Abstract: In order to solve the problem which the rate about face recognition sharp declined due to the different age，the add rapid and accurate age estimation can be added to the process.A method is presented for age estimation based on Local Binary Pattern（LBP） and Support Vector Machine（SVM） regression.Firstly，texture feature is extracted from human faces by using LBP operator which is based on the local characteristics；secondly，the PCA method which is based on the overall characteristics is used to reduce the dimension of the vectors about texture feature；and then the support vector machine regression is used to train the vectors and gain the whole age function，so as to establish the corresponding relationship between texture feature vectors and the age.Experimental results show that the method can quickly and effectively estimate the age of the human faces.

Key words: Local Binary Pattern（LBP）, Support Vector Machine（SVM）, age function, age estimation

摘要： 为了解决在人脸识别过程中由于年龄的变化而使人脸识别率急剧下降的问题，可在识别过程中加入快速、准确的年龄估计。提出了一种基于局域二值模式LBP（Local Binary Pattern）与支持向量机SVM（Support Vector Machine）回归相结合的年龄估计方法。对于人脸图像首先采用基于局部纹理特征的LBP算子进行人脸纹理特征提取；然后用基于整体特征的PCA方法对提取出来的纹理特征向量进行降维；最后使用SVM回归进行训练得到全局年龄函数，建立纹理特征向量与年龄之间的对应关系。实验结果表明，这种方法可以快速有效地对人脸图像进行年龄估计。

关键词: 局域二值模式, 支持向量机, 年龄函数, 年龄估计