Human identity recognition using sparse auto encoder for texture information representation in palmprint images based on voting technique

Nowadays, biometric systems are used for the security and personal recognition. The palmprint trait is one among the most confident physiological modalities that can be used to recognize human identity. The biggest advantage of the use of palmprint consists of weak changes affecting this modality compared to other physical modalities like face. In our paper, we report the problematic of human identity recognition using palmprint. We focus on the texture information that can be extracted using texture based descriptors such as Gabor, Wavelet, Wave Atom, Curvelet, SIFT, CNN, and LBP. Our main contribution is based on the use of the Sparse Auto Encoder in order to represent all combined feature vectors of the palmprint texture. To evaluate our proposed approach of sparse nonlinear representation of features, several experiments were carried out on the IITD palmprint database. The proposed approach has shown promising results using fusion at decision level in order to recognize human identity.