摘要
文章提出一种PCA+SVM算法优化方法,以小波变换(DWT)为基础,旨在提升人脸识别的精度。先用DWT将原本的人面影像分解成多个子带,再将每个子带进行PCA降维运算,选出最重要的特征子集作为输入资料,最后用SVM分类器来识别人面。实验结果显示,其在ORL人脸数据库中提出的方法,应用前景更好,人脸识别准确率明显提高。
Face recognition technology has been widely used,and PCA+SVM is a commonly used face recognition algorithm with better recognition performance.However,the recognition accuracy of the PCA+SVM algorithm needs to be improved when processing large-scale face data.Therefore,this paper further studies the PCA and SVM algorithms in face recognition to improve recognition rate.A PCA+SVM algorithm optimization method based on Discrete Wavelet Transform(DWT)is proposed to improve the accuracy of face recognition.The original face image is decomposed into multiple subbands by DWT,and each subband is subjected to PCA dimensionality reduction operation.The most important feature subset is selected as input data,and SVM classifier is used to recognize faces.Experimental results show that the proposed method in the ORL face database significantly improves the accuracy of face recognition,which has a better application prospect.
作者
刘敏
Liu Min(Hefei College of Finance and Economics,School of Artificial Intelligence,Hefei,Anhu 230061)
出处
《绥化学院学报》
2023年第9期157-160,共4页
Journal of Suihua University
基金
安徽省高校自然科学研究项目“基于PCA+SVM算法智能访客系统的实现和优化”(2022AH053038)
合肥财经职业学院校级自然科学研究项目“基于PCA人脸识别算法的智能访客系统设计与实现”(XQK202203Z)
