论文部分内容阅读
人脸识别是一种具有实际应用前景的技术,针对人脸识别过程中特征提取和分类器构建等问题,提出一种基于Gabor滤波器和支持向量机相融合的人脸识别方法。首先收集人脸样本组成图像训练库,并提取人脸图像的Gabor特征,生成人脸识别数据,然后通过支持向量机对人脸图像库进行训练,建立人脸图像的分类器,最后采用ORL人脸库进行测试实验。实验结果表明,与其他人脸识别方法相比,本文方法可以实现更加精准的人脸分类与识别,对人脸识别更具有适用性。
Face recognition is a technique with practical application prospects. In order to solve the problem of feature extraction and classifier construction in face recognition, a face recognition method based on Gabor filter and support vector machine is proposed. First of all, face samples are collected to form a training base of image, and Gabor features of face images are extracted to generate face recognition data. Then the face image database is trained by support vector machine to establish a classifier of face images. Finally, Face library test experiment. Experimental results show that compared with other face recognition methods, this method can achieve more accurate face classification and recognition, and is more suitable for face recognition.