The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Objek visual yang homogen tetapi berbeza yang mempunyai sempadan kontras rendah biasanya digabungkan dalam kebanyakan algoritma pembahagian. Untuk mengurangkan masalah ini, algoritma pembahagian imej yang cekap berdasarkan pendekatan bawah ke atas dicadangkan dengan menggunakan maklumat domain spatial sahaja. Untuk pembahagian imej awal, kami menggunakan algoritma pengekstrakan penanda baharu yang mematuhi sistem visual manusia. Ia menghasilkan penanda padat di kawasan visual yang kompleks dan penanda jarang di kawasan visual yang homogen. Kemudian, dua algoritma penggabungan rantau digunakan secara berturut-turut supaya objek visual homogen boleh diwakili semudah mungkin tanpa memusnahkan sempadan nyata kontras rendah di kalangan mereka. Yang pertama ialah mengalih keluar kawasan yang tidak penting dalam susunan penggabungan yang betul. Dan yang kedua menggabungkan hanya kawasan homogen, berdasarkan klasifikasi wilayah ternary. Segmen terhasil menerangkan objek visual homogen dengan beberapa kawasan sambil mengekalkan bentuk objek semantik dengan baik. Akhir sekali, prosedur keputusan wilayah berasaskan saiz boleh digunakan untuk mewakili objek visual kompleks dengan lebih mudah, jika kandungan semantiknya yang tepat tidak diperlukan. Keputusan eksperimen menunjukkan bahawa algoritma pembahagian imej yang dicadangkan mewakili objek visual homogen dengan beberapa kawasan dan menerangkan objek visual yang kompleks dengan bilangan marginal kawasan dengan bentuk objek semantik yang dipelihara dengan baik.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
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
Salinan
@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},}
Salinan
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 -