A Real-Time NCC-Based Template Matching on Modern CPUs

Abstract:

This paper proposes an optimal method for NCC-based template matching on modern CPUs for time-critical applications. In order to achieve the superior computation efficiency, the brand-and-bound (BB) scheme and the streaming SIMD extensions 2 (SSE2) instructions are employed to quickly find out the target object with rotation, translation and scaling in monochrome or color image. And we show how to reject unpromising image location very quickly using BB scheme in search process. Furthermore, an efficient implementation for similarity coefficient calculation is also pointed out by using the integration SSE2 instructions. Finally, the results show that the proposed method is very powerful when dealing with the NCC-based template matching in monochrome and color images.

• Periodical: Applied Mechanics and Materials (Volumes 764-765)
• Pages: 1288-1292
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.764-765.1288
• Online since: May 2015
• Authors: Chin Sheng Chen*, Chien Liang Huang, Chun Wei Yeh
• Keywords: Branch-and-Bound, Normalized Cross-Correlation (NCC), Similarity Measure, SSE2, Template Matching

References

[1] D. -M. Tsai, C. -T. Lin and J. -F. Chen: Pattern Recognition Letters vol. 24 (2003), p.2525.

[2] J. Lewis: Vision Interface (1995), p.120.

[3] K. Briechle and U. D. Hanebeck: Aerospace/Defense Sensing, Simulation, and Controls (2001), p.95.

[4] M. J. McDonnell: Computer Graphics and Image Processing Vol. 17 (1981), p.65.

[5] C. Sun: Image and Vision Computing Vol. 20 (2002), p.981.

[6] S. Mattoccia, F. Tombari and L. Di Stefano: IEEE Transactions on Image Processing Vol. 17 (2008), p.528.

[7] S. Mattoccia, F. Tombari and L. Di Stefano: Pattern Recognition Letters Vol. 32 (2011), p.694.

DOI: 10.1016/j.patrec.2010.12.004

[8] W. Shou-Der and L. Shang-Hong: IEEE Transactions on Image Processing Vol. 17 (2008), p.2227.

[9] C. H. Lampert, M. B. Blaschko and T. Hofmann: Computer Vision and Pattern Recognition (2008), p.1.

[10] L. Di Stefano, S. Mattoccia and F. Tombari: Computer Architecture for Machine Perception (2005), p.193.

[11] J. Kadidlo and A. Strey: Euromicro Conference on Parallel, Distributed and Network-Based Processing (2008), p.407.

[12] S. Hinterstoisser, V. Lepetit, S. Ilic, P. Fua and N. Navab: IEEE Conference on Computer Vision and Pattern Recognition (2010), p.2257.

DOI: 10.1109/cvpr.2010.5539908

[13] S. Hinterstoisser, S. Holzer, C. Cagniart, S. Ilic, K. Konolige, N. Navab and V. Lepetit: IEEE International Conference on Computer Vision (2011), p.858.

DOI: 10.1109/iccv.2011.6126326

[14] S. Hinterstoisser, C. Cagniart, S. Ilic, P. Sturm, N. Navab, P. Fua and V. Lepetit: IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 34 (2012), p.876.

DOI: 10.1109/tpami.2011.206

[15] Y. Konishi, Y. Kotake, Y. Ijiri and M. Kawade: Computer Vision–ECCV 2012 (2012), p.607.

[16] C. -S. Chen, C. -L. Huang and C. -W. Yeh: Advanced Science Letters vol. 9 (2012), p.762.