运用竞争反样本的人脸认证算法  

Face verification using competitive negative samples

作　　者：杨琼[1] 丁晓青[1] 

机构地区：[1]清华大学电子工程系智能技术与系统国家重点实验室,北京100084

出　　处：《清华大学学报（自然科学版）》2004年第1期5-8,共4页Journal of Tsinghua University(Science and Technology)

基　　金：国家"八六三"高技术项目(2001AA114081);国家自然科学基金资助项目(69972024)

摘　　要：为了在认证中增强类间可鉴别性,通过引入竞争反样本,提出一种新的人脸认证算法。算法中,测试人脸不仅与所声明客户人脸进行匹配比对,同时也与各竞争反样本逐一计算匹配分值。所有分值综合起来,形成最终认证决策。设计最近邻反样本决策、全体反样本决策、最近邻域反样本决策等3种方案,并结合开集模式的人脸认证领域分别在多个人脸库、不同特征和不同分类器上进行实验和比较。在该文的测试中,新算法的3种方案与原有基于相似度的认证算法相比,错误率依次平均降低25.13%、30.24%、30.97%。A novel verification algorithm was proposed using competitive negative samples to enhance discrimination in face verification. In the algorithm, the test face was matched not only with the claimed client face, but also with competitive negative samples, with all the matching scores combined for a final decision. Three schemes were designed. They were the closest-negative- sample scheme, the all-negative-sample scheme, and the closest- few-negative-sample scheme. The schemes were compared with the traditional similarity-based verification approach on several databases, features and classifiers. The tests demonstrat that the three schemes reduced the verification error rate by 25.13%, 30.24% and 30.97% on average.

关 键 词：竞争反样本 人脸认证 算法 图像识别 开集模式 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP301.6[自动化与计算机技术—计算机科学与技术]