A novel image matching algorithm based on sliding histograms of oriented gradients
- 163 Downloads
A novel algorithm for image matching based on recursive calculation of histograms of oriented gradients over several circular sliding windows and pyramidal image decomposition is presented. The algorithm gives good results for geometrically distorted and scaled scene images. The results of computer simulation obtained with the proposed algorithm are compared to those of available algorithms in terms of matching accuracy and processing time.
Keywordsimage matching fast algorithm histogram of oriented gradients circular window
Unable to display preview. Download preview PDF.
- 1.D. G. Lowe, “Object recognition from local scale-invariant features,” in Proc. 7th Int. Conf. on Computer Vision, Crete, 1999 (IEEE, New York, 1999), Vol. 2, pp. 1150–1157.Google Scholar
- 4.M. Calonder, V. Lepetit, C. Strecha, and P. Fua, “BRIEF: binary robust independent elementary features,” in Proc. 11th Eur. Conf. on Computer Vision. (ECCV’10), Hersonissos Heraklion Crete, Greece, 2010 (Springer-Verlag, 2010), pp. 778–792.Google Scholar
- 5.R. Ortiz, “FREAK: Fast Retina Keypoint,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, CVPR’12, Providence, RI, June, 2012 (IEEE, New York, 2012), pp. 510–517.Google Scholar
- 8.K. L. Rice, T. M. Taha, A. M. Chowdhury, A. A. S. Awwal, and D. L. Woodard, “Design and acceleration of phase-only filter-based optical pattern recognition for fingerprint identification,” Opt. Eng. 48(11), 117–206 (2009).Google Scholar
- 9.B. A. Zalesky and P. V. Lukashevich, “Scale invariant algorithm to match regions on aero or satellite images,” Proc. Pattern Recogn. Inf. Process. 11, 25–30 (2011).Google Scholar
- 10.N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” Comput. Vis. Pattern Recogn. 1, 886–893 (2005).Google Scholar