Color Image Registration under Illumination Changes
The estimation of parametric global motion has had a significant attention during the last two decades, but despite the great efforts invested, there are still open issues. One of the most important ones is related to the ability to simultaneously cope with viewpoint and illumination changes while keeping the method accurate. In this paper, a Generalized least squared-based motion estimator model able to cope with large geometric transformations and illumination changes is presented. Experiments are made on a series of images showing that the presented technique provides accurate estimates of the motion and illumination parameters.
- 1.Bartoli, A.: Groupwise geometric and photometric direct image registration. In: Proceedings of the British Machine Vision Conference, pp. 157–166 (2006)Google Scholar
- 4.Finlayson, G.D., Hordley, S.D., Xu, R.: Convex programming colour constancy with a diagonal-offset model. In: IEEE ICIP, vol. 3, pp. 948–951 (2005)Google Scholar
- 5.Gonzalez, R.C., Woods, R.E.: Digital image processing. Prentice-Hall, Englewood Cliffs (2007)Google Scholar
- 9.Lenz, R., Tran, L.V., Meer, P.: Moment based normalization of color images. In: IEEE 3rd Workshop on multimedia signal processing, pp. 103–108 (1998)Google Scholar
- 16.Wyszecki, G., Stiles, W.S.: Color science. John Wiley & Sons, Chichester (1967)Google Scholar
- 17.Xingming, Z., Huangyuan, Z.: An illumination independent eye detection algorithm. In: IEEE ICPR, vol. 1, pp. 342–345 (2006)Google Scholar