1 May 2017 Fast Legendre moment computation for template matching
Author Affiliations +
Normalized cross correlation (NCC) based template matching is insensitive to intensity changes and it has many applications in image processing, object detection, video tracking and pattern recognition. However, normalized cross correlation implementation is computationally expensive since it involves both correlation computation and normalization implementation. In this paper, we propose Legendre moment approach for fast normalized cross correlation implementation and show that the computational cost of this proposed approach is independent of template mask sizes which is significantly faster than traditional mask size dependent approaches, especially for large mask templates. Legendre polynomials have been widely used in solving Laplace equation in electrodynamics in spherical coordinate systems, and solving Schrodinger equation in quantum mechanics. In this paper, we extend Legendre polynomials from physics to computer vision and pattern recognition fields, and demonstrate that Legendre polynomials can help to reduce the computational cost of NCC based template matching significantly.
Conference Presentation
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bing C. Li, "Fast Legendre moment computation for template matching", Proc. SPIE 10202, Automatic Target Recognition XXVII, 102020J (1 May 2017); doi: 10.1117/12.2262783; https://doi.org/10.1117/12.2262783


Color vision system for industrial applications
Proceedings of SPIE (December 17 1993)
Detection and localization of edge contours
Proceedings of SPIE (August 14 2003)
Timed fast exact Euclidean distance (tFEED) maps
Proceedings of SPIE (February 25 2005)
Face detection and recognition system for news videos
Proceedings of SPIE (September 25 2003)

Back to Top