Maximum A Posteriori Estimation of Distances Between Deep Features in Still-to-Video Face Recognition

The paper deals with the still-to-video face recognition for the small sample size problem based on computation of distances between high-dimensional deep bottleneck features. We present the novel statistical recognition method, in which the still-to-video recognition task is casted into Maximum A Posteriori estimation. In this method we maximize the joint probabilistic density of the distances to all reference still images. It is shown that this likelihood can be estimated with the known asymptotically normal distribution of the Kullback-Leibler discriminations between nonnegative features. The experimental study with the LFW (Labeled Faces in the Wild), YTF (YouTube Faces) and IJB-A (IARPA Janus Benchmark A) datasets has been provided. We demonstrated, that the proposed approach can be applied with the state-of-the-art deep features and dissimilarity measures. Our algorithm achieves 3-5% higher accuracy when compared with conventional aggregation of decisions obtained for all frames. Abbreviations • CNN Convolution Neural Network • i.i.d. independent identically distributed • IJB-A IARPA Janus Benchmark A

[1]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Shiguang Shan,et al.  Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  A. V. Savchenko.  Adaptive video image recognition system using a committee machine , 2012, Optical Memory and Neural Networks.

[4]  Shiguang Shan,et al.  Still to video face recognition using a heterogeneous matching approach , 2015, 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[5]  Andrey V. Savchenko,et al.  Statistical Testing of Segment Homogeneity in Classification of Piecewise–Regular Objects , 2015, Int. J. Appl. Math. Comput. Sci..

[6]  Jian Sun,et al.  A Practical Transfer Learning Algorithm for Face Verification , 2013, 2013 IEEE International Conference on Computer Vision.

[7]  Jun-Cheng Chen,et al.  An End-to-End System for Unconstrained Face Verification with Deep Convolutional Neural Networks , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[8]  Likun Huang,et al.  Face recognition based on image sets , 2014 .

[9]  Anil K. Jain,et al.  Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Shiguang Shan,et al.  Benchmarking Still-to-Video Face Recognition via Partial and Local Linear Discriminant Analysis on COX-S2V Dataset , 2012, ACCV.

[11]  Tal Hassner,et al.  Face recognition in unconstrained videos with matched background similarity , 2011, CVPR 2011.

[12]  Ajmal S. Mian,et al.  Image Set Based Face Recognition Using Self-Regularized Non-Negative Coding and Adaptive Distance Metric Learning , 2013, IEEE Transactions on Image Processing.

[13]  Andrey V. Savchenko,et al.  Maximum Likelihood Directed Enumeration Method in Piecewise-Regular Object Recognition , 2014, Pattern Recognit..

[14]  Simon J. D. Prince,et al.  Computer Vision: Models, Learning, and Inference , 2012 .

[15]  Gang Hua,et al.  Labeled Faces in the Wild: A Survey , 2016 .

[16]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Tsuhan Chen,et al.  Video-based face recognition using adaptive hidden Markov models , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[18]  Trevor Darrell,et al.  Face Recognition from Long-Term Observations , 2002, ECCV.

[19]  Yongkang Wong,et al.  Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition , 2011, CVPR 2011 WORKSHOPS.

[20]  Rama Chellappa,et al.  Face recognition from video: a CONDENSATION approach , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[21]  Shiguang Shan,et al.  Coupling Alignments with Recognition for Still-to-Video Face Recognition , 2013, 2013 IEEE International Conference on Computer Vision.

[22]  S. Kullback,et al.  Information Theory and Statistics , 1959 .

[23]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[24]  Andrey V. Savchenko,et al.  Search Techniques in Intelligent Classification Systems , 2016 .

[25]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Shiguang Shan,et al.  Learning Euclidean-to-Riemannian Metric for Point-to-Set Classification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Gang Hua,et al.  Eigen-PEP for Video Face Recognition , 2014, ACCV.

[28]  Zhi-Hua Zhou,et al.  Face recognition from a single image per person: A survey , 2006, Pattern Recognit..

[29]  Arnold W. M. Smeulders,et al.  The Distribution Family of Similarity Distances , 2007, NIPS.

[30]  Andrey V. Savchenko.  Deep Convolutional Neural Networks and Maximum-Likelihood Principle in Approximate Nearest Neighbor Search , 2017, IbPRIA.

[31]  Mehrtash Tafazzoli Harandi,et al.  From Manifold to Manifold: Geometry-Aware Dimensionality Reduction for SPD Matrices , 2014, ECCV.

[32]  David Zhang,et al.  From Point to Set: Extend the Learning of Distance Metrics , 2013, 2013 IEEE International Conference on Computer Vision.

[33]  Lior Wolf,et al.  Kernel principal angles for classification machines with applications to image sequence interpretation , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[34]  Shuicheng Yan,et al.  Toward Large-Population Face Identification in Unconstrained Videos , 2014, IEEE Transactions on Circuits and Systems for Video Technology.