This paper presents a novel method for identity recognition based on the 2D gait representation: Gait Energy Image (GEI) which is the averaged silhouette over one gait cycle. An ensemble of Gabor kernels is first convolved with GEI to extract discriminative feature. The obtained Gabor gait representation is then projected into lower dimensional subspace using discriminative common vectors (DCV) analysis. The final classification is performed in this subspace. The proposed method is tested on the USF HumanID Database. Experimental results show that Gabor-based method can improve recognition rate, and DCV is superior to other traditional dimensional reduction algorithm in the gait recognition application.
Gabor-Based Discriminative Common Vectors for Gait Recognition
2008 Congress on Image and Signal Processing ; 4 ; 191-195
2008-05-01
837296 byte
Conference paper
Electronic Resource
English
Gait recognition based on Gabor wavelets and modified gait energy image for human identification
British Library Online Contents | 2013
|Object recognition with adaptive Gabor features
British Library Online Contents | 2004
|Pseudo-Gabor wavelet for face recognition
British Library Online Contents | 2013
|Graph-Based Discriminative Learning for Location Recognition
British Library Online Contents | 2015
|Object recognition using discriminative parts
British Library Online Contents | 2012
|