engleski

A Biometric Identification System Based on Eigenpalm and Eigenfinger Features

This paper presents a multimodal biometric identification system based on the features of the human hand. We describe a new biometric approach to personal identification using eigenfinger and eigenpalm features, with fusion applied at the matching-score level. The identification process can be divided into the following phases: capturing the image ; preprocessing ; extracting and normalising the palm and tripe-like finger subimages ; extracting the eigenpalm and eigenfinger features based on the K-L transform ; matching and fusion ; and finally, a decision based on the (k, l)-NN classifier and thresholding. The system was tested on a database of 237 people (1820 hand images). The experimental results showed the effectiveness of the system in terms of the recognition rate (100%), the equal error rate (EER = 0.58%) and the total error rate (TER = 0.72%).

biometrics; multimodal systems; hand-based identification; K-L transform; eigenpalms; eigenfingers

nije evidentirano