Human identification from body shape

We investigate the utility of static anthropometric distances as a biometric for human identification. The 3D landmark data from the CAESAR database is used to form a simple biometric consisting of distances between fixed rigidly connected body locations. This biometric is overt, and invariant to view and body posture. We use this to quantify the asymmetry of human bodies, and to characterize the interpersonal and intrapersonal distance distributions. The former is computed directly and the latter by adding zero-mean gaussian noise to the landmark points. This simulation framework is applicable to arbitrary shape based biometrics. We use gross body proportions information to model a computer vision recognition system.

[1]  Hyeonjoon Moon,et al.  The FERET verification testing protocol for face recognition algorithms , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[2]  P. Jonathon Phillips,et al.  Face recognition vendor test 2002 , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[3]  Rama Chellappa,et al.  A hidden Markov model based framework for recognition of humans from gait sequences , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[4]  Aaron F. Bobick,et al.  A Multi-view Method for Gait Recognition Using Static Body Parameters , 2001, AVBPA.

[5]  Larry S. Davis,et al.  View-invariant Estimation of Height and Stride for Gait Recognition , 2002, Biometric Authentication.

[6]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Aaron F. Bobick,et al.  Gait recognition using static, activity-specific parameters , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.