Channel Group-wise Drop Network with Global and Fine-grained-aware Representation Learning for Palm Recognition
Wu Rong, Ziyuan Yang, Lu Leng · 2022
As a relatively new biometric modality, palmprint attracts much attention for its rich intrinsic features and high commercial prospects. Most existing palmprint recognition methods only extract features from the region of interest (ROI) and neglect the features of other regions. Hence, the recognition performance of these methods highly relies on ROI localization, and it requires users' high cooperation. To relieve these problems, we propose a novel end-to-end recognition framework for contactless whole-palm region-based recognition in this paper, dubbed as Channel Groupwise Drop Network (CGDNet). CGDNet consists of a trunk branch and a part exciting branch. The trunk branch extracts the global representations, and the global scale (GS) module is designed to measure the similarity from feature positions to obtain global knowledge. In the part exciting branch, the features are split into two fine-grained parts equally along the horizontal direction. Then, the channel group-wise drop (CGD) module is designed to aggregate the same part features of the object and cooperates with the CGD mask, which randomly drops the same region in the channel group to excite diverse fine-grained features for learning. Finally, fine-grained features and the global features are concatenated as the final feature. The proposed CGDNet achieves competitive performance in two bench-mark datasets compared with the state-of-the-art methods.