Xu, Haiping, Wang, Meiqing, Chen, Fei and Lai, Choi-Hong ORCID: 0000-0002-7558-6398 (2018) Image cosegmentation using shape similarity and object discovery scheme. International Journal of Pattern Recognition and Artificial Intelligence, 32 (10):1854026. ISSN 0218-0014 (Print), 1793-6381 (Online) (doi:https://doi.org/10.1142/S0218001418540265)

Preview

PDF (Author Accepted Manuscript) 19587 LAI_Image_Cosegmentation_Using_Shape_Similarity_2018.pdf - Accepted Version Download (3MB) | Preview

Abstract

Image cosegmentation is a newly emerging research area in image processing. It refers to the problem of segmenting the common objects simultaneous in multiple images by utlising the similarity of foreground discovery scheme. The foreground discovery scheme is used to obtain the rough contours of the common objects which are used initial evolution curves. The energy function includes two parts: an intra-image energy and an inter-image energy. The intra-image energy explores the differences between foreground regions and background regions in each image. The inter-image energy is used to explore the similarities of the common objects among target images, which composes of a region color feature energy term and a shape constraint energy term. The region colour feature term indicates the foreground consistency and the background consistency among the images, and the shape constraint energy term allows the global changes of shapes and truncates the local variation caused by misleading features. Experimental results show that the proposed model can improve the accuracy of the image cosegmentation significantly through regularising the changes of shapes.

Item Type:	Article
Additional Information:	The acceptance letter was received on 17th March 2018. The paper is currently in production. There is a 12 month embargo period after the formal publication.
Uncontrolled Keywords:	Image cosegmentation; shape similarity; foreground discovery scheme
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
Related URLs:	Publisher
Last Modified:	04 Mar 2022 13:06
URI:	http://gala.gre.ac.uk/id/eprint/19587

Actions (login required)

View Item

Downloads