The FERET Evaluation Methodology for Face-Recognition Algorithms
IEEE Transactions on Pattern Analysis and Machine Intelligence
EigenGait: Motion-Based Recognition of People Using Image Self-Similarity
AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication
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 extraction and description of human gait models for recognition purposes
Computer Vision and Image Understanding
Silhouette-Based Human Identification from Body Shape and Gait
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Motion-Based Recognition of People in EigenGait Space
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Extracting Human Gait Signatures by Body Segment Properties
SSIAI '02 Proceedings of the Fifth IEEE Southwest Symposium on Image Analysis and Interpretation
Individual Identification Using Gait Sequences under Different Covariate Factors
ICVS '09 Proceedings of the 7th International Conference on Computer Vision Systems: Computer Vision Systems
On automated model-based extraction and analysis of gait
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Hi-index | 0.00 |
Gait recognition is an unobtrusive biometric, which allows identification of people from a distance by the manner in which they walk. In this paper, a new approach is proposed for extracting human gait features based on body joint identification from human silhouette images. In the proposed approach, the human silhouette image is first enhanced to remove the artifacts before it is divided into eight segments according to a priori knowledge of human body proportion. Next, the body joints which act as the pivot points in human gait are automatically identified and the joint trajectories are computed. To assess the performance of the extracted gait features, fuzzy k-nearest neighbor classification technique is used to identify subjects from the SOTON covariate database. The experimental results have shown that the gait features extracted using the proposed approach are effective as the recognition rate has been improved.