Corcoran, Padraig and Mooney, Peter and Tilton, James (2011) Convexity Grouping of Salient Contours. In: GbRPR 2011: Graph-Based Representations in Pattern Recognition. Lecture Notes in Computer Science book series (LNCS) (6658). Springer, pp. 235-244. ISBN 9783642208447

Preview

Download (263kB) | Preview

Abstract

Convexity represents an important principle of grouping in visual perceptual organization. This paper presents a new technique for contour grouping based on convexity and has the following two properties. Firstly it finds groupings that form contours of high convexity which are not strictly convex. Secondly it finds groupings that form both open and closed contours of high convexity. The authors are unaware of any existing technique which exhibits either of these properties. Contour grouping is posed as the problem of finding minimum cost paths in a graph. The proposed method is evaluated against two highly cited benchmark methods which find strictly convex contours. Both qualitative and quantitative results on natural images demonstrate the proposed method significantly outperforms both benchmark methods.

Item Type:	Book Section
Additional Information:	Cite as: Corcoran P., Mooney P., Tilton J. (2011) Convexity Grouping of Salient Contours. In: Jiang X., Ferrer M., Torsello A. (eds) Graph-Based Representations in Pattern Recognition. GbRPR 2011. Lecture Notes in Computer Science, vol 6658. Springer, Berlin, Heidelberg. Research presented in this paper was part-funded by a Strategic Research Cluster grant (07/SRC/I1168) and a Research Professor Award (07/RPR/I1177) from Science Foundation Ireland under the National Development Plan.
Keywords:	Salient Contour; Graph Searching; Convexity;
Academic Unit:	Faculty of Science and Engineering > Computer Science
Item ID:	10406
Identification Number:	https://doi.org/10.1007/978-3-642-20844-7_24
Depositing User:	Peter Mooney
Date Deposited:	08 Jan 2019 15:41
Publisher:	Springer
Refereed:	Yes
Funders:	Science Foundation Ireland (SFI)
URI:	https://link.springer.com
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads