2 December 2011 A fast template matching method based on context prediction
Author Affiliations +
Proceedings Volume 8004, MIPPR 2011: Pattern Recognition and Computer Vision; 80040C (2011) https://doi.org/10.1117/12.901571
Event: Seventh International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2011), 2011, Guilin, China
Abstract
This paper presents a novel fast template matching algorithm based on context prediction. The predicted regions are those windows that contain the current entire sub-window. Comparison skipping or comparison terminating is executed when a low bound of distance which has been calculated between the template and the window exceeds the threshold. Experimental results and theory analyses prove the proposed method is faster than the conventional fast template matching method, strictly guaranteeing the same accuracy and up to maximal twenty times faster than the SSDA.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lie Kang, Lie Kang, Sheng Zhong, Sheng Zhong, Zuoqian Du, Zuoqian Du, Zhangfa Ren, Zhangfa Ren, } "A fast template matching method based on context prediction", Proc. SPIE 8004, MIPPR 2011: Pattern Recognition and Computer Vision, 80040C (2 December 2011); doi: 10.1117/12.901571; https://doi.org/10.1117/12.901571
PROCEEDINGS
7 PAGES


SHARE
RELATED CONTENT

Fixed-point B.G. Lee IDCT without multiplication
Proceedings of SPIE (November 13 2007)
Topologically clustering: a method for discarding mismatches
Proceedings of SPIE (November 14 2007)
Relaxation-based approach for object recognition
Proceedings of SPIE (November 14 2007)
Features extraction and image analysis of seismic sections
Proceedings of SPIE (February 12 2004)
Object pre-processing for optical pattern recognition
Proceedings of SPIE (January 10 2005)

Back to Top