基于PCA算法的人脸匹配技术研究  

Study on Face Matching Technology Based on PCA

作　　者：冯伟 杨春丽 刘峰 刘光宇 程远[3] 周豹 赵恩铭 周维云 赵继强 Feng Wei;Yang Chunli;Liu Feng;Liu Guangyu;Cheng Yuan;Zhou Bao;Zhao Enming;Zhou Weiyun;Zhao Jiqiang(Dali University,Dali,Yunnan 671003,China;Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education,Shanghai Jiao Tong University,Shanghai 200030,China;Unit 32268,PLA,Dali,Yunnan 671003,China)

机构地区：[1]大理大学工程学院,云南大理671003 [2]上海交通大学海洋智能装备与系统教育部实验室,上海200030 [3]中国人民解放军32268部队信息科,云南大理671003

出　　处：《漯河职业技术学院学报》2024年第2期23-27,共5页Journal of Luohe Vocational Technical College

基　　金：国家自然科学基金资助项目(NO.62065001);云南省地方本科高校基础研究联合专项资金项目(202101BA070001-054);云南省中青年学术和技术带头人后备人才项目(202205AC160001);海洋智能装备与系统教育部重点实验室开放基金项目(MIES-2023-02)。

摘　　要：基于PCA算法的人脸匹配是一种常见的计算机视觉技术,主要应用于人脸图像的分类和匹配任务。利用PCA技术对人脸图像进行特征提取和降维处理,将人脸分为测试集和训练集,然后用欧式距离计算测试集中选择的图像和训练集中所有图像的距离,选择距离最短的图像作为人脸匹配结果。实验采集了200张不同拍摄角度和不同表情的人脸图像,对待匹配的人脸图像加入不同程度噪声进行人脸匹配,实验结果显示基于PCA算法的人脸匹配技术,完成匹配的平均时间为1.2494s,人脸图像匹配准确率为97.25%。Face matching based on PCA is a common computer vision technology,which is mainly used in face image classification and matching tasks.Firstly the feature extraction and dimensionality reduction of face imag⁃es are carried out by PCA,and they are divided into test set and training set;then the Euclidean distance is used to calculate the distance between the image selected in the test set and all the images in the training set;fi⁃nally the image with the shortest distance is selected as the face matching result.In the experiment,200 face im⁃ages with different shooting angles and different expressions are collected,and different levels of noise are added to the matched face images for face matching.It is found that the average time to complete the face matching based on PCA is 1.2494 seconds and the accuracy rate of face image matching is 97.25%.

关 键 词：人脸匹配 PCA算法 特征提取 欧式距离 图像噪声 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]