基于判别相关分析法的手指多模态融合身份识别方法

摘要

针对基于单一模态的手指生物特征身份认证技术在实际应用中受数据噪声、类内差异、类间相似及防伪性低等因素制约的问题,提出基于判别相关分析的手指多模态融合身份识别方法.以手指静脉为研究对象,结合指腹纹理特征,采用广义判别分析法降维,并采用判别相关分析法对降维后的指静脉和指腹纹理特征进行融合,实现了基于特征层融合的手指多模态生物特征的身份认证识别.本方法实现了手指静脉和指腹纹特征的融合,与传统的核线性分析和典型相关分析方法相比,提高了身份认证的准确率,促进了手指多模态生物特征认证的进一步发展.%The finger-based biometrics authentication technology based on single mode is inevitably limited by data noise,in-tra-class difference,similarity between classes and low security,a multi-modal fusion recognition method based on discrimi-nant correlation analysis is proposed.With finger vein as the research object,combined with the features of finger texture, the generalized discriminant analysis method is used to reduce the dimension,and discriminant correlation analysis is adopted for fusing two modal features after dimension reduction,and the identity authentication of finger multi-modal biometrics based on feature layer fusion is realized.This method realizes the fusion of finger vein and finger dorsal texture,which im-proves the accuracy of identity authentication and the further development of finger multi-modal biometric authentication compared with the traditional nuclear linear analysis and typical correlation analysis method.