AN IMAGE REGISTRATION TECHNIQUE FOR DETECTION OF CRACK AND RUST GROWTH

Norihiko Itoh

2006

Abstract

To observe and record the progress of cracks and rusting, it is necessary to compare the images of the past with those of the present. The angles of surfaces of structures such as a concrete wall taken vary according to the camera position, that is the location in which they were taken. The images that were taken from different points are distorted, deformed or appear as if the actual location of the cracker rust has been shifted. So need less to say, the uses of these images are not good means of accurately detecting the progress of crack and rusting. It is first necessary to make rectifications. This can be done by using the images as a basis in determining the correct camera location and the adjustments made thereof. This paper proposes the difference of the camera angle can be detected by applying the frequency element of the whole image. Especially, this method is effective for a surface with few features such as a concrete wall.

References

  1. K. Takita, T. Aoki, Y. Sasaki, T. Higuchi, K. Kobayashi. (2003). High-Accuracy Subpixel Image Registration Based on Phase-Only Correlation. IEICE Trans. Fundam. Electron. Commun. Comput. Sci., E86- A(8):1925-1934.
Download


Paper Citation


in Harvard Style

Itoh N. (2006). AN IMAGE REGISTRATION TECHNIQUE FOR DETECTION OF CRACK AND RUST GROWTH . In Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, ISBN 972-8865-40-6, pages 389-392. DOI: 10.5220/0001367303890392


in Bibtex Style

@conference{visapp06,
author={Norihiko Itoh},
title={AN IMAGE REGISTRATION TECHNIQUE FOR DETECTION OF CRACK AND RUST GROWTH},
booktitle={Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,},
year={2006},
pages={389-392},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001367303890392},
isbn={972-8865-40-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,
TI - AN IMAGE REGISTRATION TECHNIQUE FOR DETECTION OF CRACK AND RUST GROWTH
SN - 972-8865-40-6
AU - Itoh N.
PY - 2006
SP - 389
EP - 392
DO - 10.5220/0001367303890392