Utilizing venation features for efficient leaf image retrieval

JinKyu Park, Een Jun Hwang, Yunyoung Nam

Research output: Contribution to journalArticle

46 Citations (Scopus)

Abstract

Most Content-Based Image Retrieval systems use image features such as textures, colors, and shapes. However, in the case of a leaf image, it is not appropriate to rely on color or texture features only as such features are very similar in most leaves. In this paper, we propose a new and effective leaf image retrieval scheme. In this scheme, we first analyze leaf venation which we use for leaf categorization. We then extract and utilize leaf shape features to find similar leaves from the already categorized group in a leaf database. The venation of a leaf corresponds to the blood vessels in organisms. Leaf venations are represented using points selected by a curvature scale scope corner detection method on the venation image. The selected points are then categorized by calculating the density of feature points using a non-parametric estimation density. We show this technique's effectiveness by performing several experiments on a prototype system.

Original languageEnglish
Pages (from-to)71-82
Number of pages12
JournalJournal of Systems and Software
Volume81
Issue number1
DOIs
Publication statusPublished - 2008 Jan 1

Fingerprint

Image retrieval
Textures
Color
Blood vessels
Experiments

Keywords

  • CBIR
  • Classification
  • Leaf image retrieval
  • Parzen window
  • Venation

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Software

Cite this

Utilizing venation features for efficient leaf image retrieval. / Park, JinKyu; Hwang, Een Jun; Nam, Yunyoung.

In: Journal of Systems and Software, Vol. 81, No. 1, 01.01.2008, p. 71-82.

Research output: Contribution to journalArticle

@article{00cf2daa8e3546edb8122523978dc946,
title = "Utilizing venation features for efficient leaf image retrieval",
abstract = "Most Content-Based Image Retrieval systems use image features such as textures, colors, and shapes. However, in the case of a leaf image, it is not appropriate to rely on color or texture features only as such features are very similar in most leaves. In this paper, we propose a new and effective leaf image retrieval scheme. In this scheme, we first analyze leaf venation which we use for leaf categorization. We then extract and utilize leaf shape features to find similar leaves from the already categorized group in a leaf database. The venation of a leaf corresponds to the blood vessels in organisms. Leaf venations are represented using points selected by a curvature scale scope corner detection method on the venation image. The selected points are then categorized by calculating the density of feature points using a non-parametric estimation density. We show this technique's effectiveness by performing several experiments on a prototype system.",
keywords = "CBIR, Classification, Leaf image retrieval, Parzen window, Venation",
author = "JinKyu Park and Hwang, {Een Jun} and Yunyoung Nam",
year = "2008",
month = "1",
day = "1",
doi = "10.1016/j.jss.2007.05.001",
language = "English",
volume = "81",
pages = "71--82",
journal = "Journal of Systems and Software",
issn = "0164-1212",
publisher = "Elsevier Inc.",
number = "1",

}

TY - JOUR

T1 - Utilizing venation features for efficient leaf image retrieval

AU - Park, JinKyu

AU - Hwang, Een Jun

AU - Nam, Yunyoung

PY - 2008/1/1

Y1 - 2008/1/1

N2 - Most Content-Based Image Retrieval systems use image features such as textures, colors, and shapes. However, in the case of a leaf image, it is not appropriate to rely on color or texture features only as such features are very similar in most leaves. In this paper, we propose a new and effective leaf image retrieval scheme. In this scheme, we first analyze leaf venation which we use for leaf categorization. We then extract and utilize leaf shape features to find similar leaves from the already categorized group in a leaf database. The venation of a leaf corresponds to the blood vessels in organisms. Leaf venations are represented using points selected by a curvature scale scope corner detection method on the venation image. The selected points are then categorized by calculating the density of feature points using a non-parametric estimation density. We show this technique's effectiveness by performing several experiments on a prototype system.

AB - Most Content-Based Image Retrieval systems use image features such as textures, colors, and shapes. However, in the case of a leaf image, it is not appropriate to rely on color or texture features only as such features are very similar in most leaves. In this paper, we propose a new and effective leaf image retrieval scheme. In this scheme, we first analyze leaf venation which we use for leaf categorization. We then extract and utilize leaf shape features to find similar leaves from the already categorized group in a leaf database. The venation of a leaf corresponds to the blood vessels in organisms. Leaf venations are represented using points selected by a curvature scale scope corner detection method on the venation image. The selected points are then categorized by calculating the density of feature points using a non-parametric estimation density. We show this technique's effectiveness by performing several experiments on a prototype system.

KW - CBIR

KW - Classification

KW - Leaf image retrieval

KW - Parzen window

KW - Venation

UR - http://www.scopus.com/inward/record.url?scp=35848949558&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35848949558&partnerID=8YFLogxK

U2 - 10.1016/j.jss.2007.05.001

DO - 10.1016/j.jss.2007.05.001

M3 - Article

VL - 81

SP - 71

EP - 82

JO - Journal of Systems and Software

JF - Journal of Systems and Software

SN - 0164-1212

IS - 1

ER -