Proximity Based Object Segmentation in Natural Color Images Using the Level Set Method

Tran Lan Anh NGUYEN; Gueesang LEE

doi:10.1587/transfun.E96.A.1744

Proximity Based Object Segmentation in Natural Color Images Using the Level Set Method

Tran Lan Anh NGUYEN, Gueesang LEE

Full Text Views

0

Cite this

Summary :

Segmenting indicated objects from natural color images remains a challenging problem for researches of image processing. In this paper, a novel level set approach is presented, to address this issue. In this segmentation algorithm, a contour that lies inside a particular region of the concerned object is first initialized by a user. The level set model is then applied, to extract the object of arbitrary shape and size containing this initial region. Constrained on the position of the initial contour, our proposed framework combines two particular energy terms, namely local and global energy, in its energy functional, to control movement of the contour toward object boundaries. These energy terms are mainly based on graph partitioning active contour models and Bhattacharyya flow, respectively. Its flow describes dissimilarities, measuring correlative relationships between the region of interest and surroundings. The experimental results obtained from our image collection show that the suggested method yields accurate and good performance, or better than a number of segmentation algorithms, when applied to various natural images.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E96-A No.8 pp.1744-1751

Publication Date: 2013/08/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E96.A.1744

Type of Manuscript: PAPER

Category: Image

Authors

Tran Lan Anh NGUYEN
Chonnam National University
Gueesang LEE
Chonnam National University

Keyword

object-of-interest segmentation, Bhattacharyya flow, graph partitioning, level set, natural color image

Cite this

Copy

Tran Lan Anh NGUYEN, Gueesang LEE, "Proximity Based Object Segmentation in Natural Color Images Using the Level Set Method" in IEICE TRANSACTIONS on Fundamentals, vol. E96-A, no. 8, pp. 1744-1751, August 2013, doi: 10.1587/transfun.E96.A.1744.
Abstract: Segmenting indicated objects from natural color images remains a challenging problem for researches of image processing. In this paper, a novel level set approach is presented, to address this issue. In this segmentation algorithm, a contour that lies inside a particular region of the concerned object is first initialized by a user. The level set model is then applied, to extract the object of arbitrary shape and size containing this initial region. Constrained on the position of the initial contour, our proposed framework combines two particular energy terms, namely local and global energy, in its energy functional, to control movement of the contour toward object boundaries. These energy terms are mainly based on graph partitioning active contour models and Bhattacharyya flow, respectively. Its flow describes dissimilarities, measuring correlative relationships between the region of interest and surroundings. The experimental results obtained from our image collection show that the suggested method yields accurate and good performance, or better than a number of segmentation algorithms, when applied to various natural images.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E96.A.1744/_p

Copy

@ARTICLE{e96-a_8_1744,
author={Tran Lan Anh NGUYEN, Gueesang LEE, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Proximity Based Object Segmentation in Natural Color Images Using the Level Set Method},
year={2013},
volume={E96-A},
number={8},
pages={1744-1751},
abstract={Segmenting indicated objects from natural color images remains a challenging problem for researches of image processing. In this paper, a novel level set approach is presented, to address this issue. In this segmentation algorithm, a contour that lies inside a particular region of the concerned object is first initialized by a user. The level set model is then applied, to extract the object of arbitrary shape and size containing this initial region. Constrained on the position of the initial contour, our proposed framework combines two particular energy terms, namely local and global energy, in its energy functional, to control movement of the contour toward object boundaries. These energy terms are mainly based on graph partitioning active contour models and Bhattacharyya flow, respectively. Its flow describes dissimilarities, measuring correlative relationships between the region of interest and surroundings. The experimental results obtained from our image collection show that the suggested method yields accurate and good performance, or better than a number of segmentation algorithms, when applied to various natural images.},
keywords={},
doi={10.1587/transfun.E96.A.1744},
ISSN={1745-1337},
month={August},}

Copy

TY - JOUR
TI - Proximity Based Object Segmentation in Natural Color Images Using the Level Set Method
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1744
EP - 1751
AU - Tran Lan Anh NGUYEN
AU - Gueesang LEE
PY - 2013
DO - 10.1587/transfun.E96.A.1744
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E96-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 2013
AB - Segmenting indicated objects from natural color images remains a challenging problem for researches of image processing. In this paper, a novel level set approach is presented, to address this issue. In this segmentation algorithm, a contour that lies inside a particular region of the concerned object is first initialized by a user. The level set model is then applied, to extract the object of arbitrary shape and size containing this initial region. Constrained on the position of the initial contour, our proposed framework combines two particular energy terms, namely local and global energy, in its energy functional, to control movement of the contour toward object boundaries. These energy terms are mainly based on graph partitioning active contour models and Bhattacharyya flow, respectively. Its flow describes dissimilarities, measuring correlative relationships between the region of interest and surroundings. The experimental results obtained from our image collection show that the suggested method yields accurate and good performance, or better than a number of segmentation algorithms, when applied to various natural images.
ER -