A novel residual-error prediction method based on deep learning with application in lossless image compression is introduced. The proposed method employs machine learning tools to minimise the residual error of the employed prediction tools. Experimental results demonstrate average bitrate savings of 32% over the state-of-the-art in lossless image compression. To the best of the authors' knowledge, this Letter is the first to propose a deep-learning based method for residual-error prediction.
Schiopu, I & Munteanu, A 2018, 'Residual-error prediction based on deep learning for lossless image compression', Electronics Letters, vol. 54, no. 17, pp. 1032-1033. https://doi.org/10.1049/el.2018.0889
Schiopu, I., & Munteanu, A. (2018). Residual-error prediction based on deep learning for lossless image compression. Electronics Letters, 54(17), 1032-1033. https://doi.org/10.1049/el.2018.0889
@article{c1d3c5ca86a6471fb7b8ec7ebb89552f,
title = "Residual-error prediction based on deep learning for lossless image compression",
abstract = "A novel residual-error prediction method based on deep learning with application in lossless image compression is introduced. The proposed method employs machine learning tools to minimise the residual error of the employed prediction tools. Experimental results demonstrate average bitrate savings of 32% over the state-of-the-art in lossless image compression. To the best of the authors' knowledge, this Letter is the first to propose a deep-learning based method for residual-error prediction.",
keywords = "image coding, data compression, learning (artificial intelligence), minimisation, residual-error prediction method, deep-learning based method, lossless image compression, machine learning tools, residual error minimisation, employed prediction tools, bitrate savings",
author = "Ionut Schiopu and Adrian Munteanu",
year = "2018",
month = aug,
day = "23",
doi = "10.1049/el.2018.0889",
language = "English",
volume = "54",
pages = "1032--1033",
journal = "Electronics Letters",
issn = "0013-5194",
publisher = "Institution of Engineering and Technology",
number = "17",
}