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.
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.
Copy
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
Copy
@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},}
Copy
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 -