Article ID Journal Published Year Pages File Type
536456 Pattern Recognition Letters 2012 11 Pages PDF
Abstract

Finger–vein based biometrics, as a new approach to personal identification, has received much attention in recent years. However, the poor visibility of finger–vein imageries is really not beneficial for deepening the understanding of finger–vein characteristics. Moreover, unreliable finger–vein region of interest (ROI) localization can also heavily degrade the performance of a finger–vein based recognition system in practical scenario. Hence, in this paper, we first introduces a new and robust approach for finger–vein ROI localization, and then proposes a new scheme for effectively improving the visibility of finger–vein imageries. Extensive experiments are finally conducted to validate the proposed method.

► An inter-phalangeal joint prior is used for finger–vein ROI localization. ► Haze removal method is used for improving finger–vein visibility. ► A dictionary of Gabor filters are designed specifically for vein ridge detection. ► A multiscale multiplication rule is proposed for enhancing vein ridges and suppressing fake veins.

Related Topics
Physical Sciences and Engineering Computer Science Computer Vision and Pattern Recognition
Authors
, ,