Finger Vein Recognition Using Haar Wavelet Transform?

Finger vein is an important biometric technique for personal identification and authentication. The finger vein is a blood vassal network under the finger skin. The network pattern is distinct for each individual, unaffected by aging and it is internal. i.e. inside human skin which can always guarantee more security authentication. finger‐vein recognition systems capture images by using near infrared (NIR) illumination in conjunction with a camera. However, such systems can face operational difficulties, since the scattering of light from the skin can make capturing a clear image difficult, which represent the major challenge in our proposed system, which is how to localize the vein grid, and the following challenges are choosing the suitable feature vector to identify the vein pattern. The attracting features of the Haar Wavelet Transform, including fast for implementation and able to analyse the local feature makes it the suitable choice in our system. The system was tested over a database collected from 106 volunteers, where 6 images are collected for each person. The attained identification result is encouraging where equal error rate for one level decomposed wavelet was (98.7%), and when increasing the levels of decomposed wavelet was (99.8%).