统计成像和复杂性正则化

2000 IEEE International Symposium on Information Theory (Cat. No.00CH37060) Pub Date : 2000-08-01 DOI:10.1109/ISIT.2000.866344

P. Moulin, Juan Liu

{"title":"统计成像和复杂性正则化","authors":"P. Moulin, Juan Liu","doi":"10.1109/ISIT.2000.866344","DOIUrl":null,"url":null,"abstract":"We apply complexity regularization to statistical ill-posed inverse problems in imaging. We formulate a natural distortion measure in image space and develop nonasymptotic bounds on estimation performance in terms of an index of resolvability that characterizes the compressibility of the true image. These bounds extend previous results that were obtained under simpler observational models.","PeriodicalId":108752,"journal":{"name":"2000 IEEE International Symposium on Information Theory (Cat. No.00CH37060)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2000-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"33","resultStr":"{\"title\":\"Statistical imaging and complexity regularization\",\"authors\":\"P. Moulin, Juan Liu\",\"doi\":\"10.1109/ISIT.2000.866344\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We apply complexity regularization to statistical ill-posed inverse problems in imaging. We formulate a natural distortion measure in image space and develop nonasymptotic bounds on estimation performance in terms of an index of resolvability that characterizes the compressibility of the true image. These bounds extend previous results that were obtained under simpler observational models.\",\"PeriodicalId\":108752,\"journal\":{\"name\":\"2000 IEEE International Symposium on Information Theory (Cat. No.00CH37060)\",\"volume\":\"8 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2000-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"33\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2000 IEEE International Symposium on Information Theory (Cat. No.00CH37060)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISIT.2000.866344\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2000 IEEE International Symposium on Information Theory (Cat. No.00CH37060)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISIT.2000.866344","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 33

摘要

将复杂度正则化应用于成像中的统计病态逆问题。我们在图像空间中制定了一个自然失真度量，并根据表征真实图像可压缩性的可分辨性指标开发了估计性能的非渐近界。这些界限扩展了以前在更简单的观测模型下得到的结果。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Statistical imaging and complexity regularization

We apply complexity regularization to statistical ill-posed inverse problems in imaging. We formulate a natural distortion measure in image space and develop nonasymptotic bounds on estimation performance in terms of an index of resolvability that characterizes the compressibility of the true image. These bounds extend previous results that were obtained under simpler observational models.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2000 IEEE International Symposium on Information Theory (Cat. No.00CH37060)

自引率

0.00%

发文量