{"title":"New technique for face recognition based on Singular Value Decomposition (SVD)","authors":"E. Barrah, Said Safi, A. Malaoui","doi":"10.1109/CLOUDTECH.2016.7847684","DOIUrl":null,"url":null,"abstract":"In this paper, we describe a texture analysis which plays an important role in face analysis. Many studies have used texture image to characterize a face. Local Binary Pattern (LBP) coding is a state-of-the-art technique characterized by it's simplicity and efficiency. In the proposed method, we associate Local Binary Pattern with integral image representation, which permits to evaluate the sum of values over rectangular regions, in the Singular Value Decomposition (SVD) domain. Finally, the obtained results, using the proposed method, will be compared with those obtained from other local approaches.","PeriodicalId":133495,"journal":{"name":"2016 2nd International Conference on Cloud Computing Technologies and Applications (CloudTech)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 2nd International Conference on Cloud Computing Technologies and Applications (CloudTech)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CLOUDTECH.2016.7847684","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper, we describe a texture analysis which plays an important role in face analysis. Many studies have used texture image to characterize a face. Local Binary Pattern (LBP) coding is a state-of-the-art technique characterized by it's simplicity and efficiency. In the proposed method, we associate Local Binary Pattern with integral image representation, which permits to evaluate the sum of values over rectangular regions, in the Singular Value Decomposition (SVD) domain. Finally, the obtained results, using the proposed method, will be compared with those obtained from other local approaches.