Palmprint Identification Using PCA Algorithm and Hierarchical Neural Network

Palmprint-based personal identification, as a new member in the biometrics family, has become an active research topic in recent years. The rich texture information of palmprint offers one of the powerful means in the field of personal recognition. In this paper, a novel approach for handprint identification is proposed. Firstly, region of interest is segmented through hand's key points localization, then PCA algorithm is used to extract the palmprint features. A hierarchical neural network structure is employed to measure the degree of similarity in the identification stage. Experimental results show that the designed system achieves an acceptable level of performance.