Asian Journal of Engineering and Technology Innovation

With identity fraud in our society reaching unprecedented proportions and with an increasing emphasis on the emerging automatic personal identification applications, biometric-base verification, especially Palm-base identification, is receiving lot of attention. There are two major short coming of the traditional approaches to Palm represntation. The widely used minutiae-base representation does not utilize a significant component of the rich discriminatory information available in the Palm. Local ridg structures cannot be completely characterized by minutae. Further, minutae-based matching has difficulty in quickly matching two Palm image containing different number of unregistered minutiae points. The proposed filter base algorithm use a bank of Gabor filters to capture both local and global details in a Palm as a compact fixed length Finger Code. The Palm match is based on the Euclidean distance between the two corresponding FingerCodes and hence is fast. We are able to achieve a verification accuracy which is only marginally inferior to the best results of minutiae-based algorithms published in the open literature [1]. Our system performs better than a state-of-the-art minutiae-based system when the performance requirement of the application system does not demand a very low wrong acceptance rate. Finally, we show this the matching performance can be improved by combining the decisions of the matchers based on complementary (minutiae-based and filter-based) Palm information.