Distorted fingerprint verification system

Fingerprint matching is affected by non-linear distortion introduced in fingerprint impression during the image acquisition process. The proposed system operates in three stages: alignment based fingerprint matching, fuzzy clustering, and classifier framework. First, an enhanced input fingerprint image is aligned with the template and match score is computed. To improve the performance of the system, a fuzzy clustering based on distance and density clusters the feature set obtained earlier. Finally, a classifier framework finds the cost-sensitive classifier produces better results.