Silhouette Analysis-Based Gait Recognition for Human Identification
IEEE Transactions on Pattern Analysis and Machine Intelligence
The HumanID Gait Challenge Problem: Data Sets, Performance, and Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Individual Recognition Using Gait Energy Image
IEEE Transactions on Pattern Analysis and Machine Intelligence
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04
Fast communication: Gait recognition based on dynamic region analysis
Signal Processing
Frame difference energy image for gait recognition with incomplete silhouettes
Pattern Recognition Letters
Fast communication: Active energy image plus 2DLPP for gait recognition
Signal Processing
Gait flow image: A silhouette-based gait representation for human identification
Pattern Recognition
Stochastic kinematic modeling and feature extraction for gait analysis
IEEE Transactions on Image Processing
Hi-index | 0.00 |
Gait energy image (GEI) has been proved to be an effective gait feature representation method. But it's sensitive to the change of clothing and carrying conditions. We propose a novel gait recognition method called partitioned weighting gait energy image (PWGEI) to deal with these problems. A human body is divided into four parts and different weights are given to different parts to get the PWGEI from GEI. Two different weighting ways are conducted and a fusion of classifiers is adopted. We test our method on the USF database. Our average recognition rate is 48.87%, which is higher than GEI by 6% and higher than gait flow image (GFI) by 5.79%. The experimental results prove the effectiveness of our proposed PWGEI method.