多模态人脸识别融合方法比较研究

被引:6
作者
叶剑华
刘正光
机构
[1] 天津大学电气与自动化工程学院
关键词
局部二值模式; Fisherfaces; 多模态人脸识别; 融合;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
比较研究了多模态人脸识别中的5种匹配得分级融合方法。首先用局部二值模式(Local Binary Pattern,LBP)算子分别提取人脸灰度图像和深度图像的区域LBP直方图序列(LBP Histogram Sequence,LBPHS),采用Fisherfaces分别构建相应的线性子空间,用余弦相似度计算投影向量的匹配得分,再采用5种方法对匹配得分进行融合。在FRGC数据库上的实验结果表明,除最小匹配得分外,其他融合方法的识别性能都要优于单一模态的方法。
引用
收藏
页码:153 / 156
页数:4
相关论文
共 6 条
[1]  
Eigenfaces vs Fisherfaces: Recognition using class specific linear projection. Belhumeur PN,Hespanha JP,Kriegman DJ. IEEE Transactions on Pattern Analysis and Machine Intelligence . 1997
[2]  
A survey of approaches and challenges in 3D and multi-modal 3D + 2D face recognition. K. Bowyer,K. Chang,P. Flynn. Journal of Computer Vision and Image Understanding . 2006
[3]  
Optimal Linear Combination of Facial Regions for Improving Identification Performance. K. Wong,W. Lin,Y. H. Hu, et al. IEEE Transactions on Systems, Man, and Cybernetics- Part B: Cybernetics . 2007
[4]  
Face recognition with local binary patterns. Ahonen T,Pietikainen A H M. ECCV . 2004
[5]  
Large scale evaluation of multimodal biometric authentication using state-of-the-art systems. Snelick R,Uludag U,Mink A,et al. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2005
[6]  
Overview of the face recognition grand challenge. Phillips P J,Scruggs P J F T,Bowyer K W,et al. IEEE Computer Society Con-ference on Computer Vision and Pattern Recognition (CVPR’05) . 2005