9 January 2008 Image template matching based on ratio of mean and central pixel in local area
Author Affiliations +
Proceedings Volume 6794, ICMIT 2007: Mechatronics, MEMS, and Smart Materials; 67944I (2008) https://doi.org/10.1117/12.784075
Event: ICMIT 2007: Mechatronics, MEMS, and Smart Materials, 2007, Gifu, Japan
Abstract
This paper proposes a template matching method (RMCM: Ratio of Mean and Central pixel's residual sum Matching), which is based on a residual sum of ratio of mean in local area and its central pixel's gray-level in a template image. In the method, the ratio of mean and its central pixel's are registered in a local area whose center is every pixel in a template image. The target image area is searched from the matching ratio, which is obtained by residual sum between target image and template image whose correlation has been registered. The experimental results show that the proposed method had equal or better robustness to the inferior factors of objective images in comparison with the two typical conventional template matching methods.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
M. Moritani, M. Moritani, F. Saitoh, F. Saitoh, } "Image template matching based on ratio of mean and central pixel in local area", Proc. SPIE 6794, ICMIT 2007: Mechatronics, MEMS, and Smart Materials, 67944I (9 January 2008); doi: 10.1117/12.784075; https://doi.org/10.1117/12.784075
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

Pre- and post-processing correlation filter data
Proceedings of SPIE (May 19 2013)
Design analysis of a magnetorheological damper
Proceedings of SPIE (March 20 2006)
Research on identification of moving targets in space
Proceedings of SPIE (October 14 2012)
Inherent engagement mechanism study of profile of scrolls
Proceedings of SPIE (March 20 2006)

Back to Top