Supported by the National Natural Science Foundation of China under Grant Nos.60621001, 60875018 (国家自然科学基金), the National High-Tech Research and Development Plan of China under Grant No.2008AA01Z411 (国家高技术研究发展计划(863)); the Hundred Talents Program of the Chinese Academy of Sciences (中国科学院百人计划); the Beijing Municipal Natural Science Foundation of China under Grant No.4091004 (北京市自然科学基金)
对当前国内外生物特征模板保护技术发展的现状进行综述和探索,对该方向的研究内容进行详细的梳理和分类.首先阐述传统生物特征识别系统存在的本质缺陷和易于遭受到的攻击的形式,进而从理论上引出了生物特征模板保护的必要性及其难点所在.然后以模板保护算法的具体操作方式为分类标准,详细阐述了当前在这个领域出现的比较有代表性的算法,诸如Biohashing和模糊保险箱(Fuzzy Vault)等.通过实验验证了Biohashing算法的优势和缺陷,并且在FVC2002 DB2数据库上对提出的改进Fuzzy Vault算法进
This paper reviews the state-of-the-art of biometric template protection technology domestic and abroad, and then systemizes almost all the related research directions. First it is clarified that the underlying disadvantages of traditional biometric systems and the attacks they are vulnerable to. Then the necessity and difficulty of protecting biometric template are drawn naturally. Afterwards this paper classifies the methods and algorithms into various categories based on the operation manner, and elaborates specifically some representative ones, such as Biohashing and Fuzzy Vault and so on. In the experiment, evaluations of Biohashing and Fuzzy Vault are carried on different fingerprint databases, and the results show the advantages and disadvantages of Biohashing method, as well as our improved Fuzzy Fingerprint Vault’s better performance and security on FVC2002 DB2.
李鹏,田捷,杨鑫,时鹏,张阳阳.生物特征模板保护.软件学报,2009,20(6):1553-1573
复制