Biometric cryptosystem based on discretized fingerprint texture descriptors

作     者：Imamverdiyev, Yadigar Teoh, Andrew Beng Jin Kim, Jaihie 

作者机构：Yonsei Univ Biometr Engn Res Ctr Sch Elect & Elect Engn Seoul 120749 South Korea Inst Informat Technol ANAS Baku Azerbaijan 

出 版 物：《EXPERT SYSTEMS WITH APPLICATIONS》 (专家系统及其应用)

年 卷 期：2013年第40卷第5期

页      面：1888-1901页

核心收录：

学科分类：1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Research Foundation of Korea (NRF) Korea government (MEST) 

主　　题：Fuzzy commitment scheme Fingerprint texture descriptors Local binary pattern Biometric discretization Error-correcting code 

摘      要：This paper focuses on a biometric cryptosystem implementation and evaluation based on a number of fingerprint texture descriptors. The texture descriptors, namely, the Gabor filter-based FingerCode, a local binary pattern (LBP), and a local direction pattern (LDP), and their various combinations are considered. These fingerprint texture descriptors are binarized using a biometric discretization method and used in a fuzzy commitment scheme (FCS). We constructed the biometric cryptosystems, which achieve a good performance, by fusing discretized fingerprint texture descriptors and using effective error-correcting codes. We tested the proposed system on a FVC2000 DB2a fingerprint database, and the results demonstrate that the new system significantly improves the performance of the FCS for texture-based fingerprints. (C) 2012 Elsevier Ltd. All rights reserved.