Efficient Image Segmentation Preserving Semantic Object Shapes

Hyun Sang PARK; Jong Beom RA

Efficient Image Segmentation Preserving Semantic Object Shapes

Hyun Sang PARK, Jong Beom RA

Full Text Views

0

Cite this

Summary :

Homogeneous but distinct visual objects having low-contrast boundaries are usually merged in most of the segmentation algorithms. To alleviate this problem, an efficient image segmentation algorithm based on a bottom-up approach is proposed by using spatial domain information only. For initial image segmentation, we adopt a new marker extraction algorithm conforming to the human visual system. It generates dense markers in visually complex areas and sparse markers in visually homogeneous areas. Then, two region-merging algorithms are successively applied so that homogeneous visual objects can be represented as simple as possible without destroying low-contrast real boundaries among them. The first one is to remove insignificant regions in a proper merging order. And the second one merges only homogeneous regions, based on ternary region classification. The resultant segmentation describes homogeneous visual objects with few regions while preserving semantic object shapes well. Finally, a size-based region decision procedure may be applied to represent complex visual objects simpler, if their precise semantic contents are not necessary. Experimental results show that the proposed image segmentation algorithm represents homogeneous visual objects with a few regions and describes complex visual objects with a marginal number of regions with well-preserved semantic object shapes.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E82-A No.6 pp.879-886

Publication Date: 1999/06/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Section of Papers Selected from 1998 International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC '98))

Category

Cite this

Copy

Hyun Sang PARK, Jong Beom RA, "Efficient Image Segmentation Preserving Semantic Object Shapes" in IEICE TRANSACTIONS on Fundamentals, vol. E82-A, no. 6, pp. 879-886, June 1999, doi: .
Abstract: Homogeneous but distinct visual objects having low-contrast boundaries are usually merged in most of the segmentation algorithms. To alleviate this problem, an efficient image segmentation algorithm based on a bottom-up approach is proposed by using spatial domain information only. For initial image segmentation, we adopt a new marker extraction algorithm conforming to the human visual system. It generates dense markers in visually complex areas and sparse markers in visually homogeneous areas. Then, two region-merging algorithms are successively applied so that homogeneous visual objects can be represented as simple as possible without destroying low-contrast real boundaries among them. The first one is to remove insignificant regions in a proper merging order. And the second one merges only homogeneous regions, based on ternary region classification. The resultant segmentation describes homogeneous visual objects with few regions while preserving semantic object shapes well. Finally, a size-based region decision procedure may be applied to represent complex visual objects simpler, if their precise semantic contents are not necessary. Experimental results show that the proposed image segmentation algorithm represents homogeneous visual objects with a few regions and describes complex visual objects with a marginal number of regions with well-preserved semantic object shapes.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_6_879/_p

Copy

@ARTICLE{e82-a_6_879,
author={Hyun Sang PARK, Jong Beom RA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Efficient Image Segmentation Preserving Semantic Object Shapes},
year={1999},
volume={E82-A},
number={6},
pages={879-886},
abstract={Homogeneous but distinct visual objects having low-contrast boundaries are usually merged in most of the segmentation algorithms. To alleviate this problem, an efficient image segmentation algorithm based on a bottom-up approach is proposed by using spatial domain information only. For initial image segmentation, we adopt a new marker extraction algorithm conforming to the human visual system. It generates dense markers in visually complex areas and sparse markers in visually homogeneous areas. Then, two region-merging algorithms are successively applied so that homogeneous visual objects can be represented as simple as possible without destroying low-contrast real boundaries among them. The first one is to remove insignificant regions in a proper merging order. And the second one merges only homogeneous regions, based on ternary region classification. The resultant segmentation describes homogeneous visual objects with few regions while preserving semantic object shapes well. Finally, a size-based region decision procedure may be applied to represent complex visual objects simpler, if their precise semantic contents are not necessary. Experimental results show that the proposed image segmentation algorithm represents homogeneous visual objects with a few regions and describes complex visual objects with a marginal number of regions with well-preserved semantic object shapes.},
keywords={},
doi={},
ISSN={},
month={June},}

Copy

TY - JOUR
TI - Efficient Image Segmentation Preserving Semantic Object Shapes
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 879
EP - 886
AU - Hyun Sang PARK
AU - Jong Beom RA
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 1999
AB - Homogeneous but distinct visual objects having low-contrast boundaries are usually merged in most of the segmentation algorithms. To alleviate this problem, an efficient image segmentation algorithm based on a bottom-up approach is proposed by using spatial domain information only. For initial image segmentation, we adopt a new marker extraction algorithm conforming to the human visual system. It generates dense markers in visually complex areas and sparse markers in visually homogeneous areas. Then, two region-merging algorithms are successively applied so that homogeneous visual objects can be represented as simple as possible without destroying low-contrast real boundaries among them. The first one is to remove insignificant regions in a proper merging order. And the second one merges only homogeneous regions, based on ternary region classification. The resultant segmentation describes homogeneous visual objects with few regions while preserving semantic object shapes well. Finally, a size-based region decision procedure may be applied to represent complex visual objects simpler, if their precise semantic contents are not necessary. Experimental results show that the proposed image segmentation algorithm represents homogeneous visual objects with a few regions and describes complex visual objects with a marginal number of regions with well-preserved semantic object shapes.
ER -