FINGERPRINT CLASSIFICATION

A fingerprint classification algorithm is presented in this paper. Fin gerprints are classified into five categories: arch, tented arch,left loop, right loop acid whorl. The algorithm extracts singular points (c ores and deltas) in a fingerprint image and performs classification ba sed on the number and locations of the detected singular points. The c lassifier is invariant to rotation, translation and small amounts of s cale changes. The classifier is rule-based, where the rules are genera ted independent of a given data set. The classifier was tested on 4000 images in the NIST-4 database and on 5400 images in the NIST-9 databa se. For he NIST-4 database, classification accuracies of 85.4% for the five-class problem and 91.1% for the Four-class problem (with arch an d tented arch placed in the same category) were achieved. Using a reje ct option, the four-class classification error can be reduced to less than 6% with 10% fingerprint images rejected. Similar classification p erformance was obtained on the NIST-9 database.