作者: X. Tan , B. Bhanu , Y. Lin
DOI: 10.1109/TSMCC.2005.848167
关键词: Contextual image classification 、 Pattern recognition 、 Image processing 、 Classifier (UML) 、 Feature extraction 、 Naive Bayes classifier 、 Fingerprint 、 Artificial intelligence 、 Genetic programming 、 Feature learning 、 Machine learning 、 Computer science
摘要: In this paper, we present a fingerprint classification approach based on novel feature-learning algorithm. Unlike current research for that generally uses well defined meaningful features, our is Genetic Programming (GP), which learns to discover composite operators and features are evolved from combinations of primitive image processing operations. Our experimental results show can find good effectively extract useful features. Using Bayesian classifier, without rejecting any fingerprints the NIST-4 database, correct rates 4- 5-class 93.3% 91.6%, respectively, compare favorably with other published one best date.