Palmprint-Palmvein Fusion Recognition Based on Deep Hashing Network

Palmprint attracts increasing attention due to its several advantages in the biometrics field. Deep learning has achieved remarkable performance computer vision area, so a large number of deep-learning-based methods have been proposed by research community for palmprint recognition. The outputs deep hashing network (DHN) can be represented as binary bit string, DHN reduce storage and accelerate matching/retrieval speed. In this paper, is employed extract template palmvein verification. Spatial transformer used overcome rotation dislocation. acquired from visible-light spectrums, including red (R), green (G), blue (B), near infrared (NIR) spectrum, respectively. Since features different spectrums are different, their complementary exploited full fusion. Image-level fusion score-level developed palmprint-palmvein sufficient experiments demonstrate that improve accuracy efficiently.