GLCM-BASED FINGERPRINT RECOGNITION ALGORITHM

摘要：

An efficient and reliable fingerprint recognition system is the fundamental need of contemporary living. Beside forensic use, it has been deployed in a large number of commercial applications recently. In this paper, a new method for fingerprint recognition is introduced. The Core point is found initially using Poincare Index method. The dominant fingerprint region around the core point is selected and enhanced using the Diffusion Coherence Technique. The Gray level Cooccurrence Matrix (GLCM) is then applied to find out the fingerprint most significant statistical descriptors. Finally the K-Nearest Neighbor (KNN) Classifier is adopted for the recognition of unknown fingerprint images. The proposed algorithm is tested on images from FVC 2002 public domain database DB1. The experimental results demonstrate the improved performance of the algorithm.

关键词： Fingerprint Recognition Coherence Diffusion GLCM KNN Classifier

作者: Amjad Ali Xiaojun Jing Nasir Saleem

作者单位: Laboratory of Biometric and Multimedia Communication,School of Information and Communication Engineering Beijing University of Posts and Telecommunications, Beijing 100876, China

会议类型: 国际会议

会议名称: 2011 4th IEEE International Conference on Broadband Network & Multimedia Technology(第四届IEEE宽带网络与多媒体国际会议 4th IEEE IC-BNMT2011)

会议地点: 深圳

会议语种:英文

页码: 207-211

在线出版日期: 2011-10-28（万方平台首次上网日期，不代表论文的发表时间）