Personnel information automatic identification system based on support vector machine and black wing algorithm
By setting up an automatic personnel information identification system based on the support vector machine and the black-winged kite algorithm at the construction site, the problem of cumbersome and omissions in the verification of personnel access information on the construction site is solved, and the automatic access identification of construction personnel is realized, which improves the safety and efficiency of the construction site.
Patent Information
- Application Number
- CN202411550272.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-01
- Publication Date
- 2025-02-28
AI Technical Summary
At the construction site, the work person in charge needs to manually check the access information of the construction personnel, which leads to cumbersome workload and forgetful verification, which may cause the unaccepted personnel to enter the construction site.
A personnel information automatic identification system based on support vector machine and black-winged kite algorithm is designed. Through the collection, preprocessing, comparison, mapping and authority judgment modules, the automatic identification of construction personnel's facial information and the judgment of access rights are realized, so as to avoid unaccessible personnel entering the construction site.
The system can perform facial recognition before construction personnel enter the construction site, ensure that all incoming personnel have access information, reduce the verification work of safety patrol personnel, and improve the safety and efficiency of the construction site.
Smart Images
Figure CN119541016A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of face recognition, and in particular to an automatic personnel information recognition system based on a support vector machine and a black kite algorithm. Background Art
[0002] In recent years, with the rapid economic development in Mianzhu, the number of power grid construction projects and maintenance work has gradually increased, and the number of on-site subcontractors has also gradually increased. According to the current safety production management regulations, in order to implement the five four requirements of safety production, manage the team and the personnel, it is necessary to strengthen personnel management during the on-site construction process, especially to assess whether the on-site personnel participating in the operation have completed the access. If the on-site operator does not complete the personnel information access, it is a serious violation of regulations. Before each operation, the access information of the work team members must be checked one by one, so that the work leader and the on-site safety inspector can check the access information of the operator. Especially for the subcontractor team members, there is a certain degree of mobility among the subcontractor team members. If they are not careful, some unauthorized personnel may enter the construction site to work. Therefore, the person in charge of the work will check the access information of the personnel one by one before the operation, but at present, the person in charge of the work manually enters and checks the access information of the personnel one by one before the operation, which is cumbersome and there is a situation where the person in charge of the work forgets to check. Therefore, it is necessary to develop a method and system that can quickly identify personnel information to solve the above problems. Summary of the invention
[0003] The present invention provides a personnel information automatic recognition system based on a support vector machine and a black kite algorithm, so as to ensure that all construction personnel in a construction site are authorized personnel without the need for verification by the person in charge of the work.
[0004] The present invention is achieved through the following technical solutions:
[0005] A personnel information automatic recognition system based on support vector machine and black kite algorithm, comprising:
[0006] An acquisition module, used to obtain an initial image of the person to be detected;
[0007] A preprocessing module, used for preprocessing the initial image to obtain a facial image of the person to be detected;
[0008] A comparison module, used for inputting the face image into a support vector machine trained based on the Black Kite algorithm for classification, so as to obtain the face information of the person to be detected;
[0009] A mapping module, used to find the personnel information of the person to be detected according to the facial information;
[0010] The authority judgment module is used to judge whether the personnel information of the person to be detected has access authority;
[0011] The alarm module performs a corresponding alarm operation when the authority judgment module determines that the personnel information has no access authority.
[0012] As an optimization, the initial image is preprocessed to obtain the face image of the person to be detected. The specific process is:
[0013] The initial image is subjected to denoising processing, and the background segmentation processing is performed on the initial image after the denoising processing to obtain a face image.
[0014] As an optimization, a set of penalty coefficients C and kernel function σ of the support vector machine are 2 Assume that it is a black-winged kite individual, and the output of the support vector machine is the position of the black-winged kite individual. The specific process of training the support vector machine based on the black-winged kite algorithm is as follows:
[0015] A1, initializing the algorithm parameters of the black-winged kite algorithm, wherein the algorithm parameters include the number of black-winged kite populations, the maximum number of iterations, and the optimization range;
[0016] A2. Randomly initialize the black-winged kite population;
[0017] A3, respectively input the training samples into the support vector machine corresponding to the black-winged kite population, and calculate the fitness value generated by the location of each black-winged kite individual;
[0018] A4, reordering the black-winged kite individuals according to the fitness values;
[0019] A5. performing attacking and migrating behaviors on the reordered black-winged kite individuals, thereby updating the positions of the black-winged kite individuals;
[0020] A6. Determine whether the maximum number of iterations has been reached. If so, terminate the process and output the current black-winged kite population. The support vector machine corresponding to the black-winged kite individual with the largest fitness value in the black-winged kite population is the optimal support vector machine. Otherwise, return to A3.
[0021] As an optimization, the fitness value is the ratio of correct samples output by the support vector machine to the training samples.
[0022] As an optimization, the specific formula for randomly initializing the black-winged kite population is:
[0023] X i =BK lb +rand(BK ub -BK lb )
[0024] Among them, X i Indicates the position of the i-th black-winged kite individual, i is an integer between 1 and pop, pop is the number of black-winged kites in the black-winged kite population, BK lb and BK ub are the lower and upper bounds of the j-th dimension black-winged kite individual, and rand is a randomly selected value between [0,1].
[0025] As an optimization, the mathematical model of the attack behavior of the black-winged kite individual is:
[0026]
[0027] in, represents the position of the i-th black-winged kite individual in the j-th dimension and the t+1-th iteration step; represents the position of the i-th black-winged kite individual in the j-th dimension and the t-th iteration step; r is a random number between 0 and 1, p is a constant of 0.9; T is the maximum number of iterations, and t is the number of iterations completed so far.
[0028] As an optimization, the mathematical model of the migration behavior of the black-winged kite individual is:
[0029]
[0030] m=2×sin(r+π / 2)
[0031] in, represents the position of the i-th black-winged kite individual in the j-th dimension and the t+1-th iteration step; represents the position of the i-th black-winged kite individual in the j-th dimension and the t-th iteration step; F represents the leading scorer of the j-th dimension black-winged kite individual in the t-th iteration so far, that is, the optimal black-winged kite individual with the largest fitness value, i represents the j-th dimension current position of any black-winged kite individual in the t-th iteration; F ri represents the fitness value of any black kite individual at a random position in the jth dimension in the tth iteration; C(0,1) represents the Cauchy mutation.
[0032] As an optimization, the specific expression of Cauchy mutation is:
[0033]
[0034] Here, x represents a random variable.
[0035] As an optimization, a display module is further included, and the display module is used to display the judgment result of the authority judgment module, the mapping result of the mapping module and the comparison result of the comparison module.
[0036] The acquisition module is a camera device that collects facial information of people entering the camera area. When the authority judgment module determines that the person information has no access authority, the alarm module issues an alarm message of non-access.
[0037] Compared with the prior art, the present invention has the following advantages and beneficial effects:
[0038] By setting up the identification system of the present invention at the "entry and exit" entrance of the construction site, the construction workers will be subject to facial recognition before entering the construction site, thereby ensuring that the construction workers entering the construction site have access information, thereby reducing the need for security inspectors to check the access information of the construction workers.
[0039] The authority module provided in the present invention can prevent unauthorized personnel from following authorized construction personnel into the construction site.
[0040] The present invention utilizes the powerful global search capability and the characteristic of avoiding local optimal traps of the Black Kite algorithm to enable the training of the support vector machine to be more accurate and rapid, and at the same time, improves the generalization ability and recognition accuracy of the support vector machine. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:
[0042] Figure 1 The present invention is a schematic diagram of the module connection of a personnel information automatic recognition system based on a support vector machine and a black kite algorithm. DETAILED DESCRIPTION
[0043] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.
[0044] This embodiment 1 provides a personnel information automatic recognition system based on support vector machine and black kite algorithm, such as Figure 1 As shown, including:
[0045] An acquisition module, used to obtain an initial image of the person to be detected;
[0046] A preprocessing module, used for preprocessing the initial image to obtain a facial image of the person to be detected;
[0047] A comparison module, used for inputting the face image into a support vector machine trained based on the Black Kite algorithm for classification, so as to obtain the face information of the person to be detected;
[0048] A mapping module, used to find the personnel information of the person to be detected according to the facial information;
[0049] The authority judgment module is used to judge whether the personnel information of the person to be detected has access authority;
[0050] An execution module, which executes corresponding operations after the authority judgment module determines that the personnel information has access authority;
[0051] A display module is used to display the judgment result of the authority judgment module, the mapping result of the mapping module and the comparison result of the comparison module.
[0052] The acquisition module is a camera device that collects facial information of people entering the camera area. When the authority judgment module determines that the person information has no access authority, the alarm module issues an alarm message of non-access.
[0053] The alarm module can be an audible and visual alarm.
[0054] Specifically, the acquisition module can be a camera, the display module is a display, and the camera can be installed above the display. In order to prevent the rear personnel from following the front personnel into the room.
[0055] Among them, the preprocessing module, the comparison module, the mapping module, and the permission judgment module are all set in the same controller. The controller can be a 51 single-chip microcomputer or an STM32 series, which will not be repeated here.
[0056] In some embodiments, the specific process of the preprocessing module preprocessing the initial image to obtain the facial image of the person to be detected is:
[0057] The initial image is subjected to denoising processing, and the background segmentation processing is performed on the initial image after the denoising processing to obtain a face image.
[0058] Here, noise reduction processing, background segmentation, etc. can also be performed through existing means, which will not be repeated here.
[0059] Next, the end point introduces the process of training the support vector machine through the Black Kite algorithm.
[0060] In some embodiments, a set of penalty coefficients C and a kernel function σ of the support vector machine are 2 Assume that it is a black-winged kite individual, and the output of the support vector machine is the position of the black-winged kite individual. The specific process of training the support vector machine based on the black-winged kite algorithm is as follows:
[0061] A1. Initialize the algorithm parameters of the black kite algorithm, wherein the algorithm parameters include the number of black kite populations, the maximum number of iterations, and the optimization range; the optimization range here is the upper and lower bounds of the black kite individuals.
[0062] A2. Randomly initialize the black-winged kite population;
[0063] In some embodiments, the specific formula for randomly initializing the black-winged kite population is:
[0064] X i =BK lb +rand(BK ub -BK lb )
[0065] Among them, X i represents the position of the ith black-winged kite individual, that is, the penalty coefficient C and kernel function σ corresponding to the ith black-winged kite individual 2 The correct number of samples for the support vector machine. i is an integer between 1 and pop, pop is the number of black-winged kites in the black-winged kite population, BK lb and BK ub are the lower and upper bounds of the j-th dimension black-winged kite individual, and rand is a randomly selected value between [0,1].
[0066] In this embodiment, the objective function of the Black Kite algorithm is the number of correct samples output by the support vector machine under a certain number of training samples.
[0067] The training samples can come from a sample database, and the samples in the sample database come from pictures collected when employees join the company.
[0068] Assume that the training sample has 500 face images of different persons, and the sample database also has 500 face images. The 500 face images in the sample database and the 500 face images in the training sample are different face images of 500 different persons.
[0069] That is, there are 500 different persons, and each person has two different face pictures. Here, different face pictures refer to pictures that are not taken at the same time, that is to say, different face pictures can be registration photos taken at different times. The registration photos of the same person, as long as they are taken at different times, will definitely have different features.
[0070] The 500 training samples are input into the support vector machine respectively. The support vector machine compares the 500 training samples with the 500 face images in the sample database respectively, and then outputs the comparison results.
[0071] If 300 training samples are correct samples, that is, 300 training samples can correspond to the face images in the sample database, then the fitness value is 0.6, that is, 300 / 500.
[0072] A3, respectively input the training samples into the support vector machine corresponding to the black-winged kite population, and calculate the fitness value generated by the location of each black-winged kite individual;
[0073] In some embodiments, the fitness value is the ratio of correct samples output by the support vector machine to training samples.
[0074] The location of the black-winged kite individual is the training sample input to the black-winged kite individual (C,σ 2 ) is the correct sample generated by the support vector machine corresponding to it, then the fitness value is the training sample input to the black-winged kite individual (C,σ 2 ) The ratio of correct samples to training samples generated by the support vector machine corresponding to the correct sample number / training sample number
[0075] A4, reordering the black-winged kite individuals according to the fitness values;
[0076] A5. performing attacking and migrating behaviors on the reordered black-winged kite individuals, thereby updating the positions of the black-winged kite individuals;
[0077] The mathematical model of the attack behavior of the black-winged kite individual is:
[0078]
[0079]
[0080] in, represents the position of the i-th black-winged kite individual in the j-th dimension and the t+1-th iteration step; represents the position of the i-th black-winged kite individual in the j-th dimension and the t-th iteration step; r is a random number between 0 and 1, p is a constant of 0.9; T is the maximum number of iterations, and t is the number of iterations completed so far.
[0081] The mathematical model of the migration behavior of the black-winged kite individual is:
[0082]
[0083] m=2×sin(r+π / 2)
[0084] in, represents the position of the i-th black-winged kite individual in the j-th dimension and the t+1-th iteration step; represents the position of the i-th black-winged kite individual in the j-th dimension and the t-th iteration step; F represents the leading scorer of the j-th dimension black-winged kite individual in the t-th iteration so far, that is, the optimal black-winged kite individual with the largest fitness value, i represents the j-th dimension current position of any black-winged kite individual in the t-th iteration; F ri represents the fitness value of any black-winged kite individual at a random position in the jth dimension in the tth iteration; C(0,1) represents the Cauchy mutation, and r is a random number between 0 and 1.
[0085] The specific expression of Cauchy mutation is:
[0086]
[0087] Here, x represents a random variable.
[0088] A6. Determine whether the maximum number of iterations has been reached. If so, terminate the process and output the current black-winged kite population. The support vector machine corresponding to the black-winged kite individual with the largest fitness value in the black-winged kite population is the optimal support vector machine. Otherwise, return to A3.
[0089] The Black Kite algorithm's powerful global search capability and ability to avoid local optimal traps can make the training of support vector machines more accurate and rapid, while also improving the generalization ability and recognition accuracy of support vector machines.
[0090] Of course, the present invention is also provided with a power supply module, and the model of the power supply module can be AMS1117-3V3 or ME6211C33.
[0091] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A personnel information automatic recognition system based on support vector machine and black kite algorithm, characterized in that: include: An acquisition module, used to obtain an initial image of the person to be detected; A preprocessing module, used for preprocessing the initial image to obtain a facial image of the person to be detected; A comparison module, used for inputting the face image into a support vector machine trained based on the Black Kite algorithm for classification, so as to obtain the face information of the person to be detected; A mapping module, used to find the personnel information of the person to be detected according to the facial information; The authority judgment module is used to judge whether the personnel information of the person to be detected has access authority; The alarm module performs a corresponding alarm operation when the authority judgment module determines that the personnel information has no access authority.
2. The personnel information automatic recognition system based on support vector machine and black kite algorithm according to claim 1 is characterized in that: The specific process of preprocessing the initial image to obtain the face image of the person to be detected is as follows: The initial image is subjected to denoising processing, and the background segmentation processing is performed on the initial image after the denoising processing to obtain a face image.
3. The personnel information automatic recognition system based on support vector machine and black kite algorithm according to claim 1 is characterized in that: A set of penalty coefficients C and kernel function σ of the support vector machine 2 Assume that it is a black-winged kite individual, and the output of the support vector machine is the position of the black-winged kite individual. The specific process of training the support vector machine based on the black-winged kite algorithm is as follows: A1, initializing the algorithm parameters of the black-winged kite algorithm, wherein the algorithm parameters include the number of black-winged kite populations, the maximum number of iterations, and the optimization range; A2. Randomly initialize the black-winged kite population; A3, respectively input the training samples into the support vector machine corresponding to the black-winged kite population, and calculate the fitness value generated by the location of each black-winged kite individual; A4, reordering the black-winged kite individuals according to the fitness values; A5. performing attacking and migrating behaviors on the reordered black-winged kite individuals, thereby updating the positions of the black-winged kite individuals; A6. Determine whether the maximum number of iterations has been reached. If so, terminate the process and output the current black-winged kite population. The support vector machine corresponding to the black-winged kite individual with the largest fitness value in the black-winged kite population is the optimal support vector machine. Otherwise, return to A3.
4. The automatic personnel information recognition system based on support vector machine and black kite algorithm according to claim 3 is characterized in that: The fitness value is the ratio of correct samples output by the support vector machine to the training samples.
5. The personnel information automatic recognition system based on support vector machine and black kite algorithm according to claim 3 is characterized in that: The specific formula for randomly initializing the black-winged kite population is: X i =BK lb +rand(UK ub -BK lb ) Among them, X i Indicates the position of the i-th black-winged kite individual, i is an integer between 1 and pop, pop is the number of black-winged kites in the black-winged kite population, BK lb and BK ub are the lower and upper bounds of the j-th dimension black-winged kite individual, and rand is a randomly selected value between [0,1].
6. The automatic personnel information recognition system based on support vector machine and black kite algorithm according to claim 3 is characterized in that: The mathematical model of the attack behavior of the black-winged kite individual is: in, represents the position of the i-th black-winged kite individual in the j-th dimension and the t+1-th iteration step; represents the position of the i-th black-winged kite individual in the j-th dimension and the t-th iteration step; r is a random number between 0 and 1, p is a constant of 0.9; T is the maximum number of iterations, and t is the number of iterations completed so far.
7. The automatic personnel information recognition system based on support vector machine and black kite algorithm according to claim 3 is characterized in that: The mathematical model of the migration behavior of the black-winged kite individual is: m=2×sin(r+π / 2) in, represents the position of the i-th black-winged kite individual in the j-th dimension and the t+1-th iteration step; represents the position of the i-th black-winged kite individual in the j-th dimension and the t-th iteration step; F represents the leading scorer of the j-th dimension black-winged kite individual in the t-th iteration so far, that is, the optimal black-winged kite individual with the largest fitness value, i represents the j-th dimension current position of any black-winged kite individual in the t-th iteration; F ri represents the fitness value of any black kite individual at a random position in the jth dimension in the tth iteration; C(0,1) represents the Cauchy mutation.
8. The automatic personnel information recognition system based on support vector machine and black kite algorithm according to claim 1 is characterized in that: The specific expression of Cauchy mutation is: Here, x represents a random variable.
9. The automatic personnel information recognition system based on support vector machine and black kite algorithm according to claim 1 is characterized in that: It also includes a display module, which is used to display the judgment result of the authority judgment module, the mapping result of the mapping module and the comparison result of the comparison module.
10. The automatic personnel information recognition system based on support vector machine and black kite algorithm according to claim 1 is characterized in that: The acquisition module is a camera device that collects facial information of people entering the camera area. When the authority judgment module determines that the person information has no access authority, the alarm module issues an alarm message of non-access.