Detection and Recognition of Periodic, Nonrigid Motion
International Journal of Computer Vision
The Gait Identification Challenge Problem: Data Sets and Baseline Algorithm
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Automatic gait recognition by symmetry analysis
Pattern Recognition Letters - Special issue: Audio- and video-based biometric person authentication (AVBPA 2001)
Automatic gait recognition using area-based metrics
Pattern Recognition Letters
Simplest Representation Yet for Gait Recognition: Averaged Silhouette
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04
Gait recognition using image self-similarity
EURASIP Journal on Applied Signal Processing
General Tensor Discriminant Analysis and Gabor Features for Gait Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Dynamic Texture Based Gait Recognition
ICB '09 Proceedings of the Third International Conference on Advances in Biometrics
Gait feature subset selection by mutual information
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special section: Best papers from the 2007 biometrics: Theory, applications, and systems (BTAS 07) conference
Hi-index | 0.01 |
In the present scenario, Gait descriptors are required to extract the dynamic and static information of the gait. The static and dynamic descriptors are formed from the entire region of the body. We know that majority of dynamic information is in the lower silhouette whereas majority of static information is in the upper silhouette. In our work we have evaluated the significance of dynamic information extracted from the lower silhouette. State of the art feature descriptors are used along with a feature selection mask to form the final signature templates for classification. Our results indicate a significant dynamic content in the lower silhouette which itself is able to give decent recognition rate. Future work can improve performance by using dynamic information from lower silhouette in conjunction with static information derived from upper silhouette.