Multi-Scale Parallel Hybrid Network for Palmprint Recognition

Due to its rich characteristic and high accuracy, palmprint patterns have played an important role in identity recognition. However, current palmprint recognition techniques often concentrate on extracting salient features, neglecting the interactions between local and global textural attributes in palmprint images. To address this issue, we propose a novel multi-scale network capable of integrating local and global features for palmprint recognition, dubbed Multi-Scale Parallel Hybrid Network (MSPHNet). Specifically, we designed a Parallel Hybrid Feature Extraction Block (PHEB), which includes a parallel Convolutional Neural Network (CNN) -based branch for local feature extraction and a Transformer-based branch for capturing global features. Furthermore, acknowledging the uneven distribution of critical texture and its details in palmprint images, we address the current research shortfall in pixel relationship analysis by introducing the Comprehensive Attention Block (CAB). This block integrates Spatial Attention (SA) and Pixel Attention (PA) to effectively leverage the imbalanced pixel distributions within the CNN branch. Extensive experimental results on numerous public palmprint datasets demonstrated that our proposed method achieves remarkable results.