Extended Multi WLS Method for Lossless Image Coding

被引：13

作者：

Ulacha, Grzegorz ^{[1
]}

Stasinski, Ryszard ^{[2
]}

Wernik, Cezary ^{[1
]}

机构：

[1] West Pomeranian Univ Technol, Fac Comp Sci & Informat Technol, Ul Zolnierska 49, PL-71210 Szczecin, Poland

[2] Poznan Univ Tech, Dept Informat & Telecommun, Ul Piotrowo 3, PL-60965 Poznan, Poland

来源：

ENTROPY | 2020年 / 22卷 / 09期

关键词：

image coding; lossless coding; arithmetical coder; ADAPTIVE PREDICTION; COMPRESSION; ALGORITHM; SIGNALS; LOSSY; CODER;

D O I：

10.3390/e22090919

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

In this paper, the most efficient (from data compaction point of view) and current image lossless coding method is presented. Being computationally complex, the algorithm is still more time efficient than its main competitors. The presented cascaded method is based on the Weighted Least Square (WLS) technique, with many improvements introduced, e.g., its main stage is followed by a two-step NLMS predictor ended with Context-Dependent Constant Component Removing. The prediction error is coded by a highly efficient binary context arithmetic coder. The performance of the new algorithm is compared to that of other coders for a set of widely used benchmark images.

引用

页数：24

共 64 条

[1] Near-lossless image compression by relaxation-labelled prediction [J].