a-shapes for local feature detection

Varytimidis, Christos and Rapantzikos, Konstantinos and Avrithis, Yannis and Kollias, Stefanos (2016) a-shapes for local feature detection. Pattern Recognition, 50 (2). pp. 56-73. ISSN 0031-3203

Documents
α-shapes for local feature detection - patternrecognitionvol50pp56-73Feb2016.pdf
Publisher's version marked In Press

Request a copy
alpha-shapes_PR-R1_comp.pdf

Request a copy
[img] PDF
α-shapes for local feature detection - patternrecognitionvol50pp56-73Feb2016.pdf - Whole Document
Restricted to Repository staff only

17MB
[img] PDF
alpha-shapes_PR-R1_comp.pdf - Whole Document
Restricted to Repository staff only until 1 February 2018.

5MB
Item Type:Article
Item Status:Live Archive

Abstract

Local image features are routinely used in state-of-the-art methods to solve many computer vision problems like image retrieval, classification, or 3D registration. As the applications become more complex, the research for better visual features is still active. In this paper we present a feature detector that exploits the inherent geometry of sampled image edges using α-shapes. We propose a novel edge sampling scheme that exploits local shape and investigate different triangulations of sampled points. We also introduce a novel approach to represent the anisotropy in a triangulation along with different feature selection methods. Our detector provides a small number of distinctive features that is ideal for large scale applications, while achieving competitive performance in a series of matching and retrieval experiments.

Keywords:local features, point sampling, triangurisation, a-shapes, JCNotOpen
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
ID Code:25834
Deposited On:20 Jan 2017 12:24

Repository Staff Only: item control page