Karhunen-Loeve transform based hand identification system

In this paper we propose a KLT based hand identification system for personal identification. These approach offers more scope for credible authentication as compared to finger print recognition. The images of the hand are taken and length of the fingers is computed using gradient method. These are used as features for categorizing the palm. The variance of the lines in the palm is calculated for all subblocks of the palm image to get another set of feature vectors. Therefore the number of parameters which have to be matched for authentication are more in the case of palm than a finger. Our approach to extract the palm and fingers from the and reduces the computation time for recognition.