An image retrieval algorithm using independent edge self-reinforcement and integrated salient edge matching

Jun Wei Han; Lei Guo

doi:10.1117/12.476248

An image retrieval algorithm using independent edge self-reinforcement and integrated salient edge matching

Jun Wei Han, Lei Guo

School of Automation

Research output: Contribution to journal › Conference article › peer-review

Abstract

Digital image retrieval systems allow sophisticated querying and searching by image contents. Since 1990's, Content-Based Image Retrieval (CBIR) has attracted great research attention. In this paper, we propose a new approach for shape-based image retrieval. We perform an independent edge self-reinforcement algorithm on the edge map to yield the salient edges. The content of a salient edge is characterized by its low-level features, including length, rotation angle histogram and corner frequency. Then, the image similarity measure are based on the EMD (Earth Mover's Distance), named as integrated salient edge matching in this article. Preliminary experimental results on a database containing 7000 images demonstrate that the proposed method is promising.

Original language	English
Pages (from-to)	33-43
Number of pages	11
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5021
DOIs	https://doi.org/10.1117/12.476248
State	Published - 2003
Event	Storage and Retrieval for Media Databases 2003 - Santa Clara, CA, United States Duration: 22 Jan 2003 → 23 Jan 2003

Keywords

Content-based image retrieval
EMD
Independent edge self-reinforcement
Salient edges
Shape

Access to Document

10.1117/12.476248

Cite this

@article{a70e51b3de7040aba8338fb7508d1ec4,

title = "An image retrieval algorithm using independent edge self-reinforcement and integrated salient edge matching",

abstract = "Digital image retrieval systems allow sophisticated querying and searching by image contents. Since 1990's, Content-Based Image Retrieval (CBIR) has attracted great research attention. In this paper, we propose a new approach for shape-based image retrieval. We perform an independent edge self-reinforcement algorithm on the edge map to yield the salient edges. The content of a salient edge is characterized by its low-level features, including length, rotation angle histogram and corner frequency. Then, the image similarity measure are based on the EMD (Earth Mover's Distance), named as integrated salient edge matching in this article. Preliminary experimental results on a database containing 7000 images demonstrate that the proposed method is promising.",

keywords = "Content-based image retrieval, EMD, Independent edge self-reinforcement, Salient edges, Shape",

author = "Han, {Jun Wei} and Lei Guo",

year = "2003",

doi = "10.1117/12.476248",

language = "英语",

volume = "5021",

pages = "33--43",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Storage and Retrieval for Media Databases 2003 ; Conference date: 22-01-2003 Through 23-01-2003",

}

TY - JOUR

T1 - An image retrieval algorithm using independent edge self-reinforcement and integrated salient edge matching

AU - Han, Jun Wei

AU - Guo, Lei

PY - 2003

Y1 - 2003

N2 - Digital image retrieval systems allow sophisticated querying and searching by image contents. Since 1990's, Content-Based Image Retrieval (CBIR) has attracted great research attention. In this paper, we propose a new approach for shape-based image retrieval. We perform an independent edge self-reinforcement algorithm on the edge map to yield the salient edges. The content of a salient edge is characterized by its low-level features, including length, rotation angle histogram and corner frequency. Then, the image similarity measure are based on the EMD (Earth Mover's Distance), named as integrated salient edge matching in this article. Preliminary experimental results on a database containing 7000 images demonstrate that the proposed method is promising.

AB - Digital image retrieval systems allow sophisticated querying and searching by image contents. Since 1990's, Content-Based Image Retrieval (CBIR) has attracted great research attention. In this paper, we propose a new approach for shape-based image retrieval. We perform an independent edge self-reinforcement algorithm on the edge map to yield the salient edges. The content of a salient edge is characterized by its low-level features, including length, rotation angle histogram and corner frequency. Then, the image similarity measure are based on the EMD (Earth Mover's Distance), named as integrated salient edge matching in this article. Preliminary experimental results on a database containing 7000 images demonstrate that the proposed method is promising.

KW - Content-based image retrieval

KW - EMD

KW - Independent edge self-reinforcement

KW - Salient edges

KW - Shape

UR - http://www.scopus.com/inward/record.url?scp=0038732691&partnerID=8YFLogxK

U2 - 10.1117/12.476248

DO - 10.1117/12.476248

M3 - 会议文章

AN - SCOPUS:0038732691

SN - 0277-786X

VL - 5021

SP - 33

EP - 43

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Storage and Retrieval for Media Databases 2003

Y2 - 22 January 2003 through 23 January 2003

ER -

An image retrieval algorithm using independent edge self-reinforcement and integrated salient edge matching

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this