Weighted Fusion of Multi-Featured of Gait Recognition Algorithm

DOI

10.2991/mmme-16.2016.71How to use a DOI?

Keywords

skeleton model; joint angle feature; feature fusion; SVM

Abstract

Gait recognition has become one of the hottest directions in study of long-range identification. Joint angle feature is an important gait feature, but extracting joint angle feature using traditional skeleton model is too idealistic. Therefore, a method of extracting joint angle feature based on skeleton model to remove the ending points was put forward. Given the low recognition rate of single feature, the paper would the joint angle fea-ture, GEI and discrete Hu moment invariants weighted feature fusion. The experimental results show that the new joint angle feature extraction and feature weighted fusion algorithm improves gait recognition perfor-mance.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hui Wang
AU  - Taijun Li
AU  - Haoli Zhou
AU  - Zezhong Yang
PY  - 2016/10
DA  - 2016/10
TI  - Weighted Fusion of Multi-Featured of Gait Recognition Algorithm
BT  - Proceedings of the 2016 4th International Conference on Mechanical Materials and Manufacturing Engineering
PB  - Atlantis Press
SP  - 314
EP  - 318
SN  - 2352-5401
UR  - https://doi.org/10.2991/mmme-16.2016.71
DO  - 10.2991/mmme-16.2016.71
ID  - Wang2016/10
ER  -