{"title":"基于小波去噪估计的灰度图像LSB匹配隐写分析","authors":"Mankun Xu, Tianyun Li, X. Ping","doi":"10.1109/FGCN.2008.57","DOIUrl":null,"url":null,"abstract":"We consider the problem of LSB matching detection in grayscale images which is hard and hot in steganalysis. In this paper, we model the matching embedding as a kind of image degradation caused by some certain pulse additive noise, and use the restored image by wavelet denoising as an estimation of the cover image. The detectors we used are the 1D and 2D adjacency histogram characteristic function center of mass introduced in the literature [8]. We extract the features of the image before and after estimation and classify the cover and stego images with support vector machine. Experimental results show that our method is superior to Ker's calibrated estimation method, especially in low false positive probability.","PeriodicalId":125089,"journal":{"name":"International Conference on Future Generation Communication and Networking","volume":"264 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Steganalysis of LSB Matching Based on Wavelet Denoising Estimation in Grayscale Image\",\"authors\":\"Mankun Xu, Tianyun Li, X. Ping\",\"doi\":\"10.1109/FGCN.2008.57\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We consider the problem of LSB matching detection in grayscale images which is hard and hot in steganalysis. In this paper, we model the matching embedding as a kind of image degradation caused by some certain pulse additive noise, and use the restored image by wavelet denoising as an estimation of the cover image. The detectors we used are the 1D and 2D adjacency histogram characteristic function center of mass introduced in the literature [8]. We extract the features of the image before and after estimation and classify the cover and stego images with support vector machine. Experimental results show that our method is superior to Ker's calibrated estimation method, especially in low false positive probability.\",\"PeriodicalId\":125089,\"journal\":{\"name\":\"International Conference on Future Generation Communication and Networking\",\"volume\":\"264 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Conference on Future Generation Communication and Networking\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/FGCN.2008.57\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Future Generation Communication and Networking","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/FGCN.2008.57","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Steganalysis of LSB Matching Based on Wavelet Denoising Estimation in Grayscale Image
We consider the problem of LSB matching detection in grayscale images which is hard and hot in steganalysis. In this paper, we model the matching embedding as a kind of image degradation caused by some certain pulse additive noise, and use the restored image by wavelet denoising as an estimation of the cover image. The detectors we used are the 1D and 2D adjacency histogram characteristic function center of mass introduced in the literature [8]. We extract the features of the image before and after estimation and classify the cover and stego images with support vector machine. Experimental results show that our method is superior to Ker's calibrated estimation method, especially in low false positive probability.