CN106599863A - Deep face identification method based on transfer learning technology - Google Patents

Deep face identification method based on transfer learning technology Download PDF

Info

Publication number
CN106599863A
CN106599863A CN201611189168.7A CN201611189168A CN106599863A CN 106599863 A CN106599863 A CN 106599863A CN 201611189168 A CN201611189168 A CN 201611189168A CN 106599863 A CN106599863 A CN 106599863A
Authority
CN
China
Prior art keywords
training
identification method
face
face identification
depth
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.)
Pending
Application number
CN201611189168.7A
Other languages
Chinese (zh)
Inventor
刘佳
余化鹏
张建林
徐智勇
魏宇星
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute of Optics and Electronics of CAS
Original Assignee
Institute of Optics and Electronics of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Institute of Optics and Electronics of CAS filed Critical Institute of Optics and Electronics of CAS
Priority to CN201611189168.7A priority Critical patent/CN106599863A/en
Publication of CN106599863A publication Critical patent/CN106599863A/en
Pending legal-status Critical Current

Links

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
    • G06V40/168—Feature extraction; Face representation
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Artificial Intelligence (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Human Computer Interaction (AREA)
  • Evolutionary Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a deep face identification method based on a transfer learning technology. The deep face identification method comprises the steps of: performing feature extraction on a trained face image by means of a deep convolutional neural network, subjecting the extracted features to SVM classification training to obtain a decision surface, performing feature extraction on a tested face image by means of the deep convolutional neural network, combining the decision surface obtained through classification training for prediction, and voting prediction results to obtain a final identification result. The deep face identification method requires only a small amount of training samples of each face class, can adapt to changes in the face such as illumination, attitude, expression, occlusion and the like in a large range in the practical application, and is high in identification rate; meanwhile, the deep human face identification method is high in training efficiency and can meet the requirements for incremental learning in the practical application.

Description

A kind of depth face identification method based on transfer learning technology
Technical field
The invention belongs to artificial intelligence and image processing field, are related to a kind of recognition methodss of facial image, particularly base In transfer learning technology, feature extraction is carried out using the depth convolutional neural networks of pre-training, be then trained and recognize.
Background technology
Transfer learning is mainly applied to the model for previously having succeeded in school in new task, and Cognitive Study shows that migration is learned Habit is a kind of basic cognitive style that people is adopted.
Train on big unrestricted scene human face data collection (such as LFW) the depth faceform for obtaining in performance People is exceeded.But in actual applications, often lack face sample to learn a so complicated depth model.The present invention By the depth faceform of a pre-training to solve the problems, such as application-specific in recognition of face.Will depth faceform work A little specific training set is moved to for a source model, to obtain final object module.
Depth faceform trains the end-to-end deep neural network for obtaining by one to solve to pass on large data sets The recognition of face problem of system.Such as Parkhi is obtained by (2,600,000 pictures, more than 2600 people) training on large data sets CNN networks, the discrimination clearly respectively reached in standard LFW and YTF data sets.
Another interesting depth baseline model is PCANET, employs two continuous PCA layers and constitutes depth model And achieve high-performance on many classical human face data collection.Although in complexity without on constraint face collection such as LFW, its performance is not Can be compared with CNN models, but on small-scale data set, PCANET is convenient to be trained.
" face identification method and system " (publication number CN103473535A) patent of prior art is carried out to original image Gray proces, obtain gray-scale maps, and each pixel grey scale in the original gradation figure is modified according to gray-level correction table And normalized, obtain final gray scale picture；According to preset ratio value, the final gray scale picture is carried out into Scaling ratio Example is processed, and obtains Scaling image data group；The final gray scale picture is entered according to the Scaling image data group The process of row recursive feature, obtains the area data that the match is successful, face picture area information is obtained, for recognition of face.The patent Described acquisition face picture area information approach needs to carry out original image gray scale and Scaling ratio is processed, and reduces figure As quality, parts of images details is have lost, necessarily cause face recognition accuracy rate to reduce.
The content of the invention
The technical problem to be solved in the present invention is：The present invention provides a kind of depth recognition of face based on transfer learning technology Method, the model that the method is constituted using convolutional neural networks, it is right to can be very good by the stronger learning capacity of deep learning Picture is classified.
The technical solution used in the present invention is：A kind of depth face identification method based on transfer learning technology, such as Fig. 1 institutes Show, the method comprising the steps of：
Step S1：Using the depth convolutional neural networks CNN of pre-training to training facial image to carry out feature extraction, obtain Eigenmatrix, for training grader；
Step S2：Svm classifier training is carried out to eigenmatrix, decision surface is obtained, for the prediction of face identity；
Step S3：Feature extraction is carried out to testing facial image using the depth convolutional neural networks CNN of pre-training, is obtained Eigenmatrix, for the prediction of face identity；
Step S4：The SVM classifier obtained using training, it is pre- that the facial image feature to obtaining in step S3 carries out identity Survey, predicted the outcome.
Wherein, in step S1 and step S3, the image size for being input to depth convolutional neural networks CNN is 224 × 224.
Wherein, in step S1 and step S3, CNN mono- has 40 layers, and an input layer (the 0th layer) a, softmax is exported Layer (the 39th layer), 3 full articulamentums (the 32nd, 35,38 layer), remaining is conv/relu/mpool/drop layers.
Wherein, the svm classifier in step S2 has used LIBSVM tool kits, selects L2- normalizations L2- loss radial direction base cores Penalty factor is simultaneously set to 10 by function SVM.
Present invention beneficial effect compared with prior art is：The present invention extracts face characteristic and carries out by transfer learning Classification and Identification, adaptable, discrimination is high.
(1) only need each face class that there is minimal amount of training sample；
(2) change, the identification such as the illumination in very large range of face in practical application, attitude are can adapt to, are expressed one's feelings, are blocked Rate is high；
(3) training effectiveness is high, can adapt to the demand of incremental learning in practical application, without carrying out repeating instruction every time Practice.
Description of the drawings
Fig. 1 is a kind of depth face identification method flowchart based on transfer learning technology of the present invention；
Fig. 2 is specific embodiment of the invention flowchart.
Specific embodiment
Embodiments of the invention are elaborated below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention as front Put and implemented, give detailed embodiment and specific operating process, but protection scope of the present invention be not limited to Under embodiment.
The present invention provides a kind of face identification method, is input into as the sized images of single frames colour 224 × 224.
As shown in Fig. 2 the invention provides a kind of depth face identification method based on transfer learning technology, comprising following Step：
Step S1：Lost using " triplet-based ", using the depth convolutional neural networks CNN of pre-training to original Training image carries out feature extraction, obtains eigenmatrix, for training classification；
Step S2：Select L2- standardization L2- loss Radial basis kernel function SVM to carry out classification based training to eigenmatrix, obtain Decision surface, for face prediction, gives one group of example-label to (xi,yi), i=1 ..., l, xi∈Rn,yi∈{-1,+1}l, L2- standardization L2- are lost the object function of SVM：
subject to yi(wTφ(xi)+b)≥1-ξi,
ξi≥0.
Wherein, (w, b) is decision surface, ξiIt is slack variable, C>0 is penalty factor, is typically determined by application problem, C values The punishment of misclassification is increased when big, punishment of the C values hour to misclassification reduces.Training vector xiIt is mapped to by function phi More higher dimensional space, K (xi, xj)≡φ(xi)Tφ(xj) it is kernel function.
Step S3：Feature extraction is carried out to original identification image using the depth convolutional neural networks CNN of pre-training, is obtained Eigenmatrix, for the prediction of face identity；
Step S4：The SVM classifier obtained using training, it is pre- that the facial image feature to obtaining in step S3 carries out identity Survey, predicted the outcome.
Jing is tested, and for varying environment, in the case of camera imaging is the second best in quality, face recognition accuracy rate is not less than 90%, can support that multiple faces are recognized simultaneously, recognition of face response time is less than 3 seconds.

Claims (4)

1. a kind of depth face identification method based on transfer learning technology, it is characterised in that comprise the steps：
Step S1：Using the depth convolutional neural networks CNN of pre-training to training facial image to carry out feature extraction, feature is obtained Matrix, for training grader；
Step S2：Svm classifier training is carried out to eigenmatrix, decision surface is obtained, for the prediction of face identity；
Step S3：Feature extraction is carried out to testing facial image using the depth convolutional neural networks CNN of pre-training, feature is obtained Matrix, for the prediction of face identity；
Step S4：The SVM classifier obtained using training, the facial image feature to obtaining in step S3 carries out identity prediction, Predicted the outcome.
2. the depth face identification method based on transfer learning technology according to claim 1, it is characterised in that step S1 In step S3, the image size for being input to depth convolutional neural networks CNN is 224 × 224.
3. the depth face identification method based on transfer learning technology according to claim 1, it is characterised in that step S1 In step S3, CNN mono- has 40 layers, an input layer, a softmax output layer, 3 full articulamentums, and remaining is Conv/relu/mpool/drop layers.
4. the depth face identification method based on transfer learning technology according to claim 1, it is characterised in that step S2 In svm classifier used LIBSVM tool kits, select L2- normalizations L2- to lose Radial basis kernel function SVM and by penalty factor It is set to 10.
CN201611189168.7A 2016-12-21 2016-12-21 Deep face identification method based on transfer learning technology Pending CN106599863A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611189168.7A CN106599863A (en) 2016-12-21 2016-12-21 Deep face identification method based on transfer learning technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611189168.7A CN106599863A (en) 2016-12-21 2016-12-21 Deep face identification method based on transfer learning technology

Publications (1)

Publication Number Publication Date
CN106599863A true CN106599863A (en) 2017-04-26

Family

ID=58600586

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611189168.7A Pending CN106599863A (en) 2016-12-21 2016-12-21 Deep face identification method based on transfer learning technology

Country Status (1)

Country Link
CN (1) CN106599863A (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107292298A (en) * 2017-08-09 2017-10-24 北方民族大学 Ox face recognition method based on convolutional neural networks and sorter model
CN107463937A (en) * 2017-06-20 2017-12-12 大连交通大学 A kind of tomato pest and disease damage automatic testing method based on transfer learning
CN107563431A (en) * 2017-08-28 2018-01-09 西南交通大学 A kind of image abnormity detection method of combination CNN transfer learnings and SVDD
CN107798349A (en) * 2017-11-03 2018-03-13 合肥工业大学 A kind of transfer learning method based on the sparse self-editing ink recorder of depth
CN107909011A (en) * 2017-10-30 2018-04-13 广东欧珀移动通信有限公司 Face identification method and Related product
CN107944410A (en) * 2017-12-01 2018-04-20 中国科学院重庆绿色智能技术研究院 A kind of cross-cutting facial characteristics analytic method based on convolutional neural networks
CN108304800A (en) * 2018-01-30 2018-07-20 厦门启尚科技有限公司 A kind of method of Face datection and face alignment
CN108446617A (en) * 2018-03-09 2018-08-24 华南理工大学 The human face quick detection method of anti-side face interference
CN108805160A (en) * 2018-04-17 2018-11-13 平安科技（深圳）有限公司 Transfer learning method, apparatus, computer equipment and storage medium
CN109086723A (en) * 2018-08-07 2018-12-25 广东工业大学 A kind of method, apparatus and equipment of the Face datection based on transfer learning
CN109166196A (en) * 2018-06-21 2019-01-08 广东工业大学 A kind of hotel's disengaging personnel management methods based on single sample recognition of face
CN110569780A (en) * 2019-09-03 2019-12-13 北京清帆科技有限公司 high-precision face recognition method based on deep transfer learning
CN111091492A (en) * 2019-12-23 2020-05-01 韶鼎人工智能科技有限公司 Face image illumination migration method based on convolutional neural network
CN107742140B (en) * 2017-11-08 2020-07-28 重庆西南集成电路设计有限责任公司 Intelligent identity information identification method based on RFID technology
CN111680944A (en) * 2020-05-08 2020-09-18 北京联合大学 Interactive method and system for distributing articles
CN111753877A (en) * 2020-05-19 2020-10-09 海克斯康制造智能技术(青岛)有限公司 Product quality detection method based on deep neural network transfer learning
CN111783670A (en) * 2020-07-02 2020-10-16 哈尔滨理工大学 Face recognition method based on neural network and face composition
US11443559B2 (en) 2019-08-29 2022-09-13 PXL Vision AG Facial liveness detection with a mobile device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104408435A (en) * 2014-12-05 2015-03-11 浙江大学 Face identification method based on random pooling convolutional neural network
CN105426963A (en) * 2015-12-01 2016-03-23 北京天诚盛业科技有限公司 Convolutional neural network Training method and apparatus for human face identification and application
CN105608450A (en) * 2016-03-01 2016-05-25 天津中科智能识别产业技术研究院有限公司 Heterogeneous face identification method based on deep convolutional neural network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104408435A (en) * 2014-12-05 2015-03-11 浙江大学 Face identification method based on random pooling convolutional neural network
CN105426963A (en) * 2015-12-01 2016-03-23 北京天诚盛业科技有限公司 Convolutional neural network Training method and apparatus for human face identification and application
CN105608450A (en) * 2016-03-01 2016-05-25 天津中科智能识别产业技术研究院有限公司 Heterogeneous face identification method based on deep convolutional neural network

Cited By (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107463937A (en) * 2017-06-20 2017-12-12 大连交通大学 A kind of tomato pest and disease damage automatic testing method based on transfer learning
CN107292298B (en) * 2017-08-09 2018-04-20 北方民族大学 Ox face recognition method based on convolutional neural networks and sorter model
CN107292298A (en) * 2017-08-09 2017-10-24 北方民族大学 Ox face recognition method based on convolutional neural networks and sorter model
CN107563431A (en) * 2017-08-28 2018-01-09 西南交通大学 A kind of image abnormity detection method of combination CNN transfer learnings and SVDD
CN107909011A (en) * 2017-10-30 2018-04-13 广东欧珀移动通信有限公司 Face identification method and Related product
CN107909011B (en) * 2017-10-30 2021-08-24 Oppo广东移动通信有限公司 Face recognition method and related product
CN107798349A (en) * 2017-11-03 2018-03-13 合肥工业大学 A kind of transfer learning method based on the sparse self-editing ink recorder of depth
CN107798349B (en) * 2017-11-03 2020-07-14 合肥工业大学 Transfer learning method based on depth sparse self-coding machine
CN107742140B (en) * 2017-11-08 2020-07-28 重庆西南集成电路设计有限责任公司 Intelligent identity information identification method based on RFID technology
CN107944410A (en) * 2017-12-01 2018-04-20 中国科学院重庆绿色智能技术研究院 A kind of cross-cutting facial characteristics analytic method based on convolutional neural networks
CN107944410B (en) * 2017-12-01 2020-07-28 中国科学院重庆绿色智能技术研究院 Cross-domain facial feature analysis method based on convolutional neural network
CN108304800A (en) * 2018-01-30 2018-07-20 厦门启尚科技有限公司 A kind of method of Face datection and face alignment
CN108446617A (en) * 2018-03-09 2018-08-24 华南理工大学 The human face quick detection method of anti-side face interference
CN108805160A (en) * 2018-04-17 2018-11-13 平安科技（深圳）有限公司 Transfer learning method, apparatus, computer equipment and storage medium
CN109166196A (en) * 2018-06-21 2019-01-08 广东工业大学 A kind of hotel's disengaging personnel management methods based on single sample recognition of face
CN109086723A (en) * 2018-08-07 2018-12-25 广东工业大学 A kind of method, apparatus and equipment of the Face datection based on transfer learning
CN109086723B (en) * 2018-08-07 2022-03-25 广东工业大学 Method, device and equipment for detecting human face based on transfer learning
US11669607B2 (en) 2019-08-29 2023-06-06 PXL Vision AG ID verification with a mobile device
US11443559B2 (en) 2019-08-29 2022-09-13 PXL Vision AG Facial liveness detection with a mobile device
CN110569780A (en) * 2019-09-03 2019-12-13 北京清帆科技有限公司 high-precision face recognition method based on deep transfer learning
CN111091492B (en) * 2019-12-23 2020-09-04 韶鼎人工智能科技有限公司 Face image illumination migration method based on convolutional neural network
CN111091492A (en) * 2019-12-23 2020-05-01 韶鼎人工智能科技有限公司 Face image illumination migration method based on convolutional neural network
CN111680944A (en) * 2020-05-08 2020-09-18 北京联合大学 Interactive method and system for distributing articles
CN111753877A (en) * 2020-05-19 2020-10-09 海克斯康制造智能技术(青岛)有限公司 Product quality detection method based on deep neural network transfer learning
CN111753877B (en) * 2020-05-19 2024-03-05 海克斯康制造智能技术(青岛)有限公司 Product quality detection method based on deep neural network migration learning
CN111783670A (en) * 2020-07-02 2020-10-16 哈尔滨理工大学 Face recognition method based on neural network and face composition

Similar Documents

Publication Publication Date Title
CN106599863A (en) Deep face identification method based on transfer learning technology
US9436895B1 (en) Method for determining similarity of objects represented in images
WO2022252272A1 (en) Transfer learning-based method for improved vgg16 network pig identity recognition
Alani et al. Hand gesture recognition using an adapted convolutional neural network with data augmentation
JP7386545B2 (en) Method for identifying objects in images and mobile device for implementing the method
CN110889672B (en) Student card punching and class taking state detection system based on deep learning
Lin Face detection in complicated backgrounds and different illumination conditions by using YCbCr color space and neural network
CN110399821B (en) Customer satisfaction acquisition method based on facial expression recognition
CN111582044B (en) Face recognition method based on convolutional neural network and attention model
CN106529494A (en) Human face recognition method based on multi-camera model
CN112036447A (en) Zero-sample target detection system and learnable semantic and fixed semantic fusion method
Virmani et al. FDREnet: Face Detection and Recognition Pipeline.
JP2018018313A (en) Image discrimination device and image discrimination method
CN111832573A (en) Image emotion classification method based on class activation mapping and visual saliency
CN110852199A (en) Foreground extraction method based on double-frame coding and decoding model
CN114492634B (en) Fine granularity equipment picture classification and identification method and system
CN110826534A (en) Face key point detection method and system based on local principal component analysis
CN113903063A (en) Facial expression recognition method and system based on deep spatiotemporal network decision fusion
Nimbarte et al. Biased face patching approach for age invariant face recognition using convolutional neural network
KR20180092453A (en) Face recognition method Using convolutional neural network and stereo image
Singla et al. Age and gender detection using Deep Learning
CN113837263A (en) Gesture image classification method based on feature fusion attention module and feature selection
Sreemathy et al. Indian Sign Language interpretation using convolutional neural networks
Ahuja et al. Convolutional Neural Network and Kernel Extreme Learning Machine for Face Recognition
Milyaev et al. Improving the processing of machine vision images of robotic systems in the Arctic

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170426