基于特征脸和LS-SVM分类器的人脸性别分类

提出使用特征脸和最小二乘支持向量机(LS-SVM)分类器相结合进行人脸性别分类.我们首先从训练图像中求得特征脸空间,然后将训练集和测试集图像投影到特征脸空间得到投影系数.使用训练样本投影系数训练LS-SVM分类器,对训练图像和测试图像进行分类试验,同时计算出分类准确率,实验结果表明LS-SVM分类要比其他分类算法有更好的优越性.在实验中我们也使用交叉验证来确定特征脸数目和核函数参数.

Facial Gender Classification Based on Eigenfaces and LS-SVM Classifiers

The techniques of eigenfaces and Least Squares Support Vector Machine(LS-SVM) classifier are combined to categorize gender from facial knowledge in this paper.We will firstly establish the eigenfaces from the training images,and then obtain the projection coefficients for training and testing images in the space spanned by the eigenfaces.The LS-SVM classifiers are built with training coefficients,which are used for classifying training and testing images,and classification accuracy percentage values are calculated.The experiments are implemented with self-made facial images,and the results demonstrate that LS-SVM classification has better performance than the other classification algorithms.In experiments we also use cross validation to determine the number of selected primary components and kernel function parameter.