Fingerprint classification based on graylevel fuzzy clustering co-occurrence matrix

Fingerprint classification is a very important step in the fingerprint matching process in particular when the database is large, since it can provide an indexing mechanism. In this paper a finger print classification based on the Gray-Level Fuzzy Clustering Co-Occurrence Matrix is proposed. It is based on the fact that a fingerprint image is composed of regular texture regions that can be successfully represented by Gray-Level Fuzzy clustering co-occurrence matrices. So, we first extract the features based on certain characteristics of the Fuzzy Clustering co-occurrence matrix and then we use these features to train a neural network for classifying fingerprints into six common classes. The obtained results compared with the existing approaches demonstrate the superior performance of our proposed approach.