TR2015-155
On Reducing the Effect of Silhouette Quality on Individual Gait Recogniton: A Feature Fusion Approach
-
- , "On Reducing the Effect of Silhouette Quality on Individual Gait Recogniton: A Feature Fusion Approach", International Conference on the Biometrics Special Interest Group (BIOSIG), DOI: 10.1109/BIOSIG.2015.7314613, September 2015, pp. 1-5.BibTeX TR2015-155 PDF
- @inproceedings{Jia2015sep,
- author = {Jia, Ning and Sanchez, Victor and Li, Chang-Tsun and Mansour, Hassan},
- title = {On Reducing the Effect of Silhouette Quality on Individual Gait Recogniton: A Feature Fusion Approach},
- booktitle = {International Conference on the Biometrics Special Interest Group (BIOSIG)},
- year = 2015,
- pages = {1--5},
- month = sep,
- doi = {10.1109/BIOSIG.2015.7314613},
- url = {https://www.merl.com/publications/TR2015-155}
- }
- , "On Reducing the Effect of Silhouette Quality on Individual Gait Recogniton: A Feature Fusion Approach", International Conference on the Biometrics Special Interest Group (BIOSIG), DOI: 10.1109/BIOSIG.2015.7314613, September 2015, pp. 1-5.
-
MERL Contact:
-
Research Area:
Digital Video
Abstract:
The quality of the extracted gait silhouettes can hinder the performance and practicability of gait recognition algorithms. In this paper, we propose a framework that integrates a feature fusion approach to improve recognition rate under this situation. Specifically, we first generate a dataset containing gait silhouettes with various qualities based on the CASIA Dataset B. We then fuse gallery data with different qualities and project data into embedded subspaces. We perform classification based on the Euclidean distances between fused gallery features and probe features. Experimental results show that the proposed algorithm can provide important improvements on recognition rate.