Dorsal hand vein recognition based on 2D Gabor filters

Abstract

Hand vein patterns are among the biometric traits being investigated today for identification purposes, attracting interest from both the research community and industry. A reliable and robust personal verification approach using dorsal hand vein patterns is presented in this paper. This approach needs less computational and memory requirements and has a higher recognition accuracy than similar methods. In our work, a near-infrared charge-coupled device camera is adopted as an input device for capturing dorsal hand vein images, due to its advantages of the low-cost and non-contact imaging. In the proposed approach, two finger-peaks are automatically selected to define the region of interest in the dorsal hand vein images. In order to obtain effective pattern of dorsal hand vein vascular, we proposed an innovative and robust adaptive Gabor filter method to extract the dorsal hand vein patterns and encode the vein features in bit string representation. The bit string representation, called VeinCode, offers speedy template matching and enables more effective template storage and retrieval. The similarity of two VeinCodes is measured by normalised Hamming distance. A total of 6160 dorsal hand vein images were collected from 308 persons to verify the validity of the proposed dorsal hand vein recognition approach. High accuracies (.99%) have been obtained by the proposed method, and the speed of the method (responding time ,0?8 s) is rapid enough for real-time recognition. Experimental results demonstrate that our proposed approach is feasible and effective for dorsal hand vein recognition.

Research of the types of applicable people and the statistical characteristics of hand vein image

“…( ) 1 , I i j , 1 M and 1 V stand for the processed gray value, mean gray and variance. i , j are rows and columns.…”

“…Hand vein recognition is an important part of biological recognition, it acquires more and more attention and becomes a research hotspot [1][2][3][4][5][6] because of its advantages of difficult duplicate and acquisition in vivo. In the field of auxiliary medical, hand vein image has also been widely used and auxiliary vein puncture apparatus [7][8] have been applied in commerce.…”

Vein Recognition Algorithm Based on Transfer Nonnegative Matrix Factorization

“…The existing researches on vein recognition can be roughly divided into the following two categories: 1) Vein recognition based on gray features. It is very common to extract effective gray features by analyzing the highfrequency information of the vein images, where the highfrequency information can be acquired based on multi-scale analysis theories which include traditional wavelet transform [2][3], Bandelet transform [4], Gabor transform [5][6][7][8][9][10], Curvelet transform [11], Contourlet transformation [12][13], Histogram of Oriented Gridients (HOG) operator [14], spatial curve filtering [15], ridgelet transformation [16], Scale-Invariant Feature Transform (SIFT) [17] and some improved Gabor transform methods [18][19][20][21]; In recent years, some deep learning methods have also been gradually used in vein recognition such as deep neural networks [22] and convolution neural networks [23][24]; In addition, the gray statistical distribution based methods were also verified to be effective such as intensity distribution [25], hierarchical hyper-sphere model [26], sparse representation [27], gradient distribution [28], etc. 2) Vein recognition based on points and curves.…”

Robust and adaptive ROI extraction for hyperspectral dorsal hand vein images

“…Dorsal hand images in the data set sharing the minimum Euclidean distance with respect to the PLBP feature vector will be recognised as the same dorsal hand in the matching phase. In addition to PLBP, Gabor [10] and VGG-16 deep features [11] are also extracted for both identification and verification experiments. In the identification stage, we chose n samples (n = 1,…,4) for training with the others (5 − n samples) assigned as testing.…”