Human gait recognition based on Discrete Cosine Transform and Linear Discriminant Analysis

To improve the accuracy of gait recognition by fully utilizing gait information, a human gait recognition algorithm based on the Discrete Cosine Transform (DCT) and the Linear Discriminant Analysis (LDA) is proposed in this paper. First, frequency-domain features are extracted from the Gait Energy Image (GEI) by DCT, which can effectively distinguish different frequency components of human gait. Then, these frequency features are further mapped into the optimal discriminant vectors space by LDA, which can enhance the discrimination and reduce dimensions of features. Finally, the identity recognition is implemented according to the shortest similarity distance. Experiments on the database provided by Chinese Academy of Sciences (Institute of Automation) demonstrate that the proposed feature extraction strategy has the highest recognition rate among the compared methods.