摘要
采用联合动态稀疏表示方法构造一种新型的多图像人脸识别模型。该模型在多张人脸图像的稀疏表示矩阵上,利用动态数集得到联合动态稀疏表示矩阵,识别多图像的人脸。在多张人脸图像作为测试样本的情况下,利用多图像之间的关联性提高人脸图像识别的准确率。最后利用CMU人脸图像库对该算法进行仿真,结果表明其识别率较其他算法有很大的提高。
Multi-view face recognition is one of the difficult problems.In this paper,a new multi-view face recognition model is structured by the joint dynamic sparse representation.We use the dynamic number set to obtain the joint dynamic sparse representation matrix so as to recognize face on the base of multi-view face image sparse representation matrix.Taking different multi-faces as samples,it turns out that the proposed algorithm in this paper can improve face recognition accuracy.Finally,the simulation results on the CMU facial image database demonstrate that the proposed algorithm has a higher recognition rate than other algorithms.
出处
《江南大学学报(自然科学版)》
CAS
2014年第3期287-291,共5页
Joural of Jiangnan University (Natural Science Edition)
基金
江苏省产学研联合创新项目(BY2013015-33)
关键词
人脸识别
稀疏表示
CMU人脸库
多图像
识别率
face recognition
sparse representation
CMU face library
multiple views
recognition rate