An abstract image representation based on Edge Pixel Neighborhood information (EPNI)

Abdolah Chalechale; Alfred Mertins

doi:10.1007/3-540-36087-5_8

An abstract image representation based on Edge Pixel Neighborhood information (EPNI)

Abdolah Chalechale, Alfred Mertins

Institute of Signal Processing

University of Wollongong

Abstract

In this paper we introduce a new abstract image representation based on Edge Pixel Neighborhood Information (EPNI). It is applied in image retrieval problem when user query is a fast drawn, rough example. The representation consists of two main elements. Aneighborhood vector f and a vicinity table v. The former contains the frequencies of edge pixels with similar directions and the latter holds information about neighboring edge directions. An image similarity measure based on EPNI components is also designed and compared with some other measures known from the literature. Experimental results show a good recognition accuracy in a data set containing a wide range of color images.

Original language	English
Title of host publication	EurAsia-ICT 2002: EurAsia-ICT 2002: Information and Communication Technology
Number of pages	8
Publisher	Springer Verlag
Publication date	01.01.2002
Pages	67-74
ISBN (Print)	978-3-540-00028-0
ISBN (Electronic)	978-3-540-36087-2
DOIs	https://doi.org/10.1007/3-540-36087-5_8
Publication status	Published - 01.01.2002
Event	1st EurAsian Conference on Advances in Information and Communication Technology - Shiraz, Iran, Islamic Republic of Duration: 29.10.2002 → 31.10.2002 Conference number: 103444

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/3-540-36087-5_8

Cite this

@inproceedings{1df864ffb8764e20b56503165fde793a,

title = "An abstract image representation based on Edge Pixel Neighborhood information (EPNI)",

abstract = "In this paper we introduce a new abstract image representation based on Edge Pixel Neighborhood Information (EPNI). It is applied in image retrieval problem when user query is a fast drawn, rough example. The representation consists of two main elements. Aneighborhood vector f and a vicinity table v. The former contains the frequencies of edge pixels with similar directions and the latter holds information about neighboring edge directions. An image similarity measure based on EPNI components is also designed and compared with some other measures known from the literature. Experimental results show a good recognition accuracy in a data set containing a wide range of color images.",

author = "Abdolah Chalechale and Alfred Mertins",

year = "2002",

month = jan,

day = "1",

doi = "10.1007/3-540-36087-5_8",

language = "English",

isbn = "978-3-540-00028-0",

series = "Lecture Notes in Computer Science",

publisher = "Springer Verlag",

pages = "67--74",

booktitle = "EurAsia-ICT 2002: EurAsia-ICT 2002: Information and Communication Technology",

note = "1st EurAsian Conference on Advances in Information and Communication Technology , EurAsia-ICT 2002 ; Conference date: 29-10-2002 Through 31-10-2002",

}

Chalechale, A & Mertins, A 2002, An abstract image representation based on Edge Pixel Neighborhood information (EPNI). in EurAsia-ICT 2002: EurAsia-ICT 2002: Information and Communication Technology . Lecture Notes in Computer Science, Springer Verlag, pp. 67-74, 1st EurAsian Conference on Advances in Information and Communication Technology , Shiraz, Iran, Islamic Republic of, 29.10.02. https://doi.org/10.1007/3-540-36087-5_8

An abstract image representation based on Edge Pixel Neighborhood information (EPNI). / Chalechale, Abdolah; Mertins, Alfred.
EurAsia-ICT 2002: EurAsia-ICT 2002: Information and Communication Technology . Springer Verlag, 2002. p. 67-74 (Lecture Notes in Computer Science).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - An abstract image representation based on Edge Pixel Neighborhood information (EPNI)

AU - Chalechale, Abdolah

AU - Mertins, Alfred

N1 - Conference code: 103444

PY - 2002/1/1

Y1 - 2002/1/1

N2 - In this paper we introduce a new abstract image representation based on Edge Pixel Neighborhood Information (EPNI). It is applied in image retrieval problem when user query is a fast drawn, rough example. The representation consists of two main elements. Aneighborhood vector f and a vicinity table v. The former contains the frequencies of edge pixels with similar directions and the latter holds information about neighboring edge directions. An image similarity measure based on EPNI components is also designed and compared with some other measures known from the literature. Experimental results show a good recognition accuracy in a data set containing a wide range of color images.

AB - In this paper we introduce a new abstract image representation based on Edge Pixel Neighborhood Information (EPNI). It is applied in image retrieval problem when user query is a fast drawn, rough example. The representation consists of two main elements. Aneighborhood vector f and a vicinity table v. The former contains the frequencies of edge pixels with similar directions and the latter holds information about neighboring edge directions. An image similarity measure based on EPNI components is also designed and compared with some other measures known from the literature. Experimental results show a good recognition accuracy in a data set containing a wide range of color images.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-2142644864&origin=inward&txGid=b67c186bcbde20eb791f2914cfc158b7

U2 - 10.1007/3-540-36087-5_8

DO - 10.1007/3-540-36087-5_8

M3 - Conference contribution

SN - 978-3-540-00028-0

T3 - Lecture Notes in Computer Science

SP - 67

EP - 74

BT - EurAsia-ICT 2002: EurAsia-ICT 2002: Information and Communication Technology

PB - Springer Verlag

T2 - 1st EurAsian Conference on Advances in Information and Communication Technology

Y2 - 29 October 2002 through 31 October 2002

ER -

An abstract image representation based on Edge Pixel Neighborhood information (EPNI)

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this