Gait-Based Person Recognition Including the Effect of Covariates

The gait is the emerging biometric technology, which is used for person authentication based on walking style of a person. Covariates play a very important role in gait recognition, which degrades the recognition accuracy. Covariates include View point, Clothes, Footwear, Surface type, Carried weight, Walk velocity, Time, Emotional state. Among these, we consider the variation of viewpoint and large intraclass variations like carrying and wearing conditions. Gait Energy Image (GEI) features are extracted from the binary silhouette images and perform the View Transformation Model (VTM), in order to recognize the person. In this paper, the experiments conducted on CASIA gait database, shows that the proposed algorithm is robust to view point and intraclass variations like carrying and wearing conditions.

[1]  Yasushi Makihara,et al.  Gait Recognition Using a View Transformation Model in the Frequency Domain , 2006, ECCV.

[2]  Qiang Wu,et al.  Multiple views gait recognition using View Transformation Model based on optimized Gait Energy Image , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[3]  Tieniu Tan,et al.  Silhouette Analysis-Based Gait Recognition for Human Identification , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  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).

[5]  Yumei Wen,et al.  A New Gait Recognition Method Based on Body Contour , 2006, 2006 9th International Conference on Control, Automation, Robotics and Vision.

[6]  L Sloman,et al.  Gait patterns of depressed patients and normal subjects. , 1982, The American journal of psychiatry.

[7]  Hema Mamidipaka,et al.  GAIT BASED PERSON RECOGNITION USING PARTIAL LEAST SQUARES SELECTION SCHEME , 2016 .

[8]  D. Hatzinakos,et al.  Gait recognition: a challenging signal processing technology for biometric identification , 2005, IEEE Signal Processing Magazine.

[9]  Einar Snekkenes,et al.  Gait Authentication and Identification Using Wearable Accelerometer Sensor , 2007, 2007 IEEE Workshop on Automatic Identification Advanced Technologies.

[10]  Adrian Hilton,et al.  A survey of advances in vision-based human motion capture and analysis , 2006, Comput. Vis. Image Underst..

[11]  Sudeep Sarkar,et al.  The humanID gait challenge problem: data sets, performance, and analysis , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.