This paper presents a novel algorithm for performing integrated object segmentation from a single image. Unlike other state of the art methods which focus on either using contour-based or skeleton-based methods, our approach considers the duality of the two representations (contour/skeleton) and an iterative segmentation procedure that alternates between contour recovery and skeleton fitting. The contour recovery extracts the object contour by adopting the skeleton prior, while the skeleton fitting employs the contour to infer the optimal representation of the object shape. In our approach, the object contour can be directly recovered with no iteration if a detected skeleton is given. Although the proposed method is evaluated for human pose segmentation experiments, it can also be applied to other applications.
Cai, L, Wang, F, Enescu, V & Sahli, H 2014, Object Segmentation based on Contour-Skeleton Duality. in International Conference on Patten Recognition (ICPR2014). pp. 2538-2542, 22nd International Conference on Patten Recognition, ICPR 2014, Stockholm, Sweden, 24/08/14.
Cai, L., Wang, F., Enescu, V., & Sahli, H. (2014). Object Segmentation based on Contour-Skeleton Duality. In International Conference on Patten Recognition (ICPR2014) (pp. 2538-2542)
@inproceedings{0a051097055f494faa9e55d047cf2785,
title = "Object Segmentation based on Contour-Skeleton Duality",
abstract = "This paper presents a novel algorithm for performing integrated object segmentation from a single image. Unlike other state of the art methods which focus on either using contour-based or skeleton-based methods, our approach considers the duality of the two representations (contour/skeleton) and an iterative segmentation procedure that alternates between contour recovery and skeleton fitting. The contour recovery extracts the object contour by adopting the skeleton prior, while the skeleton fitting employs the contour to infer the optimal representation of the object shape. In our approach, the object contour can be directly recovered with no iteration if a detected skeleton is given. Although the proposed method is evaluated for human pose segmentation experiments, it can also be applied to other applications.",
keywords = "Object segmentation, Contour-Skeleton duality",
author = "Ling Cai and Fengna Wang and Valentin Enescu and Hichem Sahli",
year = "2014",
language = "English",
pages = "2538--2542",
booktitle = "International Conference on Patten Recognition (ICPR2014)",
note = "22nd International Conference on Patten Recognition, ICPR 2014 ; Conference date: 24-08-2014 Through 28-08-2014",
}