Perspective of Fingerprint Recognition Using Robust Local Feature

There exist many human recognition techniques which are based on fingerprints. Most of these techniques use minutiae points for fingerprint representation and matching. However, these techniques are not rotation invariant and fail when enrolled image of a person is matched with a rotated test image. Moreover, such techniques fail when partial fingerprint images are matched. This paper proposes a fingerprint recognition technique which uses local robust features for fingerprint representation and matching. The technique performs well in presence of rotation and able to carry out recognition in presence of partial fingerprints. Experiments are performed using a database of 200 images collected from 100 subjects, 2 images per subject. The technique has produced a recognition accuracy of 99.46 % with an equal error rate of 0.54 %.