An Effective Method for Fingerprint Classification

This paper presents an effective method for fingerprint classification using data mining approach. Initially, itgenerates a numeric code sequence for each fingerprint image based on the ridge flow patterns. Then for each class, a seed isselected by using a frequent itemsets generation technique. These seeds are subsequently used for clustering the fingerprintimages. The proposed method was tested and evaluated in terms of several real-life datasets and a significant improvement inreducing the misclassification errors has been noticed in comparison to its other counterparts.