Research on Finger Vein Recognition Technology

The principle of finger vein recognition is researched, a device used to collect the finger vein images is produced. The images collected are eprocessed, the images are made to gray and combined filter is used to make the model more precision. In order to avoid the effect of area on and out of the finger profile, a method which implement by iterative threshold to extract the finger area and label the profile is used, the area which less than the given threshold is wiped off, the image height is normalized. Three recognition methods which based on moment character, wavelet moment and wavelet moment fusing with K-L and FDA transform rae researched and experimented.