Direct image retrieval in JPEG and JPEG2000

K. M. Au; Ngai Fong Law; W. C. Siu

doi:10.1109/ICIP.2005.1529804

Direct image retrieval in JPEG and JPEG2000

K. M. Au, Ngai Fong Law, W. C. Siu

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

1 Citation (Scopus)

Abstract

Images are often compressed using JPEG or JPEG2000. Many retrieval systems operated in either uncompressed or compressed domains have been proposed. However, retrieving in multiple domains typically involves full decompression for feature analysis in spatial domain. Common features in different domains are thus worth of investigation for direct image indexing. By employing a common subband filtering model, outputs from JPEG and JPEG2000 can be compared directly without having a full decompression. Despite of high compression, similar translation and rotation invariant features can be extracted from these two domains. Simulation results reveal that JPEG and JPEG2000 compressed images can be searched from one another irrespective of the compression ratio. Our experimental studies confirm that retrieval in multiple domains is possible without a full decompression.

Original language	English
Title of host publication	IEEE International Conference on Image Processing 2005, ICIP 2005
Pages	529-532
Number of pages	4
Volume	1
DOIs	https://doi.org/10.1109/ICIP.2005.1529804
Publication status	Published - 1 Dec 2005
Event	IEEE International Conference on Image Processing 2005, ICIP 2005 - Genova, Italy Duration: 11 Sept 2005 → 14 Sept 2005

Conference

Conference	IEEE International Conference on Image Processing 2005, ICIP 2005
Country/Territory	Italy
City	Genova
Period	11/09/05 → 14/09/05

ASJC Scopus subject areas

General Engineering

More information

10.1109/ICIP.2005.1529804

Cite this

@inproceedings{37c0ed6f9147400e9dd4f2f4b7fa215b,

title = "Direct image retrieval in JPEG and JPEG2000",

abstract = "Images are often compressed using JPEG or JPEG2000. Many retrieval systems operated in either uncompressed or compressed domains have been proposed. However, retrieving in multiple domains typically involves full decompression for feature analysis in spatial domain. Common features in different domains are thus worth of investigation for direct image indexing. By employing a common subband filtering model, outputs from JPEG and JPEG2000 can be compared directly without having a full decompression. Despite of high compression, similar translation and rotation invariant features can be extracted from these two domains. Simulation results reveal that JPEG and JPEG2000 compressed images can be searched from one another irrespective of the compression ratio. Our experimental studies confirm that retrieval in multiple domains is possible without a full decompression.",

author = "Au, {K. M.} and Law, {Ngai Fong} and Siu, {W. C.}",

year = "2005",

month = dec,

day = "1",

doi = "10.1109/ICIP.2005.1529804",

language = "English",

isbn = "0780391349",

volume = "1",

pages = "529--532",

booktitle = "IEEE International Conference on Image Processing 2005, ICIP 2005",

note = "IEEE International Conference on Image Processing 2005, ICIP 2005 ; Conference date: 11-09-2005 Through 14-09-2005",

}

TY - GEN

T1 - Direct image retrieval in JPEG and JPEG2000

AU - Au, K. M.

AU - Law, Ngai Fong

AU - Siu, W. C.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Images are often compressed using JPEG or JPEG2000. Many retrieval systems operated in either uncompressed or compressed domains have been proposed. However, retrieving in multiple domains typically involves full decompression for feature analysis in spatial domain. Common features in different domains are thus worth of investigation for direct image indexing. By employing a common subband filtering model, outputs from JPEG and JPEG2000 can be compared directly without having a full decompression. Despite of high compression, similar translation and rotation invariant features can be extracted from these two domains. Simulation results reveal that JPEG and JPEG2000 compressed images can be searched from one another irrespective of the compression ratio. Our experimental studies confirm that retrieval in multiple domains is possible without a full decompression.

AB - Images are often compressed using JPEG or JPEG2000. Many retrieval systems operated in either uncompressed or compressed domains have been proposed. However, retrieving in multiple domains typically involves full decompression for feature analysis in spatial domain. Common features in different domains are thus worth of investigation for direct image indexing. By employing a common subband filtering model, outputs from JPEG and JPEG2000 can be compared directly without having a full decompression. Despite of high compression, similar translation and rotation invariant features can be extracted from these two domains. Simulation results reveal that JPEG and JPEG2000 compressed images can be searched from one another irrespective of the compression ratio. Our experimental studies confirm that retrieval in multiple domains is possible without a full decompression.

UR - http://www.scopus.com/inward/record.url?scp=33749600961&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2005.1529804

DO - 10.1109/ICIP.2005.1529804

M3 - Conference article published in proceeding or book

SN - 0780391349

SN - 9780780391345

VL - 1

SP - 529

EP - 532

BT - IEEE International Conference on Image Processing 2005, ICIP 2005

T2 - IEEE International Conference on Image Processing 2005, ICIP 2005

Y2 - 11 September 2005 through 14 September 2005

ER -

Direct image retrieval in JPEG and JPEG2000

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this