对人脸识别算法进行研究,采用K—L变换计算训练样本特征值及特征向量,得到特征脸向量。进而计算测试样本投影到特征脸子空间的坐标系数.最后使用SVM分类器分类匹配得到识别结果。该系统以ORL人脸库中的人脸图像作为测试样本,实验结果验证该方法可以有效地进行识别。对实际的应用具有一定的参考价值。
Studies face recognition algorithm, obtains the training sample by the K-L transform, obtains face vector, and calculates the coordinate coefficients of feature subspace. SVM is used to classify and identify the results. ORL face datasets are used in order to test the performance of our proposed method. Experimental results show that proposed method can effectively identify different attitude face. This method has been referenced for practical applications.