基于改进前向反传播神经网络的彩色图像压缩:使用不同距离度量提高图像质量

9th International Conference on Information Technology (ICIT'06) Pub Date : 2006-12-18 DOI:10.1109/ICIT.2006.37

D. Mishra, N. Bose, A. Tolambiya, A. Dwivedi, P. Kandula, Ashiwani Kumar, P. Kalra

{"title":"基于改进前向反传播神经网络的彩色图像压缩:使用不同距离度量提高图像质量","authors":"D. Mishra, N. Bose, A. Tolambiya, A. Dwivedi, P. Kandula, Ashiwani Kumar, P. Kalra","doi":"10.1109/ICIT.2006.37","DOIUrl":null,"url":null,"abstract":"A modified forward-only counterpropagation neural network (MFO-CPN) for color image compression is proposed. It uses several higher-order distance measures for calculating winning node. It also incorporates nonlinear adjustment of learning rates in both the layers. Results with these distance functions are compared. Proposed modifications leads to improvement in the image quality and faster convergence of network.","PeriodicalId":161120,"journal":{"name":"9th International Conference on Information Technology (ICIT'06)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2006-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"14","resultStr":"{\"title\":\"Color Image Compression with Modified Forward-Only Counterpropagation Neural Network: Improvement of the Quality using Different Distance Measures\",\"authors\":\"D. Mishra, N. Bose, A. Tolambiya, A. Dwivedi, P. Kandula, Ashiwani Kumar, P. Kalra\",\"doi\":\"10.1109/ICIT.2006.37\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A modified forward-only counterpropagation neural network (MFO-CPN) for color image compression is proposed. It uses several higher-order distance measures for calculating winning node. It also incorporates nonlinear adjustment of learning rates in both the layers. Results with these distance functions are compared. Proposed modifications leads to improvement in the image quality and faster convergence of network.\",\"PeriodicalId\":161120,\"journal\":{\"name\":\"9th International Conference on Information Technology (ICIT'06)\",\"volume\":\"90 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2006-12-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"14\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"9th International Conference on Information Technology (ICIT'06)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICIT.2006.37\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"9th International Conference on Information Technology (ICIT'06)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIT.2006.37","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 14

摘要

提出了一种改进的纯前向反传播神经网络(MFO-CPN)用于彩色图像压缩。它使用几个高阶距离度量来计算获胜节点。它还结合了两层学习率的非线性调整。比较了这些距离函数的计算结果。改进后的图像质量得到改善，网络收敛速度加快。

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

Color Image Compression with Modified Forward-Only Counterpropagation Neural Network: Improvement of the Quality using Different Distance Measures

A modified forward-only counterpropagation neural network (MFO-CPN) for color image compression is proposed. It uses several higher-order distance measures for calculating winning node. It also incorporates nonlinear adjustment of learning rates in both the layers. Results with these distance functions are compared. Proposed modifications leads to improvement in the image quality and faster convergence of network.

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

9th International Conference on Information Technology (ICIT'06)

自引率

0.00%

发文量