A neural network based adaptive non-linear lossless predictive coding technique

S. Marusic, G. Deng
{"title":"A neural network based adaptive non-linear lossless predictive coding technique","authors":"S. Marusic, G. Deng","doi":"10.1109/ISSPA.1999.815757","DOIUrl":null,"url":null,"abstract":"This paper presents an adaptive non-linear method for the predictive coding of images using multilayer perceptrons. By incorporating causal and localised training on the actual data being coded, rather than training separate data, the network weights are continuously updated. This results in a highly adaptive predictor, with localised optimisation based on the stochastic gradient learning. The causal nature of the training means no transmission overhead is required and also enables lossless coding of the images. In addition to the adaptive prediction, the results presented here also incorporate an arithmetic coding scheme, producing results which are better than CALIC and comparable to TMW, the state of the art lossless compression in the literature. This shows that near-optimal results can be obtained with the fundamental concept of adaptive training. The use of a neural network provides a simple means for performing this training.","PeriodicalId":302569,"journal":{"name":"ISSPA '99. Proceedings of the Fifth International Symposium on Signal Processing and its Applications (IEEE Cat. No.99EX359)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1999-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"14","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ISSPA '99. Proceedings of the Fifth International Symposium on Signal Processing and its Applications (IEEE Cat. No.99EX359)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISSPA.1999.815757","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 14

Abstract

This paper presents an adaptive non-linear method for the predictive coding of images using multilayer perceptrons. By incorporating causal and localised training on the actual data being coded, rather than training separate data, the network weights are continuously updated. This results in a highly adaptive predictor, with localised optimisation based on the stochastic gradient learning. The causal nature of the training means no transmission overhead is required and also enables lossless coding of the images. In addition to the adaptive prediction, the results presented here also incorporate an arithmetic coding scheme, producing results which are better than CALIC and comparable to TMW, the state of the art lossless compression in the literature. This shows that near-optimal results can be obtained with the fundamental concept of adaptive training. The use of a neural network provides a simple means for performing this training.
基于神经网络的自适应非线性无损预测编码技术
提出了一种基于多层感知器的自适应非线性图像预测编码方法。通过结合对实际编码数据的因果和局部训练,而不是单独训练数据,网络权重不断更新。这就产生了一个高度自适应的预测器,并基于随机梯度学习进行了局部优化。训练的因果性质意味着不需要传输开销,并且还可以对图像进行无损编码。除了自适应预测之外,本文提出的结果还包括一种算术编码方案,产生的结果优于CALIC,可与文献中最先进的无损压缩TMW相媲美。这表明,在自适应训练的基本概念下,可以获得接近最优的结果。神经网络的使用为执行这种训练提供了一种简单的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信