The pseudo-distance technique for parallel lossless compression of color-mapped images

Basar Koc, Ziya Arnavut, Huseyin Kocak

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Data compression is a challenging process with important practical applications. Specialized techniques for lossy and lossless data compression have been the subject of numerous investigations during last several decades. Previously, we studied the use of the pseudo-distance technique (PDT) in lossless compression of color-mapped images and its parallel implementation. In this paper we present a new technique (PDT2) to improve compression gain of PDT. We also present a parallelized implementation of the new technique, which results in substantial gains in compression time while providing the desired compression efficiency. We demonstrate that on non-dithered images PDT2 outperforms PDT by 22.4% and PNG by 29.3%. On dithered images, PDT2 achieves compression gains of 7.1% over PDT and 23.8% over PNG. We also show that the parallel implementation of PDT2, while compromising compression less than 0.3%, achieves near linear speedup and utilization of Intel Hyper-Threading technology on supported systems improves speedup on average 18%.

Original languageEnglish (US)
JournalComputers and Electrical Engineering
DOIs
StateAccepted/In press - May 15 2014

Fingerprint

Data compression
Color

Keywords

  • BWT
  • Color-mapped images
  • Hyper-Threading
  • Parallel image compression
  • PDT
  • PNG

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering
  • Control and Systems Engineering

Cite this

The pseudo-distance technique for parallel lossless compression of color-mapped images. / Koc, Basar; Arnavut, Ziya; Kocak, Huseyin.

In: Computers and Electrical Engineering, 15.05.2014.

Research output: Contribution to journalArticle

@article{4cf0bc66b81d4aba90642c4e8d5d0672,
title = "The pseudo-distance technique for parallel lossless compression of color-mapped images",
abstract = "Data compression is a challenging process with important practical applications. Specialized techniques for lossy and lossless data compression have been the subject of numerous investigations during last several decades. Previously, we studied the use of the pseudo-distance technique (PDT) in lossless compression of color-mapped images and its parallel implementation. In this paper we present a new technique (PDT2) to improve compression gain of PDT. We also present a parallelized implementation of the new technique, which results in substantial gains in compression time while providing the desired compression efficiency. We demonstrate that on non-dithered images PDT2 outperforms PDT by 22.4{\%} and PNG by 29.3{\%}. On dithered images, PDT2 achieves compression gains of 7.1{\%} over PDT and 23.8{\%} over PNG. We also show that the parallel implementation of PDT2, while compromising compression less than 0.3{\%}, achieves near linear speedup and utilization of Intel Hyper-Threading technology on supported systems improves speedup on average 18{\%}.",
keywords = "BWT, Color-mapped images, Hyper-Threading, Parallel image compression, PDT, PNG",
author = "Basar Koc and Ziya Arnavut and Huseyin Kocak",
year = "2014",
month = "5",
day = "15",
doi = "10.1016/j.compeleceng.2015.01.003",
language = "English (US)",
journal = "Computers and Electrical Engineering",
issn = "0045-7906",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - The pseudo-distance technique for parallel lossless compression of color-mapped images

AU - Koc, Basar

AU - Arnavut, Ziya

AU - Kocak, Huseyin

PY - 2014/5/15

Y1 - 2014/5/15

N2 - Data compression is a challenging process with important practical applications. Specialized techniques for lossy and lossless data compression have been the subject of numerous investigations during last several decades. Previously, we studied the use of the pseudo-distance technique (PDT) in lossless compression of color-mapped images and its parallel implementation. In this paper we present a new technique (PDT2) to improve compression gain of PDT. We also present a parallelized implementation of the new technique, which results in substantial gains in compression time while providing the desired compression efficiency. We demonstrate that on non-dithered images PDT2 outperforms PDT by 22.4% and PNG by 29.3%. On dithered images, PDT2 achieves compression gains of 7.1% over PDT and 23.8% over PNG. We also show that the parallel implementation of PDT2, while compromising compression less than 0.3%, achieves near linear speedup and utilization of Intel Hyper-Threading technology on supported systems improves speedup on average 18%.

AB - Data compression is a challenging process with important practical applications. Specialized techniques for lossy and lossless data compression have been the subject of numerous investigations during last several decades. Previously, we studied the use of the pseudo-distance technique (PDT) in lossless compression of color-mapped images and its parallel implementation. In this paper we present a new technique (PDT2) to improve compression gain of PDT. We also present a parallelized implementation of the new technique, which results in substantial gains in compression time while providing the desired compression efficiency. We demonstrate that on non-dithered images PDT2 outperforms PDT by 22.4% and PNG by 29.3%. On dithered images, PDT2 achieves compression gains of 7.1% over PDT and 23.8% over PNG. We also show that the parallel implementation of PDT2, while compromising compression less than 0.3%, achieves near linear speedup and utilization of Intel Hyper-Threading technology on supported systems improves speedup on average 18%.

KW - BWT

KW - Color-mapped images

KW - Hyper-Threading

KW - Parallel image compression

KW - PDT

KW - PNG

UR - http://www.scopus.com/inward/record.url?scp=84924690872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924690872&partnerID=8YFLogxK

U2 - 10.1016/j.compeleceng.2015.01.003

DO - 10.1016/j.compeleceng.2015.01.003

M3 - Article

JO - Computers and Electrical Engineering

JF - Computers and Electrical Engineering

SN - 0045-7906

ER -