Title :
A hidden Markov model fingerprint classifier
Author_Institution :
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Abstract :
Fingerprint classification is an important indexing method for any fingerprint database or recognition system. Fingerprints are classified based on overall characteristics. This paper describes a novel method of classification using hidden Markov models to recognize the ridge structure of the print. The paper also describes a method for achieving any level of accuracy required by the system by sacrificing the efficiency of the classifier. Results are presented on a NIST fingerprint database.
Keywords :
feature extraction; fingerprint identification; hidden Markov models; image classification; HMM fingerprint classifier; NIST fingerprint database; classifier efficiency; feature extraction; fingerprint classification; fingerprint recognition system; hidden Markov model; indexing method; ridge structure; Classification algorithms; Feature extraction; Fingerprint recognition; Frequency; Hidden Markov models; Image databases; Image matching; Information retrieval; Skeleton; System testing;
Conference_Titel :
Signals, Systems & Computers, 1997. Conference Record of the Thirty-First Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
Print_ISBN :
0-8186-8316-3
DOI :
10.1109/ACSSC.1997.680212
