Multi-spectral Palmprint Recognition with Deep Multi-view Representation Learning

Abstract

With the widespread application of biometrics in identification systems, palmprint recognition technology, as an emerging biometric technology, has received more and more attention in recent years. Palmprint recognition mainly focuses on image acquisition, preprocessing, feature selection and image matching. Feature extraction and matching are usually the most essential processes in palmprint recognition, and most of the research is based on feature selection and image matching, and many researchers use rich knowledge in machine learning and computer vision to solve these problems. In this paper, we propose a deep multi-view representation learning based multi-spectral palmprint fusion method, which uses deep neural networks to extract feature representation of multi-spectral palmprint images for palmprint classification. In this manner, the unique features of different spectral palmprint images can be used to learn a view-invariant representation of each palmprint. By using view-invariant representation, we can get better palmprint recognition performance than single modality. Experiments are performed on PolyU palmprint data set to validate the effectiveness of the proposed method.