A set of novel textural features based on 3D co-occurrence matrix for content-based image retrieval

Tao Dacheng; Li Xuelong; Yuan Yuan; Yu Nenghai; Liu Zhengkai; Tang Xiao-Ou

doi:10.1109/ICIF.2002.1020979

A set of novel textural features based on 3D co-occurrence matrix for content-based image retrieval

Tao Dacheng, Li Xuelong, Yuan Yuan, Yu Nenghai, Liu Zhengkai, Tang Xiao-Ou

Research output: Contribution to conference › Paper › peer-review

12 Scopus citations

Abstract

This paper presents a set of novel texture features for content-based image retrieval (CBIR). CBIR require new algorithms for the automated extraction and indexing of salient image features, while texture features provide one important cue for the visual perception and discrimination of image content, so they are always one of the most popular representations in CBIR. The proposed features are based on the 3D co-occurrence matrix, and preliminary results show they are much better than traditional texture features. In this paper, experiments are made on an image database with 25000 images.

Original language	English
Pages	1403-1407
Number of pages	5
DOIs	https://doi.org/10.1109/ICIF.2002.1020979
State	Published - 2002
Externally published	Yes
Event	5th International Conference on Information Fusion, FUSION 2002 - Annapolis, MD, United States Duration: 8 Jul 2002 → 11 Jul 2002

Conference

Conference	5th International Conference on Information Fusion, FUSION 2002
Country/Territory	United States
City	Annapolis, MD
Period	8/07/02 → 11/07/02

Keywords

3D Co-occurrence matrix
Content-Based Image Retrieval
Image Database
Texture features

Access to Document

10.1109/ICIF.2002.1020979

Cite this

@conference{cf39a80ef1c744c18db409de34e6d0ae,

title = "A set of novel textural features based on 3D co-occurrence matrix for content-based image retrieval",

abstract = "This paper presents a set of novel texture features for content-based image retrieval (CBIR). CBIR require new algorithms for the automated extraction and indexing of salient image features, while texture features provide one important cue for the visual perception and discrimination of image content, so they are always one of the most popular representations in CBIR. The proposed features are based on the 3D co-occurrence matrix, and preliminary results show they are much better than traditional texture features. In this paper, experiments are made on an image database with 25000 images.",

keywords = "3D Co-occurrence matrix, Content-Based Image Retrieval, Image Database, Texture features",

author = "Tao Dacheng and Li Xuelong and Yuan Yuan and Yu Nenghai and Liu Zhengkai and Tang Xiao-Ou",

year = "2002",

doi = "10.1109/ICIF.2002.1020979",

language = "英语",

pages = "1403--1407",

note = "5th International Conference on Information Fusion, FUSION 2002 ; Conference date: 08-07-2002 Through 11-07-2002",

}

TY - CONF

T1 - A set of novel textural features based on 3D co-occurrence matrix for content-based image retrieval

AU - Dacheng, Tao

AU - Xuelong, Li

AU - Yuan, Yuan

AU - Nenghai, Yu

AU - Zhengkai, Liu

AU - Xiao-Ou, Tang

PY - 2002

Y1 - 2002

N2 - This paper presents a set of novel texture features for content-based image retrieval (CBIR). CBIR require new algorithms for the automated extraction and indexing of salient image features, while texture features provide one important cue for the visual perception and discrimination of image content, so they are always one of the most popular representations in CBIR. The proposed features are based on the 3D co-occurrence matrix, and preliminary results show they are much better than traditional texture features. In this paper, experiments are made on an image database with 25000 images.

AB - This paper presents a set of novel texture features for content-based image retrieval (CBIR). CBIR require new algorithms for the automated extraction and indexing of salient image features, while texture features provide one important cue for the visual perception and discrimination of image content, so they are always one of the most popular representations in CBIR. The proposed features are based on the 3D co-occurrence matrix, and preliminary results show they are much better than traditional texture features. In this paper, experiments are made on an image database with 25000 images.

KW - 3D Co-occurrence matrix

KW - Content-Based Image Retrieval

KW - Image Database

KW - Texture features

UR - http://www.scopus.com/inward/record.url?scp=84891083398&partnerID=8YFLogxK

U2 - 10.1109/ICIF.2002.1020979

DO - 10.1109/ICIF.2002.1020979

M3 - 论文

AN - SCOPUS:84891083398

SP - 1403

EP - 1407

T2 - 5th International Conference on Information Fusion, FUSION 2002

Y2 - 8 July 2002 through 11 July 2002

ER -

A set of novel textural features based on 3D co-occurrence matrix for content-based image retrieval

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this