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

TAKASHI, TORIU (2017) A Method for Extracting Affine Invariant Local Features Using a Metric Tensor. In: Fifth International Conference on Advances in Computing, Communication and Information Technology - CCIT 2017, 02-03 September, 2017, Zurich, Switzerland.

[img]
Preview
Text
20170922_041135.pdf - Published Version

Download (706kB) | Preview
Official URL: https://www.seekdl.org/conferences/paper/details/9...

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.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: feature extracton, affine invariance, metric tensor, smoothing (key words)
Depositing User: Mr. John Steve
Date Deposited: 11 Mar 2019 08:30
Last Modified: 11 Mar 2019 08:30
URI: http://publications.theired.org/id/eprint/390

Actions (login required)

View Item View Item