通过多层符号转换学习纹理概念

[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91 Pub Date : 1991-11-10 DOI:10.1109/TAI.1991.167081

J. Bala, R. Michalski

{"title":"通过多层符号转换学习纹理概念","authors":"J. Bala, R. Michalski","doi":"10.1109/TAI.1991.167081","DOIUrl":null,"url":null,"abstract":"The TEXTRAL system, used for determining structural visual properties of textures through symbolic transformations, is presented. The method consists of two phases: one that extracts information from raw textural images by applying convolutional operators and learns an initial set of rules; and a second that iteratively extracts symbolic information from the transformed representation of initial image and learns another set of rules. The transformed symbolic representation is obtained by applying previously learned rules to a new image location and generating symbolic images based on rule assertions.<<ETX>>","PeriodicalId":371778,"journal":{"name":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","volume":"95 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1991-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Learning textural concepts through multilevel symbolic transformations\",\"authors\":\"J. Bala, R. Michalski\",\"doi\":\"10.1109/TAI.1991.167081\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The TEXTRAL system, used for determining structural visual properties of textures through symbolic transformations, is presented. The method consists of two phases: one that extracts information from raw textural images by applying convolutional operators and learns an initial set of rules; and a second that iteratively extracts symbolic information from the transformed representation of initial image and learns another set of rules. The transformed symbolic representation is obtained by applying previously learned rules to a new image location and generating symbolic images based on rule assertions.<<ETX>>\",\"PeriodicalId\":371778,\"journal\":{\"name\":\"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91\",\"volume\":\"95 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1991-11-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TAI.1991.167081\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TAI.1991.167081","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

提出了TEXTRAL系统，用于通过符号变换确定纹理的结构视觉特性。该方法包括两个阶段:一是通过卷积算子从原始纹理图像中提取信息，并学习一组初始规则;第二步是迭代地从原始图像的变换表示中提取符号信息，并学习另一组规则。将先前学习到的规则应用到新的图像位置，并根据规则断言生成符号图像，从而获得转换后的符号表示。

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

Learning textural concepts through multilevel symbolic transformations

The TEXTRAL system, used for determining structural visual properties of textures through symbolic transformations, is presented. The method consists of two phases: one that extracts information from raw textural images by applying convolutional operators and learns an initial set of rules; and a second that iteratively extracts symbolic information from the transformed representation of initial image and learns another set of rules. The transformed symbolic representation is obtained by applying previously learned rules to a new image location and generating symbolic images based on rule assertions.<>

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

[Proceedings] Third International Conference on Tools for Artificial Intelligence - TAI 91

自引率

0.00%

发文量