针对不可控条件对人脸识别的影响,提出一种基于多尺度分块局部二值模式(Multi-scale Block Local Binary Patterns,MB-LBP)和Fisherfaces融合的人脸识别算法。采用适当模块大小的MB-LBP算子提取图像的纹理结构信息,得到相应的特征直方图...针对不可控条件对人脸识别的影响,提出一种基于多尺度分块局部二值模式(Multi-scale Block Local Binary Patterns,MB-LBP)和Fisherfaces融合的人脸识别算法。采用适当模块大小的MB-LBP算子提取图像的纹理结构信息,得到相应的特征直方图;通过Fisherfaces方法对MB-LBP提取的特征进行降维和分类;经由最近邻方法进行匹配识别。在ORL和Yale人脸库上进行实验,分别与其他基于LBP和MB-LBP算法的识别效果进行比对。实验结果表明,识别效率显著提高,鲁棒性更好。展开更多
Fisherfaces algorithm is a popular method for face recognition.However,there exist some unstable com- ponents that degrade recognition performance.In this paper,we propose a method based on detecting reliable com- pon...Fisherfaces algorithm is a popular method for face recognition.However,there exist some unstable com- ponents that degrade recognition performance.In this paper,we propose a method based on detecting reliable com- ponents to overcome the problem and introduce it to 3D face recognition.The reliable components are detected within the binary feature vector,which is generated from the Fisherfaces feature vector based on statistical properties,and is used for 3D face recognition as the final feature vector.Experimental results show that the reliable components fea- ture vector is much more effective than the Fisherfaces feature vector for face recognition.展开更多
文摘针对不可控条件对人脸识别的影响,提出一种基于多尺度分块局部二值模式(Multi-scale Block Local Binary Patterns,MB-LBP)和Fisherfaces融合的人脸识别算法。采用适当模块大小的MB-LBP算子提取图像的纹理结构信息,得到相应的特征直方图;通过Fisherfaces方法对MB-LBP提取的特征进行降维和分类;经由最近邻方法进行匹配识别。在ORL和Yale人脸库上进行实验,分别与其他基于LBP和MB-LBP算法的识别效果进行比对。实验结果表明,识别效率显著提高,鲁棒性更好。
基金Supported by the National Natural Science Foundation of China(60671064)the Foundation for the Author of National Excellent Doctoral Dissertation of China(FANEDD-200238)+1 种基金the Foundation for the Excellent Youth of Heilongjiang Provincethe Program for New Century Excellent Talents in University(NCET-04-0330)
文摘Fisherfaces algorithm is a popular method for face recognition.However,there exist some unstable com- ponents that degrade recognition performance.In this paper,we propose a method based on detecting reliable com- ponents to overcome the problem and introduce it to 3D face recognition.The reliable components are detected within the binary feature vector,which is generated from the Fisherfaces feature vector based on statistical properties,and is used for 3D face recognition as the final feature vector.Experimental results show that the reliable components fea- ture vector is much more effective than the Fisherfaces feature vector for face recognition.