{"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.