Stable Keypoint Recognition using Viewpoint Generative Learning

Takumi Yoshida, Hideo Saito, Masayoshi Shimizu, Akinori Taguchi

2013

Abstract

We propose a stable keypoint recognition method that is robust to viewpoint changes. Conventional local features such as SIFT, SURF, etc., have scale and rotation invariance but often fail in matching points when the camera pose significantly changes. In order to solve this problem, we adopt viewpoint generative learning. By generating various patterns as seen from different viewpoints and collecting local invariant features, our system can learn feature descriptors under various camera poses for each keypoint before actual matching. Experimental results comparing usual local feature matching or patch classification method show both robustness and fastness of learning.

Paper Citation

in Harvard Style

Yoshida T., Saito H., Shimizu M. and Taguchi A. (2013). Stable Keypoint Recognition using Viewpoint Generative Learning . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-48-8, pages 310-315. DOI: 10.5220/0004295203100315

in Bibtex Style

@conference{visapp13,
author={Takumi Yoshida and Hideo Saito and Masayoshi Shimizu and Akinori Taguchi},
title={Stable Keypoint Recognition using Viewpoint Generative Learning},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={310-315},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004295203100315},
isbn={978-989-8565-48-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)
TI - Stable Keypoint Recognition using Viewpoint Generative Learning
SN - 978-989-8565-48-8
AU - Yoshida T.
AU - Saito H.
AU - Shimizu M.
AU - Taguchi A.
PY - 2013
SP - 310
EP - 315
DO - 10.5220/0004295203100315