Biometric Identification Using a New Direction in Contactless Palmprint Imaging

For the purpose of biometric applications, we explore in this paper a new approach to characterize palmprint features. In recent years, the contactless system emerges as a new viable option to address hygienic issues and improve the user acceptance. In this paper, we examine the issues related to the contactless imaging and we propose a new approach for palmprint recognition captured in contact free settings and without constraint on the capture environment. For the step of hand detection, our approach is based on a data-mining process for skin color modeling. To improve the achieved results and to determine the hand region in the image, a succession of post-processing was proposed. For the step of palmprint recognition, our approach is based on a new global approach that focuses only on areas of the image having the most discriminating features for recognition. The presented approach was evaluated experimentally on a real contactless palmprint database, namely, “Sfax-Miracl hand database”; the results of this evaluation show promising results and demonstrate the effectiveness of the proposed approach.