An efficient implementation of normalized cross-correlation image matching based on pyramid

Normalized Cross-Correlation (NCC) image matching algorithm based on gray correlation provides accurate results however it consumes a significant time for large amount of calculations. The main contribution of this paper is implementing the NCC image matching algorithm in parallel. Moreover, it proposes and implements the NCCP based on pyramid to reduce the time.

[1]  Rikard Berthilsson.  Affine correlation , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[2]  Rohit Chandra,et al.  Parallel programming in openMP , 2000 .

[3]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[4]  Roberto Brunelli,et al.  Template Matching Techniques in Computer Vision: Theory and Practice , 2009 .

[5]  Roberto Brunelli,et al.  Advanced , 1980 .

[6]  J. P. Lewis.  Fast Normalized Cross-Correlation , 2010 .

[7]  A. Ardeshir Goshtasby,et al.  A Two-Stage Cross Correlation Approach to Template Matching , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Lawrence Snyder,et al.  Principles of Parallel Programming , 2008 .

[9]  Ronald N. Bracewell,et al.  The Fourier Transform and Its Applications , 1966 .

[10]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[11]  David A. Padua,et al.  Task-Parallel versus Data-Parallel Library-Based Programming in Multicore Systems , 2009, 2009 17th Euromicro International Conference on Parallel, Distributed and Network-based Processing.

[12]  Rachid Deriche,et al.  A Robust Technique for Matching two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry , 1995, Artif. Intell..

[13]  Seyed H. Roosta.  Principles of Parallel Programming , 2000 .