GGCN: Gait Recognition with Generate Network and Convolutional Neural Network

Abstract

Gait recognition is a biometric technology with wide application prospects, but it is easily affected by various covariates, which requires the gait recognition model is robust. In this paper, we design a robust gait recognition model named GGCN (Gait recognition with Generate network and Convolutional neural Network), which uses multi-type gait sequences as input and eliminates the effects of various covariates through a supervised mapping module. The GGCN processes the gait sequence in three steps. First, the generate network is used to extract low-level features and remove the features generated by interference. Then, the low-level features are input into the encoder network to obtain high-level features. Finally, the high-level features are input into the feature mapping network to acquire more recognizable features. The experimental results on the CASIA-B, OULP, and OUMVLP datasets demonstrate that our model outperforms current state-of-the-art methods.