{"title":"基于SIFT和GMM的复制移动伪造检测","authors":"N. Yadav, Rupal A. Kapdi","doi":"10.1109/NUICONE.2015.7449647","DOIUrl":null,"url":null,"abstract":"Modifying or enhancing an image is ubiquitous but, when enhancement tends to change the interpretation of the image they are termed as an attempt of forgery on digital images. Copy move forgery (CMF) is a simple technique and has a number of well built tools in a number of image enhancement software. CMF detection techniques often tend to establish similarity between copied and pasted region on the same image as both are from same original image. Keypoint and block based techniques are used to determine the CMF. SIFT keypoints are combined with different techniques to accurately localize forgery. High dimensionality of feature vector acts as a bottle neck in SIFT based analysis. We propose a method to detect CMF using SIFT descriptors which are clustered using GMM and segment the obtained suspect region speeding up the analysis.","PeriodicalId":131332,"journal":{"name":"2015 5th Nirma University International Conference on Engineering (NUiCONE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Copy move forgery detection using SIFT and GMM\",\"authors\":\"N. Yadav, Rupal A. Kapdi\",\"doi\":\"10.1109/NUICONE.2015.7449647\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Modifying or enhancing an image is ubiquitous but, when enhancement tends to change the interpretation of the image they are termed as an attempt of forgery on digital images. Copy move forgery (CMF) is a simple technique and has a number of well built tools in a number of image enhancement software. CMF detection techniques often tend to establish similarity between copied and pasted region on the same image as both are from same original image. Keypoint and block based techniques are used to determine the CMF. SIFT keypoints are combined with different techniques to accurately localize forgery. High dimensionality of feature vector acts as a bottle neck in SIFT based analysis. We propose a method to detect CMF using SIFT descriptors which are clustered using GMM and segment the obtained suspect region speeding up the analysis.\",\"PeriodicalId\":131332,\"journal\":{\"name\":\"2015 5th Nirma University International Conference on Engineering (NUiCONE)\",\"volume\":\"33 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 5th Nirma University International Conference on Engineering (NUiCONE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NUICONE.2015.7449647\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 5th Nirma University International Conference on Engineering (NUiCONE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NUICONE.2015.7449647","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Modifying or enhancing an image is ubiquitous but, when enhancement tends to change the interpretation of the image they are termed as an attempt of forgery on digital images. Copy move forgery (CMF) is a simple technique and has a number of well built tools in a number of image enhancement software. CMF detection techniques often tend to establish similarity between copied and pasted region on the same image as both are from same original image. Keypoint and block based techniques are used to determine the CMF. SIFT keypoints are combined with different techniques to accurately localize forgery. High dimensionality of feature vector acts as a bottle neck in SIFT based analysis. We propose a method to detect CMF using SIFT descriptors which are clustered using GMM and segment the obtained suspect region speeding up the analysis.