{"title":"基于ROI像素值直方图的几何攻击非法复制图像搜索方法","authors":"H. Kuroda, K. Imamura, M. Fujimura","doi":"10.1109/UNESST.2014.10","DOIUrl":null,"url":null,"abstract":"It is very difficult to search the ornament attacked image, since added context into the attacked image by ornament is different from original image. In this paper, it is noted that the process of the decorative frame is applied to the peripheral region of the image, we propose introduction of a mask image to be limited to ROI (region of interesting) for image searching. That is, using the mask image, and measuring the histogram of pixel values in the ROI of each search target image and the original image, then calculate the correlation coefficient between the two histograms. In addition, with respect to the rotation and scaling attack any, we propose a method for determining the amount of the attack. Computer simulation results show the validity of proposed algorithm.","PeriodicalId":195062,"journal":{"name":"2014 7th International Conference on u- and e- Service, Science and Technology","volume":"51 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Search Method Using the Pixel Value Histogram of ROI for Illegal Copy Image with Geometric Attacks\",\"authors\":\"H. Kuroda, K. Imamura, M. Fujimura\",\"doi\":\"10.1109/UNESST.2014.10\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"It is very difficult to search the ornament attacked image, since added context into the attacked image by ornament is different from original image. In this paper, it is noted that the process of the decorative frame is applied to the peripheral region of the image, we propose introduction of a mask image to be limited to ROI (region of interesting) for image searching. That is, using the mask image, and measuring the histogram of pixel values in the ROI of each search target image and the original image, then calculate the correlation coefficient between the two histograms. In addition, with respect to the rotation and scaling attack any, we propose a method for determining the amount of the attack. Computer simulation results show the validity of proposed algorithm.\",\"PeriodicalId\":195062,\"journal\":{\"name\":\"2014 7th International Conference on u- and e- Service, Science and Technology\",\"volume\":\"51 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-12-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2014 7th International Conference on u- and e- Service, Science and Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/UNESST.2014.10\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 7th International Conference on u- and e- Service, Science and Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/UNESST.2014.10","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Search Method Using the Pixel Value Histogram of ROI for Illegal Copy Image with Geometric Attacks
It is very difficult to search the ornament attacked image, since added context into the attacked image by ornament is different from original image. In this paper, it is noted that the process of the decorative frame is applied to the peripheral region of the image, we propose introduction of a mask image to be limited to ROI (region of interesting) for image searching. That is, using the mask image, and measuring the histogram of pixel values in the ROI of each search target image and the original image, then calculate the correlation coefficient between the two histograms. In addition, with respect to the rotation and scaling attack any, we propose a method for determining the amount of the attack. Computer simulation results show the validity of proposed algorithm.