Abstract
In geometric image registration, illumination variations that exist between image pairs tend to degrade the precision of the registration, which can negatively affect subsequent processing. In this paper, we present a model to improve the sub-pixel geometric registration precision of image pairs when there exists locally variant illuminations with arbitrary shape. This model extends on our previous work to include multiple local shading levels of arbitrary shape, where the ill-posed problem is conditioned by constraining the solution to an estimated number of shading levels. The proposed model is solved using least-squares estimation and is cast in an iterative coarse-to-fine framework, which allows a convergence rate that is similar to competing intensity-based image registration approaches. The primary advantage of the proposed approach is the nearly tenfold improvement in sub-pixel precision for the registration when convergence is obtained in this class of technique.
Similar content being viewed by others
References
Zitová B., Flusser J.: Image registration methods: a survey. Image Vis. Comput. 21, 977–1000 (2003)
Lucchese L., Leorin S., Cortelazzo G.M.: Estimation of two-dimensional affine transformations through polar curve matching and its application to image mosaicking and remote-sensing data registration. IEEE Trans Image Process. 15(10), 3008–3019 (2006)
Gevrekci, M., Gunturk, B.K.: Superresolution under photometric diversity of images. EURASIP J. Adv. Signal Process. 2007, 205–216 (2007) Special Issue: Super-resolution enhancement of digital video. doi:10.1155/2007/36076
Wang Y., Xu L.: A global optimized registration algorithm for image stitching. IEEE CISP 3, 525–529 (2008)
Roy D.P.: The impact of misregistration upon composited wide field of view satellite data and implications for change detection. IEEE Trans Geosci. Remote Sens. 38(4), 2017–2032 (2000)
Lou, L., Zhang, F., Xu, C., Li, F., Xue, M.: Automatic registration of aerial image series using geometric invariance. IEEE ICAL 1198–1203 (2005)
Periaswamy S., Farid H.: Elastic registration in the presence of intensity variations. IEEE Trans Medical Imaging 22(7), 865–874 (2003)
Aguiar, P.M.Q.: Unsupervised simultaneous registration and exposure correction. IEEE ICIP 361–364 (2006)
Altunbasak Y., Mersereau R.M., Patti A.J.: A fast parametric motion estimation algorithm with illumination and lens distortion correction. IEEE Trans. Image Process. 12(4), 395–408 (2003)
Bartoli A.: Groupwise geometric and photometric direct image registration. IEEE Trans. Pattern Anal. Mach. Intell. 30(12), 2098–2108 (2008)
Fouad, M.M., Dansereau, R.M., Whitehead, A.D.: Geometric registration of images with arbitrarily-shaped local intensity variations from shadows. IEEE ICIP 201–204 (2009)
Jiang, J., Zheng, S., Toga, A.W., Tu, Z.: Learning based coarse- to-fine image registration. IEEE ICCVPR 1–7 (2008)
Kanungo T., Mount D.M., Netanyahu N., Piatko C., Silverman R.: An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 881–892 (2002)
Guizar-Sicairos M., Thurman S.T., Fienup J.R.: Efficient subpixel image registration algorithms. Opt. Lett. 33(2), 156–158 (2008)
Al Bovik 2000 Image and video processing, 2nd edn. Academic Press, Texas
Wang Z., Bovik A.C., Sheikh H.R., Simoncelli E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Barnea D., Silverman H.: A class of algorithms of fast digital image registration. IEEE Trans. Comput. 21(2), 179–186 (1972)
Szeliski, R.: Image alignment and stitching: a tutorial. Found. Trends Comput. Graph. Vis. 2(1) (2006)
Xu D., Kasparis T.: Robust image registration under spatially non-uniform brightness changes. IEEE ICASSP 2, 945–948 (2005)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fouad, M.M., Dansereau, R.M. & Whitehead, A.D. Geometric image registration under arbitrarily-shaped locally variant illuminations. SIViP 6, 521–532 (2012). https://doi.org/10.1007/s11760-010-0178-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-010-0178-4