Finger-Vein Recognition Based on a Bank of Gabor Filters

This paper presents a new finger-vein based method of personal identification. A reliable finger-vein region suitable for recognition is first acquired using our homemade imaging system. To exploit the finger-vein characteristics with high randomicity, a bank of Gabor filters specific to finger-vein analysis is then designed. Based on the spatial filtered images, finger-vein feature vectors are constructed for describing finger-vein characteristics in two filter scales. Finally, a fusion scheme in decision level is adopted to improve the reliability of identification. Experimental results are given to show the effectiveness of the proposed method in personal identification.