Zeng, Xunxun, Chen, Fei, Wang, Meiqing and Lai, Choi-Hong ORCID: 0000-0002-7558-6398 (2018) Circulant dissimilarity based shape registration for object segmentation. International Journal of Computer Mathematics. ISSN 0020-7160 (Print), 1029-0265 (Online) (doi:https://doi.org/10.1080/00207160.2018.1445236)

Preview

PDF (Author Accepted Manuscript) 19585 LAI_Circulant_Dissimilarity_Based_Shape_Registration_for_Object_Segmentation_2018.pdf - Accepted Version Download (1MB) | Preview

Abstract

A shape prior based object segmentation is developed in this paper by using a shape transformation distance to constrain object contour evolution. In the proposed algorithm, the transformation distance measures the dissimilarity between two unaligned shapes by cyclic shift, which is called “circulant dissimilarity”. This dissimilarity with respect to translation and rotation of the object shape is represented by circular convolution, which could be efficiently computed by using fast Fourier transform. Given a set of training shapes, the kernel density estimate is adopted to model shape prior. By integrating low-level image feature, high-level shape prior and transformation distance, a variational segmentation model is proposed to solve the transformation invariance of shape prior. Numerical experiments demonstrate that circulant dissimilarity based shape registration outperforms the iterative optimization on explicit pose parameters, and show promising results and highlight the potential of the method for object registration
and segmentation.

Item Type:	Article
Additional Information:	Accepted 21 Feb 2018, Accepted author version posted online: 26 Feb 2018, Published online: 11 Mar 2018
Uncontrolled Keywords:	Segmentation, Circulant dissimilarity, Shape prior, Kernel density estimation, Level set.
Subjects:	Q Science > QA Mathematics
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS) Faculty of Engineering & Science
Last Modified:	04 Mar 2022 13:07
URI:	http://gala.gre.ac.uk/id/eprint/19585

Actions (login required)

View Item

Downloads