Towards contactless palm region extraction in complex environment

Palm region of interest (ROI) extraction is an indispensable procedure in palmprint recognition. Prior works generally perform well on palm ROI extraction because of dedicated devices and well-controlled environment. To make hand placement less-constrained and improve usability, mobile palmprint recognition has attracted a wide attention in recent years. For mobile phone images captured in complex natural environment, palm ROI extraction is a challenging work due to varying illumination, complex background and contactless acquisition mode. In this paper, a mobile palmprint dataset (SPIC) is at first established with five smartphones, comprising 4000 images collected from 128 persons in two separate sessions. Furthermore, a novel pre-processing approach is proposed to achieve ROI extraction in mobile scenarios, which include colour component selection, learning-based fast hand segmentation and geometry-driven valley point location. Experimental results demonstrate that the proposed method can achieve high extraction accuracy and computational efficiency on PolyU1.0, HA-BJTU and SPIC palmprint databases.