Ridgeline Based 2-Layer Classifier in Fingerprint Classification

Fingerprint classification is an important indexing method for any large scale fingerprint recognition system or database as a method for reducing the number of fingerprints that need to be searched. Fingerprints are generally classified into broad categories based on global features. This paper describes a new 2-layer fingerprint classifier that uses curve features and singularities. In the first layer, the fingerprint was classified into Henry classes based on some curve features of ridgelines and singularities; the second layer classified the first layer´s results into N classes based on ridge counts between core and delta .Using these information, a continuous classification is performed. This 2-layer classifier was tested on NIST-4 database and got a good accuracy for the 6 classes or continuous classes.