0128] Set the coordinates of the center point of the extracted rubber mold image contour, calculate the distance from each extracted rubber mold image contour feature point to the center point of the extracted rubber mold image contour, and calculate the average value of the distance from each extracted rubber mold image contour feature point to the center point of the extracted rubber mold image contour ;

[0129] The fitness calculation formula for each individual is as follows:

[0130] ;

[0131] in, represents the fitness of the tth individual;

[0132] S44, selecting the best individuals from all individuals based on the roulette wheel method;

[0133] The calculation formula for selecting the best individuals among all individuals by roulette is as follows:

[0134]

[0135] in, represents the probability of the tth individual being selected, represents probability, T represents population size;

[0136] S45. Cross the selected excellent individuals through sequential crossover to generate a new population ;

[0137] S46. Randomly select an individual in the population and perform marginalization with a set probability to generate a mutated population ;

[0138] S47. Compare the fitness difference between the initial population and the population after genetic algorithm crossover mutation ;

[0139] when <0, indicating that the fitness of the mutated population is higher than that of the initial population. Accept the population. ≥0, indicating that the fitness of the mutated population is lower than that of the initial population, and the population is rejected;

[0140] S48, judging whether the maximum number of iterations has been reached according to the number of iterations of the algorithm, outputting the optimal solution when the maximum number of iterations has been reached, and continuing to execute step S44 when the maximum number of iterations has not been reached;

[0141] A set of extracted rubber mold image contour feature points represented by the output optimal solution is set as the optimal standard size parameters of the rubber mold;

[0142] Further, the rubber mold construction error range is set, and the rubber mold standard size parameter range of each rubber mold image contour feature point is determined based on the rubber mold optimal standard size parameter;

[0143] S5, collecting the current batch of rubber mold image data in real time, extracting the rubber mold image contour of the current batch of rubber mold image data, and determining the size parameters of the current batch of rubber molds by contour comparison;

[0144] Real-time acquisition of the current batch of rubber mold image data, extraction of the rubber mold image contours of the current batch of rubber mold image data, and determination of the current batch of rubber mold size parameters by contour comparison include the following steps:

[0145] definition It represents the optimal standard size parameters of the rubber mold. The projection image of the optimal standard size parameters of the rubber mold on the two-dimensional plane is , the contour image extracted from the projection image of the two-dimensional plane is set to ; Set the rubber mold image contour for extracting the current batch of rubber mold image data to ; Through the similarity function To judge the contour image , degree of overlap;

[0146]

[0147] in, For two outlines and The area of ​​the overlapping part, and are the areas of the corresponding contours respectively; , the larger S is, the more similar the two regions are. When the two regions overlap, ;

[0148] when When , it means that the current batch of rubber molds has the optimal standard size parameters;

[0149] when , select dissimilar feature points, calculate the distance between dissimilar contour feature points and the optimal standard size parameters, and output the size parameters of all contour feature points of the current batch of rubber molds;

[0150] Example 2

[0151] This embodiment also discloses a rubber mold size parameter measurement system, including: an image acquisition module, an image processing module, a contour extraction module, a standard size determination module and a rubber mold size parameter determination module;

[0152] The image acquisition module is used to collect image data of rubber molds of different batches and transmit them to the image processing module;

[0153] The image processing module is used to process the received rubber mold image data to obtain processed rubber mold image data;

[0154] The contour extraction module is used to extract the contour of the processed rubber mold image data;

[0155] The standard size determination module is used to determine the standard size parameters of the rubber mold image contour according to the rubber mold image contours of different batches;

[0156] The rubber mold size parameter determination module is used to determine the real-time rubber mold size parameters according to the contour comparison method.

[0157] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for measuring dimensional parameters of a rubber mold, characterized in that: The following steps are involved: S1. Install a laser camera to collect image data of rubber molds from different batches and establish a training data set; S2, processing different batches of rubber mold image data in the training data set based on an image processing method to obtain processed rubber mold image data; S3, extracting the rubber mold image contour by a background separation method based on the processed rubber mold image data; The method of extracting the rubber mold image contour based on the processed rubber mold image data by a background separation method comprises the following steps: S31, initializing fuzzy mean algorithm parameters; Set the total number of pixels of the processed image data to N and divide it into category A. For the center point of each class, Represents about point and Class The matrix, objective function and constraint condition of the fuzzy mean algorithm are as follows: Objective function: ; Constraints: ; Where m is the blur index, which is the blur degree in the captured image. Indicates The center point of the class, represents the collected feature points, Indicate point To Class center The distance, J represents the objective function; S32, performing iterative clustering operation on similar pixel points to complete the separation of image target and background; The iterative clustering operation is performed on the pixels of the same type to separate the image target from the background, and the following steps are included: Based on the initially set center point of each class, calculate the distance from the random point in the class to the center point of the class; The center point of each class is continuously adjusted according to the constraints, and the iteration is continued until the center points of all classes no longer change and the iteration stops; By finding the minimum value of the objective function corresponding to each feature point, the pixel points in the image are classified, thereby achieving the separation of the image target and the background; Cluster centers updated based on clustering algorithm and matrix As shown below: ； ； in, represents the center point of the kth class; Indicate point To Class center The distance Indicate point To the center point of the kth class distance; Through continuous iterative clustering, the pixel types are converged into two categories. By setting the gray values ​​of the two types of pixels respectively, the rubber mold image contour is extracted and the rubber mold image contour feature points are recorded. S4, based on the extracted image contours of different batches of rubber molds, determining the optimal standard size parameters of the rubber molds and setting the standard size parameter range of the rubber molds through a genetic algorithm; S5, collecting the current batch of rubber mold image data in real time, extracting the rubber mold image contour of the current batch of rubber mold image data, and determining the size parameters of the current batch of rubber molds by contour comparison; The real-time acquisition of the current batch of rubber mold image data, extraction of the rubber mold image contours of the current batch of rubber mold image data, and determination of the current batch of rubber mold size parameters by contour comparison include the following steps: definition It represents the optimal standard size parameters of the rubber mold. The projection image of the optimal standard size parameters of the rubber mold on the two-dimensional plane is , the contour image extracted from the projection image of the two-dimensional plane is set to ; Set the rubber mold image contour for extracting the current batch of rubber mold image data to ; Through the similarity function To judge the contour image , degree of overlap; ； in, For two outlines and The area of ​​the overlapping part, and are the areas of the corresponding contours respectively; , the larger S is, the more similar the two regions are. When the two regions overlap, ; when When , it means that the current batch of rubber molds has the optimal standard size parameters; when When the dissimilar feature points are selected, the distances between the dissimilar contour feature points and the optimal standard size parameters are calculated, and the size parameters of all contour feature points of the current batch of rubber molds are output.

2. A method for measuring size parameters of a rubber mold according to claim 1, characterized in that: The steps of installing a laser camera, collecting image data of rubber molds of different batches, and establishing a training data set include the following steps: Set the positions of all feature points on the rubber mold and fix the relative positions of the camera and the rubber mold so that the feature points on the rubber mold are evenly distributed in the entire camera field of view; Within the preset working range of the laser camera, according to the preset sampling interval, different batches of rubber mold images taken by the laser camera are collected, and a training data set is established.

3. A method for measuring size parameters of a rubber mold according to claim 1, characterized in that: The method of processing the rubber mold image data of different batches in the training data set based on the image processing method to obtain the processed rubber mold image data includes the following steps: S21, selecting a pixel point in the image data of the training data set, and setting a rectangular window with the pixel point as the center; S22. Calculate the average grayscale value of all pixels in the set rectangular window by using a mean filtering algorithm.

4. A method for measuring size parameters of a rubber mold according to claim 3, characterized in that: The method of calculating the average grayscale value of all pixels in the set rectangular window by using the mean filtering algorithm includes the following steps: Set the rectangular window size to n×n; The calculation formula of the mean filter algorithm is as follows: ； in, Indicates that the selected coordinates are The gray value after mean filtering, n represents the window size, Indicates that the coordinates in the window are Gray value of The value of the selected pixel point calculated by the mean filtering algorithm is used as the grayscale value of the pixel point, and data processing is performed on all the pixel points in the image data of the training data set to obtain the processed image data.

5. A method for measuring size parameters of a rubber mold according to claim 1, characterized in that: The method of determining the optimal standard size parameters of the rubber mold and setting the standard size parameter range of the rubber mold by a genetic algorithm based on the extracted image contours of different batches of rubber molds comprises the following steps: S41, set the genetic population size, number of iterations and chromosome encoding; S42, Randomly generate initial population ; S43, using the parameter averaging algorithm as the fitness function of the genetic algorithm, and calculating the fitness of each individual in the population; Each individual is set to represent a set of extracted contour feature points of the rubber mold image; Set the coordinates of the center point of the extracted rubber mold image contour, calculate the distance from each extracted rubber mold image contour feature point to the center point of the extracted rubber mold image contour, and calculate the average value of the distance from each extracted rubber mold image contour feature point to the center point of the extracted rubber mold image contour ; The fitness calculation formula for each individual is as follows: ； in, represents the fitness of the tth individual; S44, selecting the best individuals from all individuals based on the roulette wheel method; The calculation formula for selecting the best individuals among all individuals by roulette is as follows: ； in, represents the probability of the tth individual being selected, represents probability, T represents population size; S45. Cross the selected excellent individuals through sequential crossover to generate a new population ; S46. Randomly select an individual in the population and perform marginalization with a set probability to generate a mutated population ; S47. Compare the fitness difference between the initial population and the population after genetic algorithm crossover mutation ; when <0, indicating that the fitness of the mutated population is higher than that of the initial population. Accept the population. ≥0, indicating that the fitness of the mutated population is lower than that of the initial population, and the population is rejected; S48, judging whether the maximum number of iterations has been reached according to the number of iterations of the algorithm, outputting the optimal solution when the maximum number of iterations has been reached, and continuing to execute step S44 when the maximum number of iterations has not been reached; A set of extracted rubber mold image contour feature points represented by the output optimal solution is set as the optimal standard size parameters of the rubber mold; The rubber mold construction error range is set, and the rubber mold standard size parameter range of each rubber mold image contour feature point is determined based on the rubber mold optimal standard size parameter.

6. A system for implementing the rubber mold size parameter measurement method according to any one of claims 1 to 5, characterized in that: include: Image acquisition module, image processing module, contour extraction module, standard size determination module and rubber mold size parameter determination module; The image acquisition module is used to collect image data of rubber molds of different batches and transmit them to the image processing module; The image processing module is used to process the received rubber mold image data to obtain processed rubber mold image data; The contour extraction module is used to extract the contour of the processed rubber mold image data; The standard size determination module is used to determine the standard size parameters of the rubber mold image contour according to the rubber mold image contours of different batches; The rubber mold size parameter determination module is used to determine the real-time rubber mold size parameters according to the contour comparison method.

Images