针对局部二值模式(LBP)特征在低分辨率的人脸图像上识别率较低的问题,提出了一种基于分块中心对称局部二值模式(CS-LBP,center symmetric local binary pattern)和加权主成分分析(PCA)算法的低分辨率人脸识别算法。首先利用分块CS-LBP...针对局部二值模式(LBP)特征在低分辨率的人脸图像上识别率较低的问题,提出了一种基于分块中心对称局部二值模式(CS-LBP,center symmetric local binary pattern)和加权主成分分析(PCA)算法的低分辨率人脸识别算法。首先利用分块CS-LBP算子提取低分辨率人脸图像的特征;然后利用加权PCA算子对特征进行降维,从而得到更强的分类特征;最后利用最近邻分类器选出人脸最优分类类别并计算识别率。在ORL人脸库上的实验表明,在人脸图像分辨率下降到(12×10)时,本文算法的识别率仍能达到85.00%,基本满足了实际运用中对识别率的要求,并且降低了运算时间。展开更多
In order to solve the problem of low recognition rate of traditional feature extraction operators under low-resolution images, a novel algorithm of expression recognition is proposed, named central oblique average cen...In order to solve the problem of low recognition rate of traditional feature extraction operators under low-resolution images, a novel algorithm of expression recognition is proposed, named central oblique average center-symmetric local binary pattern(CS-LBP) with adaptive threshold(ATCS-LBP). Firstly, the features of face images can be extracted by the proposed operator after pretreatment. Secondly, the obtained feature image is divided into blocks. Thirdly, the histogram of each block is computed independently and all histograms can be connected serially to create a final feature vector. Finally, expression classification is achieved by using support vector machine(SVM) classifier. Experimental results on Japanese female facial expression(JAFFE) database show that the proposed algorithm can achieve a recognition rate of 81.9% when the resolution is as low as 16×16, which is much better than that of the traditional feature extraction operators.展开更多
提出了一种鲁棒的图像局部特征区域的描述方法,即IWCS-LTP(Improved weighted center symmetric local trinarypattern)描述子.该方法对图像局部特征区域采用类似SIFT描述子的分块处理,可以使描述子包含更多的结构信息;采用ICS-LTP算子...提出了一种鲁棒的图像局部特征区域的描述方法,即IWCS-LTP(Improved weighted center symmetric local trinarypattern)描述子.该方法对图像局部特征区域采用类似SIFT描述子的分块处理,可以使描述子包含更多的结构信息;采用ICS-LTP算子进行编码,可以在不大量增加描述子维数和计算量的同时对图像的梯度方向信息进行更具体的描述;采用加权纹理谱直方图计算方法可以使描述子包含图像的梯度幅值信息.大量的实验结果验证了该描述子的有效性.展开更多
文摘针对局部二值模式(LBP)特征在低分辨率的人脸图像上识别率较低的问题,提出了一种基于分块中心对称局部二值模式(CS-LBP,center symmetric local binary pattern)和加权主成分分析(PCA)算法的低分辨率人脸识别算法。首先利用分块CS-LBP算子提取低分辨率人脸图像的特征;然后利用加权PCA算子对特征进行降维,从而得到更强的分类特征;最后利用最近邻分类器选出人脸最优分类类别并计算识别率。在ORL人脸库上的实验表明,在人脸图像分辨率下降到(12×10)时,本文算法的识别率仍能达到85.00%,基本满足了实际运用中对识别率的要求,并且降低了运算时间。
基金supported by the National Natural Science Foundation of China(No.61401237)
文摘In order to solve the problem of low recognition rate of traditional feature extraction operators under low-resolution images, a novel algorithm of expression recognition is proposed, named central oblique average center-symmetric local binary pattern(CS-LBP) with adaptive threshold(ATCS-LBP). Firstly, the features of face images can be extracted by the proposed operator after pretreatment. Secondly, the obtained feature image is divided into blocks. Thirdly, the histogram of each block is computed independently and all histograms can be connected serially to create a final feature vector. Finally, expression classification is achieved by using support vector machine(SVM) classifier. Experimental results on Japanese female facial expression(JAFFE) database show that the proposed algorithm can achieve a recognition rate of 81.9% when the resolution is as low as 16×16, which is much better than that of the traditional feature extraction operators.
文摘提出了一种鲁棒的图像局部特征区域的描述方法,即IWCS-LTP(Improved weighted center symmetric local trinarypattern)描述子.该方法对图像局部特征区域采用类似SIFT描述子的分块处理,可以使描述子包含更多的结构信息;采用ICS-LTP算子进行编码,可以在不大量增加描述子维数和计算量的同时对图像的梯度方向信息进行更具体的描述;采用加权纹理谱直方图计算方法可以使描述子包含图像的梯度幅值信息.大量的实验结果验证了该描述子的有效性.