M. Laadjel, Khalil Zebbiche, F. Kurugullu, A. Bouridane, O. Nibouche
{"title":"Watermarking for Palmprint Image Protection","authors":"M. Laadjel, Khalil Zebbiche, F. Kurugullu, A. Bouridane, O. Nibouche","doi":"10.1109/IMVIP.2009.20","DOIUrl":null,"url":null,"abstract":"systems. This paper introduces a new blind watermarking technique to address the vulnerabilities of a palmprint recognition system against replay attacks. In particular, we focus on protecting the system against changing or submitting a fake palmprint image at the enrollment and/or recognition stage while still not affecting the recognition performance. To achieve this, the watermark is embedded into the palm's region of intersect which inherently makes it robust to common attacks. The origin of the palmprint images is proven by checking the presence of the watermark in the watermarked palmprint image by comparing the Maximum Likelihood (ML) ratio of a given binary hypotheses to a determined threshold based on the statistical model of the watermarked coefficients. The results obtained have shown that using watermarking concept can efficiently protect a palmprint recognition system against replay attacks.","PeriodicalId":179564,"journal":{"name":"2009 13th International Machine Vision and Image Processing Conference","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2009-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 13th International Machine Vision and Image Processing Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IMVIP.2009.20","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
systems. This paper introduces a new blind watermarking technique to address the vulnerabilities of a palmprint recognition system against replay attacks. In particular, we focus on protecting the system against changing or submitting a fake palmprint image at the enrollment and/or recognition stage while still not affecting the recognition performance. To achieve this, the watermark is embedded into the palm's region of intersect which inherently makes it robust to common attacks. The origin of the palmprint images is proven by checking the presence of the watermark in the watermarked palmprint image by comparing the Maximum Likelihood (ML) ratio of a given binary hypotheses to a determined threshold based on the statistical model of the watermarked coefficients. The results obtained have shown that using watermarking concept can efficiently protect a palmprint recognition system against replay attacks.