基于PCA和SVM的人脸识别研究  

Research on Face Recognition Based on PCA and SVM

作　　者：付康 陈中举[1] 杜友福[1] FU Kang;CHEN Zhong-ju;DU You-fu(Yangtze University ,Jingzhou 434023, China)

机构地区：[1]长江大学,湖北荆州434023

出　　处：《电脑知识与技术》2019年第3期209-211,共3页Computer Knowledge and Technology

摘　　要：针对人脸图像的像素维度太高,不利于机器识别的问题,提出了基于PCA和SVM的人脸识别系统。以LFW数据集为数据源,使用Python编程语言进行测试。对数据进行预处理后,使用PCA算法对图像数据降维,最后利用SVM进行模型的训练与测试,获得实验结果。采用网格搜索的方法获取SVM的最优参数,保证了实验结果的准确性。Aiming at the problem that the pixel dimension of the face image is too high, which is not conducive to machine recognition, a face recognition system based on PCA and SVM is proposed. The LFW data set is used as the data source and the Python programming language is used to test. After preprocessing the data, the PCA algorithm is used to reduce the dimensionality of the image data. Finally, the SVM is used to train and test the model, and the experimental results are obtained. The grid search method is used to obtain the optimal parameters of the SVM, which ensures the accuracy of the experimental results.

关 键 词：PCA SVM 人脸识别 PYTHON 机器学习 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]