Image indexing and retrieval based on human perceptual color clustering

Yihong Gong; Guido Proietti; Christos Faloutsos

doi:10.1109/CVPR.1998.698664

Image indexing and retrieval based on human perceptual color clustering

Yihong Gong
, Guido Proietti
, Christos Faloutsos

Carnegie Mellon University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

68 Scopus citations

Abstract

We propose a new image retrieval method based on human perceptual clustering of color images. This color clustering produces for each image a small set of representative colors which captures the color properties of the image, and a small set of sizable contiguous regions which captures the spatial/geometrical properties of the image. The proposed method outperforms the traditional histogram and its improved methods not only with its richer image retrieval capabilities which cover a wider spectrum of user requirements, but also with its powerful indexing scheme which is essential to cater for large scale image databases.

Original language	English
Title of host publication	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher	IEEE Comp Soc
Pages	578-583
Number of pages	6
ISBN (Print)	0818684976
DOIs	https://doi.org/10.1109/CVPR.1998.698664
State	Published - 1998
Externally published	Yes
Event	1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1998 - Santa Barbara, CA, USA Duration: 23 Jun 1998 → 25 Jun 1998

Conference

Conference	1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1998
City	Santa Barbara, CA, USA
Period	23/06/98 → 25/06/98

Access to Document

10.1109/CVPR.1998.698664

Cite this

@inproceedings{fb7aa23050b04781b5ce148aa517e1d0,

title = "Image indexing and retrieval based on human perceptual color clustering",

abstract = "We propose a new image retrieval method based on human perceptual clustering of color images. This color clustering produces for each image a small set of representative colors which captures the color properties of the image, and a small set of sizable contiguous regions which captures the spatial/geometrical properties of the image. The proposed method outperforms the traditional histogram and its improved methods not only with its richer image retrieval capabilities which cover a wider spectrum of user requirements, but also with its powerful indexing scheme which is essential to cater for large scale image databases.",

author = "Yihong Gong and Guido Proietti and Christos Faloutsos",

year = "1998",

doi = "10.1109/CVPR.1998.698664",

language = "英语",

isbn = "0818684976",

pages = "578--583",

booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Comp Soc",

note = "1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1998 ; Conference date: 23-06-1998 Through 25-06-1998",

}

Gong, Y, Proietti, G & Faloutsos, C 1998, Image indexing and retrieval based on human perceptual color clustering. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Comp Soc, pp. 578-583, 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1998, Santa Barbara, CA, USA, 23/06/98. https://doi.org/10.1109/CVPR.1998.698664

TY - GEN

T1 - Image indexing and retrieval based on human perceptual color clustering

AU - Gong, Yihong

AU - Proietti, Guido

AU - Faloutsos, Christos

PY - 1998

Y1 - 1998

N2 - We propose a new image retrieval method based on human perceptual clustering of color images. This color clustering produces for each image a small set of representative colors which captures the color properties of the image, and a small set of sizable contiguous regions which captures the spatial/geometrical properties of the image. The proposed method outperforms the traditional histogram and its improved methods not only with its richer image retrieval capabilities which cover a wider spectrum of user requirements, but also with its powerful indexing scheme which is essential to cater for large scale image databases.

AB - We propose a new image retrieval method based on human perceptual clustering of color images. This color clustering produces for each image a small set of representative colors which captures the color properties of the image, and a small set of sizable contiguous regions which captures the spatial/geometrical properties of the image. The proposed method outperforms the traditional histogram and its improved methods not only with its richer image retrieval capabilities which cover a wider spectrum of user requirements, but also with its powerful indexing scheme which is essential to cater for large scale image databases.

UR - https://www.scopus.com/pages/publications/0032293337

U2 - 10.1109/CVPR.1998.698664

DO - 10.1109/CVPR.1998.698664

M3 - 会议稿件

AN - SCOPUS:0032293337

SN - 0818684976

SP - 578

EP - 583

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

PB - IEEE Comp Soc

T2 - 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1998

Y2 - 23 June 1998 through 25 June 1998

ER -

Image indexing and retrieval based on human perceptual color clustering

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this