【摘要】 针对单模生物特征识别在实际应用中易受干扰、识别率低且无法达到零错误识别的问题,提出一种基于二代Curvelet和2DLog-Gabor滤波器的人脸与虹膜特征层融合识别算法.该方法利用二代曲波变换提取人脸特征,用2DLog-Gabor幅值法提取虹膜特征,通过PCA降维单模特征向量,在特征层进行融合,通过SVM分类识别融合特征向量.在ORL人脸库和CISIA虹膜库构成的多模生物特征库上进行测试.实验结果表明:该算法正确识别率能达到100%,较单模人脸、单模虹膜识别方法的识别率均提高3.33%,为多模生物特征识别提供了一种有效模型.更多还原

【Abstract】 For single-modal biometric system is susceptible to interference in appliacation,with low recognition rate,and not able to achieve zero error identification,a new fusion recognition approach in feature level of face and iris is proposed,based on the second-generation Curvelet and 2D Log-Gabor filtering.In the proposed approach,the second generation Curvelet is employed to extract face information,and amplitudes of 2D Log-Gabor are used to extract iris information.Then we use PCA to reduce the dimention of single-modal feature vectors,combine them in feature level,and distinguish fusion feature vectors by SVM.Experimental results on ORL face database and CASIA iris database show that: the correct fusion recognition rate can reach 100%,improved both 3.33% compared with single face feature and single iris feature,and the proposed algorithm is an effective model for multimodal biometric recognition.更多还原