Invariant and Perceptually Consistent Texture Mapping for Content-Based Image Retrieval

Huizhong Long; Chee-Wee Tan; Wee Kheng Leow

doi:10.1109/ICIP.2001.958438

Invariant and Perceptually Consistent Texture Mapping for Content-Based Image Retrieval

Huizhong Long, Chee-Wee Tan, Wee Kheng Leow

National University of Singapore

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Abstract

Texture is an important visual feature for content-based image retrieval. An ideal content-based retrieval system should compare images in its database with the query in a manner that is consistent with human's perception of visual similarity. Moreover, texture matching should be invariant to texture scale and orientation because the same texture can appear in the images in varying scales and orientations. In practice, however, texture similarity computed using computational texture features is not necessarily consistent with human's perception. This paper presents a method of mapping texture features into a texture space that is scale and orientation invariant, and at the same time, consistent with human's perception. Test results show that this method achieves a better retrieval performance than methods that are not invariant and not perceptually consistent

Originalsprog	Engelsk
Titel	Proceedings of the 2001 International Conference on Image Processing. ICIP 2001. Vol. 2
Antal sider	4
Udgivelsessted	Los Alamitos, CA
Forlag	IEEE
Publikationsdato	2001
Sider	117-120
ISBN (Trykt)	0780367251
DOI	https://doi.org/10.1109/ICIP.2001.958438
Status	Udgivet - 2001
Udgivet eksternt	Ja
Begivenhed	International Conference on Image Processing 2001 - Thessaloniki, Grækenland Varighed: 7 okt. 2001 → 10 okt. 2001 Konferencens nummer: 1 http://conferences.visionbib.com/2001/icip-10-01-call.pdf

Konference

Konference	International Conference on Image Processing 2001
Nummer	1
Land/Område	Grækenland
By	Thessaloniki
Periode	07/10/2001 → 10/10/2001
Internetadresse	http://conferences.visionbib.com/2001/icip-10-01-call.pdf

Emneord

Content-based retrieval
Image matching
Image texture
Neural nets
Visual databases
Visual perception

Adgang til dokumentet

10.1109/ICIP.2001.958438Licens: Ikke-specificeret

Handle.net

Persistent link

Citationsformater

@inproceedings{347da83b9c5d417080406a75930565d2,

title = "Invariant and Perceptually Consistent Texture Mapping for Content-Based Image Retrieval",

abstract = "Texture is an important visual feature for content-based image retrieval. An ideal content-based retrieval system should compare images in its database with the query in a manner that is consistent with human's perception of visual similarity. Moreover, texture matching should be invariant to texture scale and orientation because the same texture can appear in the images in varying scales and orientations. In practice, however, texture similarity computed using computational texture features is not necessarily consistent with human's perception. This paper presents a method of mapping texture features into a texture space that is scale and orientation invariant, and at the same time, consistent with human's perception. Test results show that this method achieves a better retrieval performance than methods that are not invariant and not perceptually consistent",

keywords = "Content-based retrieval, Image matching, Image texture, Neural nets, Visual databases, Visual perception",

author = "Huizhong Long and Chee-Wee Tan and Leow, {Wee Kheng}",

year = "2001",

doi = "10.1109/ICIP.2001.958438",

language = "English",

isbn = "0780367251",

pages = "117--120",

booktitle = "Proceedings of the 2001 International Conference on Image Processing. ICIP 2001. Vol. 2",

publisher = "IEEE",

address = "United States",

note = "International Conference on Image Processing 2001 ; Conference date: 07-10-2001 Through 10-10-2001",

url = "http://conferences.visionbib.com/2001/icip-10-01-call.pdf",

}

Long, H, Tan, C-W & Leow, WK 2001, Invariant and Perceptually Consistent Texture Mapping for Content-Based Image Retrieval. i Proceedings of the 2001 International Conference on Image Processing. ICIP 2001. Vol. 2. IEEE, Los Alamitos, CA, s. 117-120, International Conference on Image Processing 2001, Thessaloniki, Grækenland, 07/10/2001. https://doi.org/10.1109/ICIP.2001.958438

Invariant and Perceptually Consistent Texture Mapping for Content-Based Image Retrieval. / Long, Huizhong; Tan, Chee-Wee; Leow, Wee Kheng.
Proceedings of the 2001 International Conference on Image Processing. ICIP 2001. Vol. 2. Los Alamitos, CA: IEEE, 2001. s. 117-120.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - Invariant and Perceptually Consistent Texture Mapping for Content-Based Image Retrieval

AU - Long, Huizhong

AU - Tan, Chee-Wee

AU - Leow, Wee Kheng

N1 - Conference code: 1

PY - 2001

Y1 - 2001

N2 - Texture is an important visual feature for content-based image retrieval. An ideal content-based retrieval system should compare images in its database with the query in a manner that is consistent with human's perception of visual similarity. Moreover, texture matching should be invariant to texture scale and orientation because the same texture can appear in the images in varying scales and orientations. In practice, however, texture similarity computed using computational texture features is not necessarily consistent with human's perception. This paper presents a method of mapping texture features into a texture space that is scale and orientation invariant, and at the same time, consistent with human's perception. Test results show that this method achieves a better retrieval performance than methods that are not invariant and not perceptually consistent

AB - Texture is an important visual feature for content-based image retrieval. An ideal content-based retrieval system should compare images in its database with the query in a manner that is consistent with human's perception of visual similarity. Moreover, texture matching should be invariant to texture scale and orientation because the same texture can appear in the images in varying scales and orientations. In practice, however, texture similarity computed using computational texture features is not necessarily consistent with human's perception. This paper presents a method of mapping texture features into a texture space that is scale and orientation invariant, and at the same time, consistent with human's perception. Test results show that this method achieves a better retrieval performance than methods that are not invariant and not perceptually consistent

KW - Content-based retrieval

KW - Image matching

KW - Image texture

KW - Neural nets

KW - Visual databases

KW - Visual perception

U2 - 10.1109/ICIP.2001.958438

DO - 10.1109/ICIP.2001.958438

M3 - Article in proceedings

SN - 0780367251

SP - 117

EP - 120

BT - Proceedings of the 2001 International Conference on Image Processing. ICIP 2001. Vol. 2

PB - IEEE

CY - Los Alamitos, CA

T2 - International Conference on Image Processing 2001

Y2 - 7 October 2001 through 10 October 2001

ER -