期刊名称:International Journal of Computer Science Issues
印刷版ISSN:1694-0784
电子版ISSN:1694-0814
出版年度:2011
卷号:8
期号:5
出版社:IJCSI Press
摘要:Fingerprint recognition is one of the most promising and evergreen biometric recognition technique used presently. In this paper we have proposed Extended Fuzzy Hyperline Segment Clustering Neural Network (EFHLSCNN) with its learning algorithm, which utilizes fuzzy sets as pattern clusters. In this extended version of paper we have used Manhattan distance for calculating distance of hyperline segments. The performance of EFHLSCNN when verified with fingerprint feature vectors, it is found superior than fuzzy hyperline segment clustering neural network (FHLSCNN) proposed by Kulkarni and Sontakke in terms of higher recognition rate and generalization.