Contactless palmprint biometrics using DeepNet with dedicated assistant layers

Palmprint biometrics has a broad application prospect owing to non-intrusiveness, ease of image acquisition and stable textural pattern. Hand-crafted approaches are vulnerable to non-ideal palmprint images caused by uneven illumination, motion blur and noise contamination. Many researchers have designed excellent texture descriptors or/and advanced image pre-processing algorithms. Nevertheless, they are highly targeted at some specific data, less adaptable to the emerging data. In this paper, a semi-pretrained contactless palmprint recognition deep network is developed to achieve high accuracy and robustness. Semi-CPRN is composed of underlying network structure from ResNet-152 and the proposed assistant layers dedicated to high-performance palmprint recognition. The well-designed assistant layers enhance convolutional neural network to steadily extract the real palmprint features even from the degraded images without being deceived by the degradation factors. Besides, to better carry out the research on palmprint recognition in the open environment, we established a new contactless database HIT-NIST-V1 under natural scene. The comparative experiments on CASIA, IITD, PolyU3D/2D, Tongji and HIT-NIST-V1 illustrate that Semi-CPRN is comparable and superior to previously published state-of-the-art approaches. Simultaneously, CNN-based palmprint biometrics methods show significant robustness to motion blur, Gaussian noise, and salt and pepper noise.