Conference Proceedings

Fifth International Conference on Advances in Computing, Communication and Information Technology - CCIT 2017

A Method for Extracting Affine Invariant Local Features Using a Metric Tensor

Author(s) : TAKASHI TORIU

Abstract

This paper proposes a method for extracting local features which is invariant under affine transformations. This method is based on the metric tensor . Using the met ric tensor, an affine invariant smoothing filter and a set of affine invariant differential operator s are construc ted. Then, combining them a set of affine invariant feature extractions is constructed. Effectiveness of the proposed method is confirmed by experiments.

Conference Title : Fifth International Conference on Advances in Computing, Communication and Information Technology - CCIT 2017
Conference Date(s) : 02-03 September, 2017
Place : Novotel Zurich City-West Schiffbaustrasse 13, 8005 Zurich, Switzerland
No fo Author(s) : 1
DOI : 10.15224/978-1-63248-131-3-18
Page(s) : 48 - 54
Electronic ISBN : 978-1-63248-131-3
Views : 268   |   Download(s) : 174