FINGERPRINT IMAGE-ENHANCEMENT - ALGORITHM AND PERFORMANCE EVALUATION

A critical step in automatic fingerprint matching is to automatically and reliably extract minutiae from the input fingerprint images. Howev er, the performance of a minutiae extraction algorithm relies heavily on the quality of the input fingerprint images. In order to ensure tha t the performance of an automatic fingerprint identification/verificat ion system will be robust with respect to the quality of input fingerp rint images, it is essential to incorporate a fingerprint enhancement algorithm in the minutiae extraction module. We present a fast fingerp rint enhancement algorithm, which can adaptively improve the clarity o f ridge and valley structures of input fingerprint images based on the estimated local ridge orientation and frequency. We have evaluated th e performance of the image enhancement algorithm using the goodness in dex of the extracted minutiae and the accuracy of an online fingerprin t verification system. Experimental results show that incorporating th e enhancement algorithm improves both the goodness index and the verif ication accuracy.