基于统计特征的3D人脸识别生物模板保护方案  

A Statistic Feature-Based Scheme for the Template Protection of 3D Face Recognition

作　　者：黄文军[1] 牛夏牧[1,2] 李琼[2] 马舰[2] 

机构地区：[1]哈尔滨工业大学深圳研究生院信息安全研究中心,广东深圳518055 [2]哈尔滨工业大学信息对抗技术研究所,黑龙江哈尔滨150001

出　　处：《电子学报》2007年第B12期104-108,共5页Acta Electronica Sinica

基　　金：国家自然科学基金（N0.60671064,No.60703011）;全国百名优秀博士学位论文作者专项资金（N0.FANEDD-200238）;教育部新世纪人才计划（No.NCET-04-0330）;国家863计划（No.2007AA012458）;2007年度高校博士点专项科研基金（No.RFI）P-20070213047）

摘　　要：生物模板的安全是生物识别系统安全的一个重要因素，传统的生物识别系统直接存储生物模板的方式导致一系列的安全和隐私问题，成为阻碍生物识别技术发展与推广的瓶颈．基于统计特性提取特征是人脸识别中一项较为成熟的技术，本文针对此类生物模板，提出了一种合适的模板保护方案，该方案的核心思想是利用密码学中的Hash函数实现模板与待测特征信息之间的匹配，通过选取特征向量中的主要成分、量化和纠错码等方法解决生物信息模糊性和Hash函数敏感性之问的矛盾．通过对方案的安全分析和在3D人脸识别中的仿真实验，验证了方案的安全性和可行性．The security of biometric template is an important factor in a biometric system＇s security. In a traditional biometo ric system, the template being saved directly in a reference database results in a series of security and privacy risks, which limits the development of biometric recognition technique. This paper provides a template protection scheme that is suit for statistic featurebased algorithm, which is widely used in face recognition. The core idea of the scheme is the match between template and measured feature by using Hash function. The scheme merges of three methods, which are selecting primary components, quantization and error correction coding, to eliminate the contradiction between the fuzziness of the biometric information and the sensitiveness of the hash function. The proposed scheme has been applied to 3D face recognition, the analysis demonstrated the security of the scheme and the simulation results showed the feasibility of the scheme.

关 键 词：生物模板保护 统计特征 3D人脸识别 HASH函数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]