TY - GEN
T1 - Hand vein recognition based on multi-scale LBP and wavelet
AU - Wang, Yi Ding
AU - Yan, Qing Yu
AU - Li, Ke Feng
PY - 2011
Y1 - 2011
N2 - This paper proposes a novel approach to extract multi-scale LBP features of hand vein images. Local Binary Patterns (LBP) is a simple but efficient texture operator for hand vein images. However there are two big limitations of LBP. One is that it only covers a small neighborhood area and gets very limited local information. The other is some non-uniform information will be lost as uniform patterns is adopted. To solve these problems, the hand vein image is decomposed with two-level wavelet, and gets 8 coefficient matrices: A1, H 1, V1, D1, A2, H2, V 2 and D2. In order to obtain the weight of each sub-band, the recognition accuracy of each sub-band is calculated by original LBP based on Euclidean Distance. In consideration of the direction of hand vein images, two diagonal high frequency components, D1 and D2, are abandoned. Meanwhile, A1, H1, V1, A 2, H2, V2 and the original image are chosen as multi-scale components. Finally all LBP features of components are fused. Experimental results on a database of 2040 images show that the proposed method outperforms original LBP and traditional multi-scale LBP.
AB - This paper proposes a novel approach to extract multi-scale LBP features of hand vein images. Local Binary Patterns (LBP) is a simple but efficient texture operator for hand vein images. However there are two big limitations of LBP. One is that it only covers a small neighborhood area and gets very limited local information. The other is some non-uniform information will be lost as uniform patterns is adopted. To solve these problems, the hand vein image is decomposed with two-level wavelet, and gets 8 coefficient matrices: A1, H 1, V1, D1, A2, H2, V 2 and D2. In order to obtain the weight of each sub-band, the recognition accuracy of each sub-band is calculated by original LBP based on Euclidean Distance. In consideration of the direction of hand vein images, two diagonal high frequency components, D1 and D2, are abandoned. Meanwhile, A1, H1, V1, A 2, H2, V2 and the original image are chosen as multi-scale components. Finally all LBP features of components are fused. Experimental results on a database of 2040 images show that the proposed method outperforms original LBP and traditional multi-scale LBP.
KW - Hand Vein
KW - LBP
KW - Multi-scale
KW - Wavelet
UR - http://www.scopus.com/inward/record.url?scp=80155161939&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80155161939&partnerID=8YFLogxK
U2 - 10.1109/ICWAPR.2011.6014480
DO - 10.1109/ICWAPR.2011.6014480
M3 - Conference contribution
AN - SCOPUS:80155161939
SN - 9781457702808
T3 - International Conference on Wavelet Analysis and Pattern Recognition
SP - 214
EP - 218
BT - Proceedings of 2011 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2011
T2 - 2011 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2011
Y2 - 10 July 2011 through 13 July 2011
ER -