Computer Science ›› 2021, Vol. 48 ›› Issue (11A): 295-302.doi: 10.11896/jsjkx.201200159

• Image Processing & Multimedia Technology • Previous Articles     Next Articles

Low-quality Video Face Recognition Method Based on Super-resolution Reconstruction

LU Yao-yao1, YUAN Jia-bin1,2, HE Shan1, WANG Tian-xing1   

  1. 1 School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
    2 Information Department(Informationization Technology Center),Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
  • Online:2021-11-10 Published:2021-11-12
  • About author:LU Yao-yao,born in 1995,postgraduate.Her main research interests include deep learning and face recognition.
    YUAN Jia-bin,born in 1968,Ph.D,professor,is a senior member of China Computer Federation.His main research interests include deep learning,high performance computing and information security,etc.
  • Supported by:
    National Key Research and Development Program of China(2017YFB0802303) and National Natural Science Foundation of China(62076127,61571226).

Abstract: With the rise of deep neural networks,face recognition technology has developed rapidly.However,S2V (Still to Video)face recognition for low-quality video that is poor lighting conditions and low resolution still does not achieve the expected results,because the heterogeneous matching problem between the test video of low-quality and the high-definition image of the sample library.To solve this problem,this paper proposes a face recognition method for low-quality video based on super-resolution reconstruction.First,it uses clustering algorithm and random algorithm to select key frames for low-quality video frames based on face pose.Then,it builds a super-resolution reconstruction model S2V-SR for low-quality video S2V face recognition,and performs super-resolution reconstruction on key frames to obtain super-resolution key frames with higher resolution and more identity features.Finally,it uses the video face recognition network to extract deep features for classification and voting to obtain the final result.The proposed method is experimentally tested on the COX video face data set,and the best recognition accuracy is 55.91% and 70.85% in the relatively high-quality cam1 and cam3 videos,while in the relatively low-quality cam2 video the re-cognition accuracy rate second only to the best method is obtained.Experiments show that the proposed method can solve the hete-rogeneous matching problem in S2V face recognition to a certain extent,and obtain higher recognition accuracy and stability.

Key words: Depth feature, Face recognition(FR), Llow-quality video, Super-resolution reconstruction(SR)

CLC Number: 

  • TP183
[1]ZHANG K P,ZHANG Z P,CHENG C W,et al.Super-Identity Convolutional Neural Network for Face Hallucination[C]//European Conference on Computer Vision(ECCV).Springer,Cham,2018:196-211.
[2]WANG R,GUO H,DAVIS L S,et al.Covariance discriminative learning:A natural and efficient approach to image set classification[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2012:2496-2503.
[3]LU J,WANG G,MOULIN P.Image Set Classification UsingHolistic Multiple Order Statistics Features and Localized Multi-kernel Metric Learning[C]//2013 IEEE International Conference on Computer Vision(ICCV).IEEE 2013:329-336.
[4]WANG W,WANG R,HUANG Z,et al.Discriminant Analysis on Riemannian Manifold of Gaussian Distributions for Face Recognition with ImageSets[J].IEEE Transactions on Image Processing,2018,27(1):151-163.
[5]CHIEN J T,WU C C.Discriminant Waveletfaces and NearestFeature Classifiers for Face Recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2002(12):1644-1649.
[6]XIAO Q L.Research and application of face recognition methods in low-quality videos[D].Nanjing:Nanjing University,2019.
[7]SUN Y,WANG X,TANG X.Deep Learning Face Representation by Joint Identification-Verification[C]//Advances in Neural Information Processing Systems.2014:1988-1996.
[8]SCHROFF F,KALENICHENKO D,PHILBIN J.FaceNet:AUnified Embedding for Face Recognition and Clustering[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE 2015:815-823
[9]WEN Y,ZHANG K,LI Z,et al.A Discriminative FeatureLearning Approach for Deep Face Recognition[C]//European Conference on Computer Vision.Springer,Cham,2016:499-515.
[10]LIU W,WEN Y,YU Z,et al.SphereFace:Deep Hypersphere Embedding for Face Recognition[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2017:212-220.
[11]WANG F,XIANG X,CHENG J,et al.NormFace:L 2 Hypersphere Embedding for Face Verification[C]//ACM Conference on MultiMedia (MM) 2017.ACM,2017:1041-1049.
[12]DENG J,GUO J,ZAFEIRIOU S.ArcFace:Additive AngularMargin Loss for Deep Face Recognition[J].arXiv:1801.07698,2018.
[13]SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition[J].arXiv:1409.1556,2014.
[14]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]//2016 IEEE Conference on Computer Vision & Pattern Recognition(CVPR).IEEE,2016:770-778.
[15]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision & Pattern Recognition(CVPR).IEEE,2015.
[16]SZEGEDY C,IOFFE S,VANHOUCKE V.Inception-v4,inception-resnetandtheimpact of residual connections on learning[J].arXiv:1602.07261,2016.
[17]ZHANG K B,ZHENG D D,JING J F.Overview of low-resolution face recognition[J].Computer Engineering and Applications,2019,55(22):14-24.
[18]HERRMANN C,WILLERSINN D,JURGEN B.Low-resolution Convolutional Neural Networks for video face recognition[C]//IEEE International Conference on Advanced Video & Signal Based Surveillance(AVSS).IEEE,2016:221-227.
[19]ZANGENEH E,RAHMATI M,MOHSENZADEH Y.LowResolution Face Recognition Using a Two-Branch Deep Convolutional Neural Network Architecture[J].arXiv:1706.06247,2017.
[20]ELAZHARI A,AHMADI M.A neural network based humanface recognition of low resolution images[C]//2014 World Automation Congress (WAC).IEEE,2014:185-190.
[21]HUANG Z,SHAN S,WANG R,et al.A Benchmark and Comparative Study of Video-Based Face Recognition on COX Face Database[J].IEEE Transactions on Image Processing,2015,24(12):5967-5981.
[22]HUANG G,LIU Z,Maaten L V D,et al.Densely Connected Convolutional Networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2017.
[23]JOHNSON J,ALAHI A,FEI-FEI L.Perceptual Losses for Real-Time Style Transfer and Super-Resolution[C]//European Conference on Computer Vision(ECCV).Springer,Cham,2016:694-711.
[24]DONG Y,ZHEN L,LIAO S,et al.Learning face representation from scratch[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2014.
[25]CHAO D,CHEN C L,TANG X.Accelerating the Super-Resolution Convolutional Neural Network[C]//2016 IEEE Conference on Computer Vision & Pattern Recognition(CVPR).IEEE,2016.
[26]LAI W S,HUANG J B,AHUJA N,et al.Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution[C]//2017 IEEE Conference on Computer Vision & Pattern Recognition(CVPR).IEEE,2017.
[27]LIM B,SON S,KIM H,et al.Enhanced Deep Residual Networks for Single Image Super-Resolution[C]//2017 IEEE Conference on Computer Vision & Pattern Recognition(CVPR).IEEE,2017.
[28]LEDIG C,THEIS L,HUSZAR F,et al.Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network[C]//2016 IEEE Conference on Computer Vision & Pat-tern Recognition(CVPR).IEEE,2016.
[1] NIU Chen-xiao, SUN Jin and DING Yong-hui. Adaptive Hand Tracking Based on Fusing Depth and Skin Features [J]. Computer Science, 2016, 43(Z6): 125-129.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!