CN113239761A - Face recognition method, face recognition device and storage medium - Google Patents
Face recognition method, face recognition device and storage medium Download PDFInfo
- Publication number
- CN113239761A CN113239761A CN202110472915.2A CN202110472915A CN113239761A CN 113239761 A CN113239761 A CN 113239761A CN 202110472915 A CN202110472915 A CN 202110472915A CN 113239761 A CN113239761 A CN 113239761A
- Authority
- CN
- China
- Prior art keywords
- optimized
- particle
- sub
- face
- channels
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 239000013598 vector Substances 0.000 claims abstract description 93
- 238000012549 training Methods 0.000 claims abstract description 90
- 238000012706 support-vector machine Methods 0.000 claims abstract description 89
- 238000012360 testing method Methods 0.000 claims abstract description 56
- 238000005457 optimization Methods 0.000 claims abstract description 40
- 239000002245 particle Substances 0.000 claims description 208
- 230000001815 facial effect Effects 0.000 claims description 18
- 210000000697 sensory organ Anatomy 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 7
- 230000009977 dual effect Effects 0.000 claims description 4
- 238000005498 polishing Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 53
- 238000001514 detection method Methods 0.000 description 9
- 230000011218 segmentation Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/245—Classification techniques relating to the decision surface
- G06F18/2453—Classification techniques relating to the decision surface non-linear, e.g. polynomial classifier
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Biomedical Technology (AREA)
- Nonlinear Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a face recognition method, which comprises the steps of obtaining a nonlinear support vector machine model, training the nonlinear support vector machine model according to a training set and a test set which are obtained in advance to obtain an optimized nonlinear support vector machine model and the number of sub-block channels, and the human face image area to be recognized is preprocessed according to the optimized number of the sub-block channels to obtain a human face feature vector, wherein the dimension of the face feature vector is equal to the product of the number of the sub-block channels after optimization and the number of the preset sub-blocks, and finally the face feature vector is input into the nonlinear support vector machine model after optimization to obtain a face recognition result, the influence of uneven polishing of the face and random and variable interference of the background environment where the face is located on face recognition can be considered, and the accuracy of the face recognition and the face recognition efficiency are improved. The invention also correspondingly provides a face recognition device and a storage medium.
Description
Technical Field
The present invention relates to the field of face recognition technologies, and in particular, to a face detection method, a face detection device, and a computer-readable storage medium.
Background
The face recognition is a technology for identity recognition based on face feature information of a person, and the face feature is extracted and compared with feature information stored in a database to obtain a comparison result, so that identity recognition is performed. At present, due to the reasons of age change of people, makeup posture change and the like, the accuracy of face recognition is not accurate. Particularly, it is difficult to perform face recognition and extraction in places with high degree of people clustering and variable environments, the face of the target person cannot be clearly separated by the existing face recognition method, and both the detection efficiency and the accuracy are low.
Disclosure of Invention
The embodiment of the invention provides a face detection method, a face detection device and a computer readable storage medium, which can effectively improve the face recognition efficiency and accuracy.
A first aspect of an embodiment of the present invention provides a face recognition method, including:
acquiring a nonlinear support vector machine model, and training the nonlinear support vector machine model according to a training set and a test set which are acquired in advance to obtain an optimized nonlinear support vector machine model and the number of sub-block channels; the training set and the test set comprise a plurality of face feature vector samples with different sub-block channels;
acquiring a face image to be recognized;
preprocessing the face image area to be recognized according to the number of the optimized sub-block channels to obtain a face feature vector, wherein the dimension of the face feature vector is equal to the product of the number of the optimized sub-block channels and the number of preset sub-blocks;
and inputting the human face feature vector into the optimized nonlinear support vector machine model to obtain a human face recognition result.
Preferably, the nonlinear support vector machine model is specifically:
s.t.yi(wTxi+b)≥1-ξi,ξi≥0,i=1,2,…,n,
converting the optimization problem of the nonlinear support vector machine model into a dual problem as follows:
wherein x isiIs the ith sample of the given size n samples, w is the weight vector, yiIs xiThe label of (1) or-1, xiiIs a non-negative relaxation variable, C is an adjustable penalty parameter, n is the number of samples, L (alpha) represents a Lagrangian function, alphaiRepresenting lagrange multiplier, alphajLagrange multiplier, x, representing dualjIs the j sample, y, paired with the i sample of a given size n samplejIs xjThe label of (1).
Preferably, the preprocessing the face image region to be recognized according to the optimized number of sub-block channels to obtain a face feature vector specifically includes:
after the inclination correction is carried out on the face image area to be recognized, the binarization processing is carried out on the face area by adopting a self-adaptive threshold method;
dividing the face image to be recognized after binarization processing into n according to the number of preset sub-blocks and the positions occupied by the facial image five sense organ regions0A sub-block of n0The number of the subblocks is preset;
dividing each subblock into m channels according to the number of the optimized subblock channels to obtain N channels, wherein m is equal to the number of the optimized subblock channels, and N is equal to the total number of the channels;
and calculating the direction gradient value of each channel, and obtaining a face feature vector according to the direction gradient value of each channel.
Preferably, the obtaining a nonlinear support vector machine model, and training the nonlinear support vector machine model according to a training set and a test set obtained in advance to obtain an optimized nonlinear support vector machine model and an optimized number of subblock channels specifically includes:
according to a training set and a test set which are obtained in advance, the number of subblock channels in the face feature vector establishing process is calculated by adopting a particle population algorithm, and the punishment parameters and the kernel function parameters in the nonlinear support vector machine model establishing process are optimally trained to obtain the optimized punishment parameters, the optimized kernel function parameters and the optimized number of subblock channels;
and obtaining an optimized nonlinear support vector machine model according to the optimized punishment parameters and the optimized kernel function parameters.
Preferably, the method includes, according to a training set and a test set obtained in advance, performing optimization training on the number of subblock channels in the face feature vector establishing process by using a particle population algorithm, and performing optimization training on a penalty parameter and a kernel function parameter in the nonlinear support vector machine model establishing process to obtain an optimized penalty parameter, an optimized kernel function parameter and an optimized number of subblock channels, and specifically includes:
particle determination: combining the channel number of the subblocks in the establishing process of the face feature vector, and the penalty parameter and the kernel function parameter in the establishing process of the nonlinear support vector machine model into particles;
a particle population obtaining step: randomly generating different combinations of the sub-block channel number, the penalty parameter and the kernel function parameter to obtain a particle population, wherein each particle is represented as: xi=(mi,Ci,δi),XiDenotes the ith particle, miIndicates the number of sub-block channels corresponding to the ith particle, CiRepresents a penalty parameter, δ, corresponding to the ith particleiRepresenting the kernel function parameter corresponding to the ith particle;
and (3) calculating the particle fitness: obtaining a plurality of sets of training sets SiAnd multiple test sets TiWherein, training set SiThe dimension of the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle, and a test set TiThe dimension in the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle;
using training set SiPenalty parameter C corresponding to ith particleiKernel function parameter delta corresponding to ith particleiTraining the nonlinear support vector machine model to obtain a facial feature recognition model Mi;
Identifying the five sense organs by a model MiActing on test set TiObtaining the identification accuracy of the ith particle, and taking the identification accuracy of the ith particle as the fitness of the ith particle;
global optimal particle determination: taking the particles with the highest fitness among all the particles as global optimal particles;
particle updating step: for each particle, updating the position and the speed of each particle according to the fitness of each particle to obtain a new particle;
and an optimization parameter obtaining step: judging whether preset conditions are met or not, if so, acquiring the global optimal particles to obtain optimized punishment parameters, optimized kernel function parameters and optimized sub-block channel numbers; otherwise, returning to the step of calculating the particle fitness.
A second aspect of an embodiment of the present invention provides a face recognition apparatus, including:
the optimization parameter model obtaining module is used for obtaining a nonlinear support vector machine model and training the nonlinear support vector machine model according to a pre-obtained training set and a pre-obtained test set to obtain an optimized nonlinear support vector machine model and an optimized number of subblock channels; the training set and the test set comprise a plurality of face feature vector samples with different sub-block channels;
the face image acquisition module is used for acquiring a face image to be recognized;
an optimized face feature vector obtaining module, configured to pre-process the face image region to be recognized according to the number of sub-block channels after optimization to obtain a face feature vector, where a dimension of the face feature vector is equal to a product of the number of sub-block channels after optimization and a preset number of sub-blocks;
and the face recognition result acquisition module is used for inputting the face feature vector into the optimized nonlinear support vector machine model to obtain a face recognition result.
Preferably, the optimized face feature vector obtaining module is specifically configured to:
after the inclination correction is carried out on the face image area to be recognized, the binarization processing is carried out on the face area by adopting a self-adaptive threshold method;
dividing the face image to be recognized after binarization processing into n according to the number of preset sub-blocks and the positions occupied by the facial image five sense organ regions0A sub-block of n0The number of the subblocks is preset;
dividing each subblock into m channels according to the number of the optimized subblock channels to obtain N channels, wherein m is equal to the number of the optimized subblock channels, and N is equal to the total number of the channels;
and calculating the direction gradient value of each channel, and obtaining a face feature vector according to the direction gradient value of each channel.
Preferably, the parameter optimization and model obtaining module includes:
the optimization parameter acquisition unit is used for performing optimization training on the punishment parameters and the kernel function parameters in the establishment process of the nonlinear support vector machine model by adopting a particle population algorithm according to a pre-acquired training set and a pre-acquired test set to obtain the optimized punishment parameters, the optimized kernel function parameters and the optimized sub-block channel number;
and the optimization model obtaining unit is used for obtaining an optimized nonlinear support vector machine model according to the optimized punishment parameter and the optimized kernel function parameter.
Preferably, the optimization parameter obtaining unit is specifically configured to perform:
particle determination: combining the channel number of the subblocks in the establishing process of the face feature vector, and the penalty parameter and the kernel function parameter in the establishing process of the nonlinear support vector machine model into particles;
a particle population obtaining step: randomly generating different combinations of the sub-block channel number, the penalty parameter and the kernel function parameter to obtain a particle population, wherein each particle is represented as: xi=(mi,Ci,δi),XiDenotes the ith particle, miIndicates the number of sub-block channels corresponding to the ith particle, CiRepresents a penalty parameter, δ, corresponding to the ith particleiRepresenting the kernel function parameter corresponding to the ith particle;
and (3) calculating the particle fitness: obtaining a plurality of sets of training sets SiAnd multiple test sets TiWherein, training set SiThe dimension of the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle, and a test set TiThe dimension in the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle;
using training set SiPenalty parameter C corresponding to ith particleiKernel function parameter delta corresponding to ith particleiTraining the nonlinear support vector machine model to obtain a facial feature recognition model Mi;
Identifying the five sense organs by a model MiActing on test set TiObtaining the identification accuracy of the ith particle, and taking the identification accuracy of the ith particle as the fitness of the ith particle;
global optimal particle determination: taking the particles with the highest fitness among all the particles as global optimal particles;
particle updating step: for each particle, updating the position and the speed of each particle according to the fitness of each particle to obtain a new particle, and taking the new particle as the particle in the particle population;
and an optimization parameter obtaining step: judging whether preset conditions are met or not, if so, acquiring the global optimal particles to obtain optimized punishment parameters, optimized kernel function parameters and optimized sub-block channel numbers; otherwise, returning to the step of calculating the particle fitness.
A third aspect of the embodiments of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the face recognition method according to the above embodiments.
Compared with the prior art, the face recognition method provided by the embodiment of the invention comprises the steps of obtaining a nonlinear support vector machine model, training the nonlinear support vector machine model according to a pre-obtained training set and a pre-obtained testing set to obtain an optimized nonlinear support vector machine model and an optimized number of subblock channels, preprocessing a face image area to be recognized according to the optimized number of subblock channels to obtain a face feature vector, wherein the dimension of the face feature vector is equal to the product of the optimized number of subblock channels and the preset number of subblocks, and finally inputting the face feature vector into the optimized nonlinear support vector machine model to obtain a face recognition result, wherein the face recognition result can take the influences of uneven face polishing and random and variable interference of a background environment where a face is located on face recognition into consideration, the accuracy of face recognition and the recognition efficiency of the face are improved. In addition, the embodiment of the invention also correspondingly provides a face recognition device and a computer readable storage medium.
Drawings
Fig. 1 is a flowchart of a face detection method according to an embodiment of the present invention;
fig. 2 is a block diagram of a face detection apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, it is a flowchart of a face detection method provided in the embodiment of the present invention.
The face detection method provided by the embodiment of the invention comprises the following steps from S11 to S14:
step S11, acquiring a nonlinear support vector machine model, and training the nonlinear support vector machine model according to a training set and a test set which are acquired in advance to obtain an optimized nonlinear support vector machine model and an optimized number of subblock channels; the training set and the test set comprise a plurality of face feature vector samples with different sub-block channels.
Specifically, a Support Vector Machine (SVM) is a generalized linear classifier (generalized linear classifier) that performs binary classification on data in a supervised learning manner, and solves a problem by maximizing a classification interval of a hyperplane and converting an optimal classification surface problem into a dual problem by a lagrange function. For the linear inseparable problem, original samples in a low-dimensional space are converted into linear separable samples in a high-dimensional feature space through kernel function mapping, and therefore correct identification of the linear inseparable samples is achieved. In the embodiment of the invention, through introducing the non-negative relaxation variable xiiAnd a penalty coefficient C, a support vector machine model for solving the nonlinear divisibility can be obtained:
converting the optimization problem of the nonlinear support vector machine model into a dual problem as follows:
wherein x isiIs the ith sample of the given size n samples, w is the weight vector, yiIs xiThe label of (1) or-1, xiiIs a non-negative relaxation variable, C is an adjustable penalty parameter, n is the number of samples, L (alpha) represents a Lagrangian function, alphaiRepresenting lagrange multiplier, alphajLagrange multiplier, x, representing dualjIs the j sample, y, paired with the i sample of a given size n samplejIs xjThe label of (1).
In the embodiment of the present invention, the training set and the test set are face feature vectors, and for example, the face feature vectors may be implemented by first obtaining a face image to be trained, performing tilt correction on a face region of the face image to be trained, performing binarization segmentation to obtain a binarized face image, and dividing the binarized face image into n regions according to positions occupied by facial features0An individual block; for each sub-block j, it is equally divided into m channels (i.e., m symmetric regions) with its center as the origin of coordinates, and then the directional gradient value of channel k is calculated. Thus, the channel k in the sub-block j of the facial image five sense organ region corresponds to a gradient value alphajk,1≤j≤n0K is more than or equal to 1 and less than or equal to m, and then the face feature vector of the face image to be trained is obtainedAnd the face feature vector is taken as a sample. It will be appreciated that the dimension of the face feature vector is equal to n0M. In order to facilitate the subsequent training of the number of subblock channels (i.e. the number of channels contained in each subblock), a large number of face feature vectors with different numbers of subblock channels need to be obtained to obtain a large number of face feature vector samples, so as to obtain the training set. It will be appreciated that the test set also employs the trainingThe set is obtained, except that each sample in the training set carries a known label, and the label of each sample in the testing set is unknown.
In a possible case, in the above-mentioned five sense organ region segmentation process of the face image after binarization, m' channels can be obtained by directly performing peer-to-peer segmentation based on the five sense organ region of the face image after binarization, that is, in this case, n0=1。
In another possible case, in the above-mentioned five sense organ region segmentation process for the binarized face image, the five sense organ region of the binarized face image may be firstly divided into n0Individual block (n)0>1) At this time, each sub-block is further divided into m '' channels. It can be understood that, in this way, the amount of calculation in the subsequent training process can be effectively reduced, and therefore, this way is preferably adopted in the embodiment of the present invention.
In the embodiment of the invention, the influence of the illumination intensity on facial image five sense organs segmentation is considered, so that the processed facial image is closer to the original effect. In the embodiment of the present invention, in the process of preprocessing the face image, the following adaptive threshold scheme may be adopted to perform binarization processing on the face image:
wherein t represents the total number of pixels with gray scale value larger than 125 in the face image, and s represents the total number of pixels in the face image area.
Step S12, a face image to be recognized is acquired.
Step S13, preprocessing the face image area to be recognized according to the optimized number of sub-block channels to obtain a face feature vector, wherein the dimension of the face feature vector is equal to the product of the optimized number of sub-block channels and the preset number of sub-blocks.
And step S14, inputting the human face feature vector into the optimized nonlinear support vector machine model to obtain a human face recognition result.
In specific implementation, a plurality of face images M can be input at one timekAnd k is 1,2 and …, preprocessing each face image according to the number of the sub-block channels to be optimized to obtain a corresponding face feature vector, and inputting the corresponding face feature vector into the optimized nonlinear support vector machine model to obtain a corresponding face recognition result.
The face recognition method provided by the embodiment of the invention comprises the steps of obtaining a nonlinear support vector machine model, training the nonlinear support vector machine model according to a training set and a test set which are obtained in advance to obtain an optimized nonlinear support vector machine model and the number of sub-block channels, and the human face image area to be recognized is preprocessed according to the optimized number of the sub-block channels to obtain a human face feature vector, wherein the dimension of the face feature vector is equal to the product of the number of the sub-block channels after optimization and the number of the preset sub-blocks, and finally the face feature vector is input into the nonlinear support vector machine model after optimization to obtain a face recognition result, the influence of uneven polishing of the face and random and variable interference of the background environment where the face is located on face recognition can be considered, and the accuracy of the face recognition and the face recognition efficiency are improved.
In an optional implementation manner, the step S1 "acquiring a nonlinear support vector machine model, and training the nonlinear support vector machine model according to a training set and a test set acquired in advance to obtain an optimized nonlinear support vector machine model and an optimized number of subblock channels" specifically includes:
according to a training set and a test set which are obtained in advance, the number of subblock channels in the face feature vector establishing process is calculated by adopting a particle population algorithm, and the punishment parameters and the kernel function parameters in the nonlinear support vector machine model establishing process are optimally trained to obtain the optimized punishment parameters, the optimized kernel function parameters and the optimized number of subblock channels;
and obtaining an optimized nonlinear support vector machine model according to the optimized punishment parameters and the optimized kernel function parameters.
In the embodiment of the invention, the human face is identified by adopting the human face characteristic vector and the nonlinear support vector machine, so that the number of sub-block channels in the establishing process of the human face characteristic vector and the punishment parameters and kernel function parameters in the establishing process of the nonlinear support vector machine all influence the accuracy of human face identification. Further, the number of subblock channels, the penalty parameter and the kernel function parameter need to be optimized to obtain an optimized penalty parameter, an optimized kernel function parameter and an optimized number of subblock channels.
Further, the method includes, according to a training set and a test set obtained in advance, performing optimization training on the number of subblock channels in the face feature vector establishing process by using a particle population algorithm, and performing optimization training on a penalty parameter and a kernel function parameter in the nonlinear support vector machine model establishing process to obtain an optimized penalty parameter, an optimized kernel function parameter and an optimized number of subblock channels, and specifically includes:
particle determination: combining the channel number of the subblocks in the establishing process of the face feature vector, and the penalty parameter and the kernel function parameter in the establishing process of the nonlinear support vector machine model into particles;
a particle population obtaining step: randomly generating different combinations of the sub-block channel number, the penalty parameter and the kernel function parameter to obtain a particle population, wherein each particle is represented as: xi=(mi,Ci,δi),XIDenotes the ith particle, miIndicates the number of sub-block channels corresponding to the ith particle, CiRepresents a penalty parameter, δ, corresponding to the ith particleiRepresenting the kernel function parameter corresponding to the ith particle;
and (3) calculating the particle fitness: obtaining a plurality of sets of training sets SIAnd multiple test sets TiWherein, training set SIThe dimension of the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle, and a test set TiThe dimension in the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle;
using training set SiPenalty parameter C corresponding to ith particleiKernel function parameter delta corresponding to ith particleiTraining the nonlinear support vector machine model to obtain a facial feature recognition model Mi;
Identifying the five sense organs by a model MiActing on test set TiObtaining the identification accuracy of the ith particle, and taking the identification accuracy of the ith particle as the fitness of the ith particle;
global optimal particle determination: taking the particles with the highest fitness among all the particles as global optimal particles;
particle updating step: for each particle XiAccording to each particle XiUpdating the position and speed of each particle to obtain a new particle Xi', and mixing the particles XiRenewed to a new particle Xi';
And an optimization parameter obtaining step: judging whether preset conditions are met, if so, taking the global optimal particles as optimal particles to obtain optimized punishment parameters, optimized kernel function parameters and optimized subblock channel numbers; otherwise, returning to the step of calculating the particle fitness.
In specific implementation, the value ranges of three parameters to be optimized, namely the value ranges of each of the subblock channel number m, the penalty parameter C and the kernel function parameter δ, can be preset, and after the value ranges of the subblock channel number m, the penalty parameter C and the kernel function parameter δ are randomly selected, random combination is performed to obtain an initial particle population. Then, training the non-support vector machine model by obtaining a training set and a test set which are generated through preselection, specifically, the training set and the test set comprise a plurality of face feature vector samples with different subblock channel numbers, in order to better test the recognition accuracy effect of inputting different subblock channel numbers into different models, the embodiment of the invention divides the training set into a plurality of groups of training sets, the dimension of the face feature vector sample of each group of training sets is set according to the subblock channel number corresponding to the ith particle, and the dimension of the face feature vector sample in the same group of training setsNumber equal to mi*n0And using the training set SiPenalty parameter C corresponding to ith particleiKernel function parameter delta corresponding to ith particleiTraining the nonlinear support vector machine model to obtain a facial feature recognition model MiFurther enables the officer to recognize the model MiActing on test set TiTo obtain particles XiThe accuracy of face recognition is obtained, so that the number of channels in the subblock is miInputting the face feature vector into penalty parameter CiKernel function parameter of deltaiThe accuracy of face recognition in the nonlinear support vector machine model is continuously optimized through an algorithm to find the optimal particles (m)*,C*,δ*) So as to obtain the optimized number of sub-block channels, the optimized punishment parameter and the optimized kernel function parameter, further obtain the optimized nonlinear support vector machine model, and further can be according to the training set SiAnd test set TiThe recognition accuracy is obtained by the following formula:
and r (m, C, delta) is the recognition accuracy of the optimized nonlinear support vector machine model obtained by utilizing a classifier obtained by social media optimization and a training set to act on the test set under the given m, C and delta.
Illustratively, the following are detailed steps of the particle population algorithm employed for embodiments of the present invention:
s1, setting the channel number of the subblocks, the penalty parameter and the value range of the kernel function parameter, wherein m belongs to [1, 36], C, and delta belongs to [ 10-3, 10 ];
step S2, obtaining a face image to be trained and a face image to be tested;
step S3, setting the number of iterations, making the current number of iterations T equal to 1, and randomly generating N particles: xi=(mi,Ci,δi),1≤i≤N;
Step S4, for each particle XiCalculating each particle XiFitness F (X)i):
Step S4.1, by taking integer number m of sub-block channelsiAccording to the number m of sub-block channelsiPreprocessing the face image to be trained and the face image to be tested to obtain the face feature vector of the face image to be trained and the face image feature vector to be trained, and further obtaining a training set SiAnd test set Ti;
Step S4.2, with Ci、δiAnd training set SiTraining the nonlinear support vector machine model to obtain a facial feature recognition model MiActing on test set TiAnd the recognition accuracy thus obtained as the particle XiFitness F (X)i);
Step S5, taking the particle with the highest fitness among the N particles as a global optimal particle gb;
in step S6, the position x 'of the ith particle is updated for each particle according to the following formula'ijAs new particles Xi:
x′ij←xij+v′ij,1≤j≤3,
v′ij←vij+c1r1j(pbij-xij)+c2r2j(gbij-xij)
Wherein, c1And c2To the learning rate, r1jAnd r2jIs a random number between 0 and 1; v'ijIndicates the velocity, v, of the updated i-th particleijDenotes the speed of the i-th particle before update, pbijRepresents the locally optimal solution, gb, of the ith particleijRepresenting the global optimal solution of the population of particles, i.e. the global optimal particle, xijIndicates the position, x 'of the ith particle before update'ijIndicating the updated position of the ith particle;
step S7, let the iteration count T be T +1, determine whether the iteration count is greater than or equal to the maximum iteration count, if so, obtain the global optimum particle (m)*,C*,δ*) Further obtaining the optimized number of subblock channels, the optimized punishment parameter and the optimized kernel function parameter; otherwise, return to step S4.
In another optional implementation manner, the step S13 "pre-process the to-be-recognized face image region according to the optimized number of sub-block channels to obtain a face feature vector, where a dimension of the face feature vector is equal to a product of the optimized number of sub-block channels and a preset number of sub-blocks", specifically includes:
after the identified face image area is subjected to tilt correction, carrying out binarization processing on the face area by adopting a self-adaptive threshold method;
dividing the face image to be recognized after binarization processing into n according to the number of preset sub-blocks and the positions occupied by the facial five sense organ regions0A sub-block of n0The number of the subblocks is preset;
dividing each subblock into m channels according to the number of the optimized subblock channels to obtain N channels, wherein m is equal to the number of the optimized subblock channels, and N is equal to the total number of the channels;
and calculating the direction gradient value of each channel, and obtaining a face feature vector according to the direction gradient value of each channel.
It can be understood that the above method for processing the face image region to be recognized is the same as the processing method of the training set, and will not be described in detail here.
Accordingly, referring to fig. 2, fig. 2 is a block diagram of a structure of a face recognition apparatus according to an embodiment of the present invention. The face recognition device provided by the embodiment of the invention comprises:
an optimization parameter model obtaining module 110, configured to obtain a nonlinear support vector machine model, and train the nonlinear support vector machine model according to a training set and a test set obtained in advance, so as to obtain an optimized nonlinear support vector machine model and an optimized number of subblock channels; the training set and the test set comprise a plurality of face feature vector samples with different sub-block channels;
a face image obtaining module 120, configured to obtain a face image to be recognized;
an optimized face feature vector obtaining module 130, configured to pre-process the face image region to be recognized according to the number of the optimized sub-block channels, so as to obtain a face feature vector, where a dimension of the face feature vector is equal to a product of the number of the optimized sub-block channels and a preset number of sub-blocks;
and a face recognition result obtaining module 140, configured to input the face feature vector into the optimized nonlinear support vector machine model to obtain a face recognition result.
In an optional implementation manner, the optimized face feature vector obtaining module 130 is specifically configured to:
after the inclination correction is carried out on the face image area to be recognized, the binarization processing is carried out on the face area by adopting a self-adaptive threshold method;
dividing the face image to be recognized after binarization processing into n pieces according to the positions occupied by the facial five sense organ regions according to the preset number of sub-blocks0Sub-blocks of which n0The number of the subblocks is preset;
dividing each subblock into m channels according to the number of the optimized subblock channels to obtain N channels, wherein m is equal to the number of the optimized subblock channels, and N is equal to the total number of the channels;
and calculating the direction gradient value of each channel, and obtaining a face feature vector according to the direction gradient value of each channel.
In another optional embodiment, the optimization parameter and model obtaining module 110 includes:
the optimization parameter acquisition unit is used for performing optimization training on the punishment parameters and the kernel function parameters in the establishment process of the nonlinear support vector machine model by adopting a particle population algorithm according to a pre-acquired training set and a pre-acquired test set to obtain the optimized punishment parameters, the optimized kernel function parameters and the optimized sub-block channel number;
and the optimization model obtaining unit is used for obtaining an optimized nonlinear support vector machine model according to the optimized punishment parameter and the optimized kernel function parameter.
In another optional embodiment, the optimization parameter obtaining unit includes:
particle determination: combining the channel number of the subblocks in the establishing process of the face feature vector, and the penalty parameter and the kernel function parameter in the establishing process of the nonlinear support vector machine model into particles;
a particle population obtaining step: randomly generating different combinations of the sub-block channel number, the penalty parameter and the kernel function parameter to obtain a particle population, wherein each particle is represented as: xi=(mi,Ci,δi),XiDenotes the ith particle, miIndicates the number of sub-block channels corresponding to the ith particle, CiRepresents a penalty parameter, δ, corresponding to the ith particleiRepresenting the kernel function parameter corresponding to the ith particle;
and (3) calculating the particle fitness: obtaining a plurality of sets of training sets SiAnd multiple test sets TiWherein, training set SiThe dimension of the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle, and a test set TiThe dimension in the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle;
using training set SiPenalty parameter C corresponding to ith particleiKernel function parameter delta corresponding to ith particleiTraining the nonlinear support vector machine model to obtain a facial feature recognition model Mi;
Identifying the five sense organs by a model MiActing on test set TiObtaining the identification accuracy of the ith particle, and taking the identification accuracy of the ith particle as the fitness of the ith particle;
global optimal particle determination: taking the particles with the highest fitness among all the particles as global optimal particles;
particle updating step: for each particle, updating the position and the speed of each particle according to the fitness of each particle to obtain a new particle;
and an optimization parameter obtaining step: judging whether preset conditions are met or not, if so, acquiring the global optimal particles to obtain optimized punishment parameters, optimized kernel function parameters and optimized sub-block channel numbers; otherwise, returning to the step of calculating the particle fitness.
It should be noted that, the face recognition apparatus is used for executing all the processes and steps of the face recognition method according to the embodiment of the present invention, and the working principles and functions of the two correspond to each other, which is not described herein again.
Furthermore, the above-described device embodiments are merely illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort. In addition, the network function chain deployment apparatus provided in the foregoing embodiment and the network function chain deployment method provided in the embodiment of the present invention belong to the same concept, and the specific implementation process and the specific technical solution thereof are described in the foregoing method embodiment and are not described herein again.
Accordingly, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where, when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to perform steps S11 to S14 of the above-mentioned face recognition method.
The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A face recognition method, comprising:
acquiring a nonlinear support vector machine model, and training the nonlinear support vector machine model according to a training set and a test set which are acquired in advance to obtain an optimized nonlinear support vector machine model and the number of sub-block channels; the training set and the test set comprise a plurality of face feature vector samples with different sub-block channels;
acquiring a face image to be recognized;
preprocessing the face image area to be recognized according to the number of the optimized sub-block channels to obtain a face feature vector, wherein the dimension of the face feature vector is equal to the product of the number of the optimized sub-block channels and the number of preset sub-blocks;
and inputting the human face feature vector into the optimized nonlinear support vector machine model to obtain a human face recognition result.
2. The face recognition method of claim 1, wherein the non-linear support vector machine model is specifically:
converting the optimization problem of the nonlinear support vector machine model into a dual problem as follows:
wherein x isiIs the ith sample of the given size n samples, w is the weight vector, yiIs xiThe label of (1) or-1, xiiIs a non-negative relaxation variable, C is an adjustable penalty parameter, n is the number of samples, L (alpha) represents a Lagrangian function, alphaiRepresenting lagrange multiplier, alphajLagrange multiplier, x, representing dualjIs the j sample, y, paired with the i sample of a given size n samplejIs xjThe label of (1).
3. The method according to claim 1, wherein the preprocessing the face image region to be recognized according to the optimized number of sub-block channels to obtain a face feature vector comprises:
after the inclination correction is carried out on the face image area to be recognized, the binarization processing is carried out on the face area by adopting a self-adaptive threshold method;
dividing the face image to be recognized after binarization processing into n according to the number of preset sub-blocks and the positions occupied by the facial image five sense organ regions0A sub-block of n0The number of the subblocks is preset;
dividing each subblock into m channels according to the number of the optimized subblock channels to obtain N channels, wherein m is equal to the number of the optimized subblock channels, and N is equal to the total number of the channels;
and calculating the direction gradient value of each channel, and obtaining a face feature vector according to the direction gradient value of each channel.
4. The face recognition method according to claim 1, wherein the obtaining a nonlinear support vector machine model and training the nonlinear support vector machine model according to a training set and a test set obtained in advance to obtain an optimized nonlinear support vector machine model and an optimized number of sub-block channels specifically comprises:
according to a training set and a test set which are obtained in advance, the number of subblock channels in the face feature vector establishing process is calculated by adopting a particle population algorithm, and the punishment parameters and the kernel function parameters in the nonlinear support vector machine model establishing process are optimally trained to obtain the optimized punishment parameters, the optimized kernel function parameters and the optimized number of subblock channels;
and obtaining an optimized nonlinear support vector machine model according to the optimized punishment parameters and the optimized kernel function parameters.
5. The face recognition method according to claim 4, wherein the optimizing training is performed on the number of sub-block channels in the process of establishing the face feature vector by using a particle population algorithm according to a training set and a test set which are obtained in advance, and the penalty parameter and the kernel function parameter in the process of establishing the nonlinear support vector machine model are optimized to obtain the optimized penalty parameter, the optimized kernel function parameter and the optimized number of sub-block channels, and specifically includes:
particle determination: combining the channel number of the subblocks in the establishing process of the face feature vector, and the penalty parameter and the kernel function parameter in the establishing process of the nonlinear support vector machine model into particles;
a particle population obtaining step: randomly generating different combinations of the sub-block channel number, the penalty parameter and the kernel function parameter to obtain a particle population, wherein each particle is represented as: xi=(mi,Ci,δi),XiDenotes the ith particle, miIndicates the number of sub-block channels corresponding to the ith particle, CiRepresents a penalty parameter, δ, corresponding to the ith particleiRepresenting the kernel function parameter corresponding to the ith particle;
and (3) calculating the particle fitness: obtaining a plurality of sets of training sets SiAnd multiple test sets TiWherein, training set SiFace of manThe dimension of the characteristic vector sample is set according to the number of sub-block channels corresponding to the ith particle, and a test set TiThe dimension in the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle;
using training set SiPenalty parameter C corresponding to ith particleiKernel function parameter delta corresponding to ith particleiTraining the nonlinear support vector machine model to obtain a facial feature recognition model Mi;
Identifying the five sense organs by a model MiActing on test set TiObtaining the identification accuracy of the ith particle, and taking the identification accuracy of the ith particle as the fitness of the ith particle;
global optimal particle determination: taking the particles with the highest fitness among all the particles as global optimal particles;
particle updating step: for each particle, updating the position and the speed of each particle according to the fitness of each particle to obtain a new particle;
and an optimization parameter obtaining step: judging whether preset conditions are met, if so, acquiring the global optimal particles to obtain optimized punishment parameters, optimized kernel function parameters and optimized subblock channel numbers; otherwise, returning to the step of calculating the particle fitness.
6. A face recognition apparatus, comprising:
the optimization parameter model obtaining module is used for obtaining a nonlinear support vector machine model and training the nonlinear support vector machine model according to a pre-obtained training set and a pre-obtained test set to obtain an optimized nonlinear support vector machine model and an optimized number of subblock channels; the training set and the test set comprise a plurality of face feature vector samples with different sub-block channels;
the face image acquisition module is used for acquiring a face image to be recognized;
an optimized face feature vector obtaining module, configured to pre-process the face image region to be recognized according to the number of sub-block channels after optimization to obtain a face feature vector, where a dimension of the face feature vector is equal to a product of the number of sub-block channels after optimization and a preset number of sub-blocks;
and the face recognition result acquisition module is used for inputting the face feature vector into the optimized nonlinear support vector machine model to obtain a face recognition result.
7. The face recognition apparatus of claim 6, wherein the optimized face feature vector obtaining module is specifically configured to:
after the inclination correction is carried out on the face image area to be recognized, the binarization processing is carried out on the face area by adopting a self-adaptive threshold method;
dividing the face image to be recognized after binarization processing into n according to the number of preset sub-blocks and the positions occupied by the facial image five sense organ regions0A sub-block of n0The number of the subblocks is preset;
dividing each subblock into m channels according to the number of the optimized subblock channels to obtain N channels, wherein m is equal to the number of the optimized subblock channels, and N is equal to the total number of the channels;
and calculating the direction gradient value of each channel, and obtaining a face feature vector according to the direction gradient value of each channel.
8. The face recognition apparatus of claim 6, wherein the optimization parameter and model acquisition module comprises:
the optimization parameter acquisition unit is used for performing optimization training on the punishment parameters and the kernel function parameters in the establishment process of the nonlinear support vector machine model by adopting a particle population algorithm according to a pre-acquired training set and a pre-acquired test set to obtain the optimized punishment parameters, the optimized kernel function parameters and the optimized sub-block channel number;
and the optimization model obtaining unit is used for obtaining an optimized nonlinear support vector machine model according to the optimized punishment parameter and the optimized kernel function parameter.
9. The face recognition apparatus of claim 8, wherein the optimization parameter obtaining unit is specifically configured to perform:
particle determination: combining the channel number of the subblocks in the establishing process of the face feature vector, and the penalty parameter and the kernel function parameter in the establishing process of the nonlinear support vector machine model into particles;
a particle population obtaining step: randomly generating different combinations of the sub-block channel number, the penalty parameter and the kernel function parameter to obtain a particle population, wherein each particle is represented as: xi=(mi,Ci,δi),XiDenotes the ith particle, miIndicates the number of sub-block channels corresponding to the ith particle, CiRepresents a penalty parameter, δ, corresponding to the ith particleiRepresenting the kernel function parameter corresponding to the ith particle;
and (3) calculating the particle fitness: obtaining a plurality of sets of training sets SIAnd multiple test sets TiWherein, training set SIThe dimension of the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle, and a test set TiThe dimension in the face feature vector sample is set according to the number of sub-block channels corresponding to the ith particle;
using training set SiPenalty parameter C corresponding to ith particleiKernel function parameter delta corresponding to ith particleiTraining the nonlinear support vector machine model to obtain a facial feature recognition model Mi;
Identifying the five sense organs by a model MiActing on test set TiObtaining the identification accuracy of the ith particle, and taking the identification accuracy of the ith particle as the fitness of the ith particle;
global optimal particle determination: taking the particles with the highest fitness among all the particles as global optimal particles;
particle updating step: for each particle, updating the position and the speed of each particle according to the fitness of each particle to obtain a new particle;
and an optimization parameter obtaining step: judging whether preset conditions are met or not, if so, acquiring the global optimal particles to obtain optimized punishment parameters, optimized kernel function parameters and optimized sub-block channel numbers; otherwise, returning to the step of calculating the particle fitness.
10. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the face recognition method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110472915.2A CN113239761B (en) | 2021-04-29 | 2021-04-29 | Face recognition method, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110472915.2A CN113239761B (en) | 2021-04-29 | 2021-04-29 | Face recognition method, device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113239761A true CN113239761A (en) | 2021-08-10 |
CN113239761B CN113239761B (en) | 2023-11-14 |
Family
ID=77131354
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110472915.2A Active CN113239761B (en) | 2021-04-29 | 2021-04-29 | Face recognition method, device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113239761B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130163829A1 (en) * | 2011-12-21 | 2013-06-27 | Electronics And Telecommunications Research Institute | System for recognizing disguised face using gabor feature and svm classifier and method thereof |
CN104766063A (en) * | 2015-04-08 | 2015-07-08 | 宁波大学 | Living body human face identifying method |
CN107679528A (en) * | 2017-11-24 | 2018-02-09 | 广西师范大学 | A kind of pedestrian detection method based on AdaBoost SVM Ensemble Learning Algorithms |
WO2018072351A1 (en) * | 2016-10-20 | 2018-04-26 | 北京工业大学 | Method for optimizing support vector machine on basis of particle swarm optimization algorithm |
CN109033954A (en) * | 2018-06-15 | 2018-12-18 | 西安科技大学 | A kind of aerial hand-written discrimination system and method based on machine vision |
CN109359536A (en) * | 2018-09-14 | 2019-02-19 | 华南理工大学 | Passenger behavior monitoring method based on machine vision |
CN111723700A (en) * | 2020-06-08 | 2020-09-29 | 国网河北省电力有限公司信息通信分公司 | Face recognition method and device and electronic equipment |
CN111783704A (en) * | 2020-07-07 | 2020-10-16 | 中电万维信息技术有限责任公司 | Face recognition system based on particle swarm optimization radial basis |
-
2021
- 2021-04-29 CN CN202110472915.2A patent/CN113239761B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130163829A1 (en) * | 2011-12-21 | 2013-06-27 | Electronics And Telecommunications Research Institute | System for recognizing disguised face using gabor feature and svm classifier and method thereof |
CN104766063A (en) * | 2015-04-08 | 2015-07-08 | 宁波大学 | Living body human face identifying method |
WO2018072351A1 (en) * | 2016-10-20 | 2018-04-26 | 北京工业大学 | Method for optimizing support vector machine on basis of particle swarm optimization algorithm |
CN107679528A (en) * | 2017-11-24 | 2018-02-09 | 广西师范大学 | A kind of pedestrian detection method based on AdaBoost SVM Ensemble Learning Algorithms |
CN109033954A (en) * | 2018-06-15 | 2018-12-18 | 西安科技大学 | A kind of aerial hand-written discrimination system and method based on machine vision |
CN109359536A (en) * | 2018-09-14 | 2019-02-19 | 华南理工大学 | Passenger behavior monitoring method based on machine vision |
CN111723700A (en) * | 2020-06-08 | 2020-09-29 | 国网河北省电力有限公司信息通信分公司 | Face recognition method and device and electronic equipment |
CN111783704A (en) * | 2020-07-07 | 2020-10-16 | 中电万维信息技术有限责任公司 | Face recognition system based on particle swarm optimization radial basis |
Non-Patent Citations (2)
Title |
---|
廖周宇;王钰婷;谢晓兰;刘建明;: "基于粒子群优化的支持向量机人脸识别", 计算机工程, no. 12, pages 248 - 254 * |
谌璐;贺兴时;: "改进的支持向量机算法在人脸识别上的应用", 纺织高校基础科学学报, no. 01, pages 108 - 115 * |
Also Published As
Publication number | Publication date |
---|---|
CN113239761B (en) | 2023-11-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105069400B (en) | Facial image gender identifying system based on the sparse own coding of stack | |
CN105469034B (en) | Face identification method based on Weighting type distinctive sparse constraint Non-negative Matrix Factorization | |
CN104268593B (en) | The face identification method of many rarefaction representations under a kind of Small Sample Size | |
CN107169504B (en) | A kind of hand-written character recognition method based on extension Non-linear Kernel residual error network | |
US9031305B2 (en) | Image classification apparatus with first and second feature extraction units and recording medium having program recorded therein | |
CN107341463B (en) | Face feature recognition method combining image quality analysis and metric learning | |
Javed et al. | Multiplex cellular communities in multi-gigapixel colorectal cancer histology images for tissue phenotyping | |
CN109389074A (en) | A kind of expression recognition method extracted based on human face characteristic point | |
CN105335732B (en) | Based on piecemeal and differentiate that Non-negative Matrix Factorization blocks face identification method | |
CN113239839B (en) | Expression recognition method based on DCA face feature fusion | |
Mähönen et al. | Automated source classification using a Kohonen network | |
Wang et al. | A novel neural network approach to cDNA microarray image segmentation | |
CN111709313A (en) | Pedestrian re-identification method based on local and channel combination characteristics | |
CN103714340B (en) | Self-adaptation feature extracting method based on image partitioning | |
CN110119695A (en) | A kind of iris activity test method based on Fusion Features and machine learning | |
Chen et al. | Fast detection of human using differential evolution | |
Jena et al. | Texture analysis based feature extraction and classification of lung cancer | |
Han et al. | High-order statistics of microtexton for hep-2 staining pattern classification | |
CN110135327A (en) | A kind of driving behavior recognition methods based on multi-region feature learning model | |
CN109508692A (en) | A kind of gender identification method and system based on 3D fingerprint image | |
Kumar et al. | An amalgam method efficient for finding of cancer gene using CSC from micro array data | |
CN106529490B (en) | Based on the sparse system and method for realizing writer verification from coding code book | |
CN117649621A (en) | Fake video detection method, device and equipment | |
CN110378414B (en) | Multi-mode biological characteristic fusion identity recognition method based on evolution strategy | |
CN113239761B (en) | Face recognition method, device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |