Compressed-domain image retrieval based on colour visual patterns

Gerald Schaefer*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Image retrieval and image compression have been typically pursued separately. Only little research has been done on a synthesis of the two by allowing image retrieval to be performed directly in the compressed domain of images without the need to uncompress them first. In this chapter the authors show that such compressed domain image retrieval can indeed be done and lead to effective and efficient retrieval performance. They introduce a novel compression algorithm - colour visual pattern image coding (CVPIC) - and present several retrieval algorithms that operate directly on compressed CVPIC data. Their experiments demonstrate that it is not only possible to realise such midstream content access, but also that the presented techniques outperform standard retrieval techniques such as colour histograms and colour correlograms.

Original languageEnglish
Title of host publicationSemantic mining technologies for multimedia databases
EditorsDacheng Tao, Dong Xu, Xuelong Li
PublisherIGI Global
Pages407-418
Number of pages12
ISBN (Electronic)978-1-605-66-189-6
ISBN (Print)978-1-605-66188-9, 978-1-616-92602-1
DOIs
Publication statusPublished - Dec 2009

Fingerprint

coding
experiment
performance

Cite this

Schaefer, G. (2009). Compressed-domain image retrieval based on colour visual patterns. In D. Tao, D. Xu, & X. Li (Eds.), Semantic mining technologies for multimedia databases (pp. 407-418). IGI Global. https://doi.org/10.4018/978-1-60566-188-9.ch017
Schaefer, Gerald. / Compressed-domain image retrieval based on colour visual patterns. Semantic mining technologies for multimedia databases. editor / Dacheng Tao ; Dong Xu ; Xuelong Li. IGI Global, 2009. pp. 407-418
@inbook{c1c6ada023684958a9292edc178eae99,
title = "Compressed-domain image retrieval based on colour visual patterns",
abstract = "Image retrieval and image compression have been typically pursued separately. Only little research has been done on a synthesis of the two by allowing image retrieval to be performed directly in the compressed domain of images without the need to uncompress them first. In this chapter the authors show that such compressed domain image retrieval can indeed be done and lead to effective and efficient retrieval performance. They introduce a novel compression algorithm - colour visual pattern image coding (CVPIC) - and present several retrieval algorithms that operate directly on compressed CVPIC data. Their experiments demonstrate that it is not only possible to realise such midstream content access, but also that the presented techniques outperform standard retrieval techniques such as colour histograms and colour correlograms.",
author = "Gerald Schaefer",
year = "2009",
month = "12",
doi = "10.4018/978-1-60566-188-9.ch017",
language = "English",
isbn = "978-1-605-66188-9",
pages = "407--418",
editor = "Dacheng Tao and Dong Xu and Xuelong Li",
booktitle = "Semantic mining technologies for multimedia databases",
publisher = "IGI Global",
address = "United States",

}

Schaefer, G 2009, Compressed-domain image retrieval based on colour visual patterns. in D Tao, D Xu & X Li (eds), Semantic mining technologies for multimedia databases. IGI Global, pp. 407-418. https://doi.org/10.4018/978-1-60566-188-9.ch017

Compressed-domain image retrieval based on colour visual patterns. / Schaefer, Gerald.

Semantic mining technologies for multimedia databases. ed. / Dacheng Tao; Dong Xu; Xuelong Li. IGI Global, 2009. p. 407-418.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Compressed-domain image retrieval based on colour visual patterns

AU - Schaefer, Gerald

PY - 2009/12

Y1 - 2009/12

N2 - Image retrieval and image compression have been typically pursued separately. Only little research has been done on a synthesis of the two by allowing image retrieval to be performed directly in the compressed domain of images without the need to uncompress them first. In this chapter the authors show that such compressed domain image retrieval can indeed be done and lead to effective and efficient retrieval performance. They introduce a novel compression algorithm - colour visual pattern image coding (CVPIC) - and present several retrieval algorithms that operate directly on compressed CVPIC data. Their experiments demonstrate that it is not only possible to realise such midstream content access, but also that the presented techniques outperform standard retrieval techniques such as colour histograms and colour correlograms.

AB - Image retrieval and image compression have been typically pursued separately. Only little research has been done on a synthesis of the two by allowing image retrieval to be performed directly in the compressed domain of images without the need to uncompress them first. In this chapter the authors show that such compressed domain image retrieval can indeed be done and lead to effective and efficient retrieval performance. They introduce a novel compression algorithm - colour visual pattern image coding (CVPIC) - and present several retrieval algorithms that operate directly on compressed CVPIC data. Their experiments demonstrate that it is not only possible to realise such midstream content access, but also that the presented techniques outperform standard retrieval techniques such as colour histograms and colour correlograms.

UR - http://www.igi-global.com/gateway/chapter/28843

UR - http://www.scopus.com/inward/record.url?scp=84898528861&partnerID=8YFLogxK

U2 - 10.4018/978-1-60566-188-9.ch017

DO - 10.4018/978-1-60566-188-9.ch017

M3 - Chapter

AN - SCOPUS:84898528861

SN - 978-1-605-66188-9

SN - 978-1-616-92602-1

SP - 407

EP - 418

BT - Semantic mining technologies for multimedia databases

A2 - Tao, Dacheng

A2 - Xu, Dong

A2 - Li, Xuelong

PB - IGI Global

ER -

Schaefer G. Compressed-domain image retrieval based on colour visual patterns. In Tao D, Xu D, Li X, editors, Semantic mining technologies for multimedia databases. IGI Global. 2009. p. 407-418 https://doi.org/10.4018/978-1-60566-188-9.ch017