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
Cette lettre propose un nouvel algorithme de segmentation des superpixels basé sur la similarité globale et la transformation des régions de contour. L’idée de base est que les pixels entourés du même contour sont plus susceptibles d’appartenir à la même région d’objet, qui pourrait facilement être regroupée dans le même superpixel. À cette fin, nous utilisons le balayage de contours pour estimer la similarité globale entre les pixels et les centres correspondants. De plus, nous introduisons les informations de gradient du pixel de la carte de transformation de contour pour améliorer la similarité globale du pixel afin de surmonter les contours manquants dans la région floue. Bénéficiant de notre similarité globale, la méthode proposée pourrait adhérer à des limites floues et à faible contraste. Un grand nombre d'expériences sur les ensembles de données BSDS500 et VOC2012 montrent que l'algorithme proposé est plus performant que le SLIC traditionnel.
Bing LUO
Xihua University
Junkai XIONG
Xihua University
Li XU
Xihua University
Zheng PEI
Xihua University
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.
Copier
Bing LUO, Junkai XIONG, Li XU, Zheng PEI, "Superpixel Segmentation Based on Global Similarity and Contour Region Transform" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 3, pp. 716-719, March 2020, doi: 10.1587/transinf.2019EDL8153.
Abstract: This letter proposes a new superpixel segmentation algorithm based on global similarity and contour region transformation. The basic idea is that pixels surrounded by the same contour are more likely to belong to the same object region, which could be easily clustered into the same superpixel. To this end, we use contour scanning to estimate the global similarity between pixels and corresponded centers. In addition, we introduce pixel's gradient information of contour transform map to enhance the pixel's global similarity to overcome the missing contours in blurred region. Benefited from our global similarity, the proposed method could adherent with blurred and low contrast boundaries. A large number of experiments on BSDS500 and VOC2012 datasets show that the proposed algorithm performs better than traditional SLIC.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8153/_p
Copier
@ARTICLE{e103-d_3_716,
author={Bing LUO, Junkai XIONG, Li XU, Zheng PEI, },
journal={IEICE TRANSACTIONS on Information},
title={Superpixel Segmentation Based on Global Similarity and Contour Region Transform},
year={2020},
volume={E103-D},
number={3},
pages={716-719},
abstract={This letter proposes a new superpixel segmentation algorithm based on global similarity and contour region transformation. The basic idea is that pixels surrounded by the same contour are more likely to belong to the same object region, which could be easily clustered into the same superpixel. To this end, we use contour scanning to estimate the global similarity between pixels and corresponded centers. In addition, we introduce pixel's gradient information of contour transform map to enhance the pixel's global similarity to overcome the missing contours in blurred region. Benefited from our global similarity, the proposed method could adherent with blurred and low contrast boundaries. A large number of experiments on BSDS500 and VOC2012 datasets show that the proposed algorithm performs better than traditional SLIC.},
keywords={},
doi={10.1587/transinf.2019EDL8153},
ISSN={1745-1361},
month={March},}
Copier
TY - JOUR
TI - Superpixel Segmentation Based on Global Similarity and Contour Region Transform
T2 - IEICE TRANSACTIONS on Information
SP - 716
EP - 719
AU - Bing LUO
AU - Junkai XIONG
AU - Li XU
AU - Zheng PEI
PY - 2020
DO - 10.1587/transinf.2019EDL8153
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2020
AB - This letter proposes a new superpixel segmentation algorithm based on global similarity and contour region transformation. The basic idea is that pixels surrounded by the same contour are more likely to belong to the same object region, which could be easily clustered into the same superpixel. To this end, we use contour scanning to estimate the global similarity between pixels and corresponded centers. In addition, we introduce pixel's gradient information of contour transform map to enhance the pixel's global similarity to overcome the missing contours in blurred region. Benefited from our global similarity, the proposed method could adherent with blurred and low contrast boundaries. A large number of experiments on BSDS500 and VOC2012 datasets show that the proposed algorithm performs better than traditional SLIC.
ER -