{"title":"Geometrically robust image hashing scheme for image authentication","authors":"Yan Wo, Bo Zhang","doi":"10.1109/ICMLC.2012.6359518","DOIUrl":null,"url":null,"abstract":"In this paper, a geometrically robust image hashing scheme based on Polar Complex Exponential Transform(PCET) is proposed. The reported scheme enhances visual image with the response values of SUSAN detector, then performs PCET on the enhanced image to get the moment features which have rotation and scaling invariance. And then the moment features are processed by the rules, derived from SFFS feature selection method, to obtain the intermediate hash. Finally, the intermediate hash is quantized as the final image hash bits with the deterministic adaptive quantizer. Experimental results show that this scheme can tolerate most of the typical image processing manipulations, such as JPEG compression, geometric distortion, blur, addition of noise, and enhancement. Compared with other approaches in literatures, our method is more effective for image authentication in terms of small tampering detection.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"53 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 International Conference on Machine Learning and Cybernetics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMLC.2012.6359518","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, a geometrically robust image hashing scheme based on Polar Complex Exponential Transform(PCET) is proposed. The reported scheme enhances visual image with the response values of SUSAN detector, then performs PCET on the enhanced image to get the moment features which have rotation and scaling invariance. And then the moment features are processed by the rules, derived from SFFS feature selection method, to obtain the intermediate hash. Finally, the intermediate hash is quantized as the final image hash bits with the deterministic adaptive quantizer. Experimental results show that this scheme can tolerate most of the typical image processing manipulations, such as JPEG compression, geometric distortion, blur, addition of noise, and enhancement. Compared with other approaches in literatures, our method is more effective for image authentication in terms of small tampering detection.