Hand vein recognition using local SIFT feature analysis
Sujin Zhou · Journal of Optoelectronics·laser · 2009
Aiming at the emerging hand vein pattern recognition technology,an algorithm with translation and rotation invariance is developed in this contribution,which is based on local scale invariant feature transform(SIFT) feature analysis.First,the region of interest (ROI) of the hand vein image is obtained and filtered to reduce the image noises,and then SIFT features are extracted and matched.Finally the matching ratio of features between the registered image and test image is calculated as the similarity measurement to verify the human identification.The performance of the proposed method is evaluated in the hand vein image database constructed by our group,which is also compared with the classical recognition image matching algorithm.The results show that the presented approach has better recognition performance,especially the speed which has been improved greatly.