Fusion of Gait and Facial Features using Coupled Projections for People Identification at a Distance

A novel feature-level fusion scheme for people identification at a distance has been developed by coupling gait feature with facial feature. The proposed coupled projections based method first maps the heterogeneous features from gait and face into a unified subspace to minimize the distance between the two features extracted from the same individual. The fusion features are obtained by computing the mean of the two projecting features from the same person in the coupled subspace. Experimental results demonstrate that the proposed feature-level fusion scheme outperforms the match score-level and two other feature-level fusion schemes in the application of access control at a distance.

[1]  Yajie Tian,et al.  Handbook of face recognition , 2003 .

[2]  Sudeep Sarkar,et al.  Outdoor recognition at a distance by fusing gait and face , 2007, Image Vis. Comput..

[3]  Xiaoli Zhou,et al.  Feature fusion of side face and gait for video-based human identification , 2008, Pattern Recognit..

[4]  Donghai Guan,et al.  Class Energy Image Analysis for Video Sensor-Based Gait Recognition: A Review , 2015, Sensors.

[5]  Xiaoli Zhou,et al.  Feature Fusion of Face and Gait for Human Recognition at a Distance in Video , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[6]  Chang-Tsun Li,et al.  People Identification and Tracking Through Fusion of Facial and Gait Features , 2014, BIOMET.

[7]  Xiaofei He,et al.  Locality Preserving Projections , 2003, NIPS.

[8]  Bir Bhanu,et al.  Person Re-Identification by Robust Canonical Correlation Analysis , 2015, IEEE Signal Processing Letters.

[9]  Kate Smith-Miles,et al.  Adaptive Fusion of Gait and Face for Human Identification in Video , 2008, 2008 IEEE Workshop on Applications of Computer Vision.

[10]  Anil K. Jain,et al.  Handbook of Face Recognition, 2nd Edition , 2011 .

[11]  Jieping Ye,et al.  Canonical Correlation Analysis for Multilabel Classification: A Least-Squares Formulation, Extensions, and Analysis , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Xiaoli Zhou,et al.  Integrating Face and Gait for Human Recognition at a Distance in Video , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[13]  Xianglei Xing,et al.  Complete canonical correlation analysis with application to multi-view gait recognition , 2016, Pattern Recognit..

[14]  David Zhang,et al.  Human Gait Recognition via Sparse Discriminant Projection Learning , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[15]  John Shawe-Taylor,et al.  Canonical Correlation Analysis: An Overview with Application to Learning Methods , 2004, Neural Computation.

[16]  Gerhard Rigoll,et al.  Combined face and gait recognition using alpha matte preprocessing , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[17]  Chang-Tsun Li,et al.  Combining gait and face for tackling the elapsed time challenges , 2013, 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[18]  Haifeng Hu,et al.  Multiview Gait Recognition Based on Patch Distribution Features and Uncorrelated Multilinear Sparse Local Discriminant Canonical Correlation Analysis , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[19]  Tieniu Tan,et al.  A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[20]  Rama Chellappa,et al.  Fusion of gait and face for human identification , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[21]  Michael K. Ng,et al.  Sparse Canonical Correlation Analysis: New Formulation and Algorithm , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Bruno Emile,et al.  Access control based on gait analysis and face recognition , 2015 .