Méthodes Biométriques Pour La Reconnaissance Des Personnes

Résumé: Person’s identity validation is becoming much more essential due to the increasing demand for high-security systems. A biometric system testifies the authenticity of specific physiological or behavioral characteristics-based biometric technology. This technology has been successfully applied to verification and identification systems. In our work, we analyze the multispectral palmprint and finger knuckle print identification systems in unimodal and multimodal modes. The feature extraction is a crucial step in the biometric system. For this reason, we propose two efficient deep learning feature extraction algorithms called discrete cosine transform network (DCTNet) and principal component analysis network (PCANet). . The effectiveness of the proposed approaches has been evaluated on two publicly available databases : CASIA and PolyU. The obtained results clearly indicate that the proposed deep learning-based feature extraction techniques can achieve comparable performance to the best of the state-of-the-art techniques.

Publié dans la revue: