A Novel Multiresolution based Optimization Scheme for Robust Affine Parameter Estimation

Authors: J.Dinesh Peter

Abstract:

This paper describes a new method for affine parameter estimation between image sequences. Usually, the parameter estimation techniques can be done by least squares in a quadratic way. However, this technique can be sensitive to the presence of outliers. Therefore, parameter estimation techniques for various image processing applications are robust enough to withstand the influence of outliers. Progressively, some robust estimation functions demanding non-quadratic and perhaps non-convex potentials adopted from statistics literature have been used for solving these. Addressing the optimization of the error function in a factual framework for finding a global optimal solution, the minimization can begin with the convex estimator at the coarser level and gradually introduce nonconvexity i.e., from soft to hard redescending non-convex estimators when the iteration reaches finer level of multiresolution pyramid. Comparison has been made to find the performance of the results of proposed method with the results found individually using two different estimators.

Keywords: Image Processing, Affine parameter estimation, Outliers, Robust Statistics, Robust M-estimators

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1082704

References:

[1] S. Geman and D. Geman, Stochastic relaxation, Gibbs Distributions and the Bayesian restoration of Images, IEEE Trans. on Pattern Analysis and Machine Intelligence, 6, 721-741, 1984.
[2] F. C. Jeng and J. W. Woods, Image estimation by stochastic relaxation in the compound Gaussian case, In Proceedings IEEE Conf. on Acoust., Speech, and Signal Proc., 1988.
[3] S. Kirkpatrick and C. D. Gelatt and M. P. Vecchi, Optimization by Simulated Annealing, Science, 220(4598), 671-680, 1983.
[4] K. Matsui, M. Sase and Y. Kosugi, Medical Image Mapping Using Collaborative Genetic Algorithm, In Proceedings of Sixteenth Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Baltimore, Maryland, U.S.A., 1(2), 612-613, 1994.
[5] B.C.S. Tom, S.N. Efstratiadis and A.K. Katsaggelos, Motion Estimation of Skeletonized Angiographic Images Using Elastic Registration, IEEE Transactions on Medical Imaging, 13(3), 450-460, 1994.
[6] V.R. Mandava, J.M. Fitzpatrick and D.R. Pickens, Adaptive Search Space Scaling in Digital Image Registration, IEEE Transactions on Medical Imaging, 8(3), 251-262, 1989.
[7] S. Farsiu, D. Robinson, M. Elad, and P. Milanfar, Fast and Robust Multiframe Super-resolution, IEEE Transactions on Image Processing, 13(10), 1327-1344, 2004.
[8] Ming Ye, Linda G. Shapiro, Robert M. Haralick, Estimating Piecewise- Smooth Optical Flow with Global Matching and Graduated Optimization, IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(12), 1625-1630, 2003.
[9] C. Koch, J. L. Marroquin, and A. L. Yuille, Analog neuronal networks in early vision,In Proceedings of the National Academy of Sciences, pp. 4263-4267, 1986.
[10] D. Geiger and F. Girosi, Parallel and deterministic algorithms for MRFs: surface reconstruction and integration, Technical Report A. I. Memo, No. 1114, Artificial Intelligence Lab, M. I. T, 1989.
[11] D. Terzopoulos, The Computation of Visible-Surface Representations, IEEE Transactions on Pattern Analysis and Machine Intelligence, 10, 417-437, 1988.
[12] M. Lefebure and L. Cohen, A multiresolution algorithm for signal and image registration, in Proc. IEEE Int. Conf. on Image Processing, 3, 252- 255, 1997.
[13] A.Blake, A. Zisserman, Visual Reconstruction, MIT Press, Cambridge, MA, 1987.
[14] P. J. Green, Bayesian reconstructions from emission tomography data using a modified EM algorithm, IEEE Transactions on Medical Imaging, 9, 84-93, 1990.
[15] R. R. Schultz and R. L. Stevenson, Stochastic modeling and estimation of multispectral image data, IEEE Transactions on Image Processing, 4, 1109-1119, 1995.
[16] C. Bouman and K. Sauer, A generalized Gaussian image model for edgepreserving MAP estimation, IEEE Transactions on Image Processing, 2, 296-310, 1993.
[17] K. Lange, Convergence of EM image reconstruction algorithms with Gibbs smoothing, IEEE Transactions on Medical Imaging, 9, 439-446, 1990.
[18] Pierre Charbonnier, Laure Blanc-Fraud, Gilles Aubert, Michel Barlaud, Deterministic edge-preserving regularization in computed imaging, IEEE Transactions on Image Processing, 6(2), 298-311, 1997.
[19] R. Dahyot, P. Charbonnier, and F. Heitz, Robust visual recognition of colour images, In proceedings of CVPR, 1, 685-690, 2000.
[20] T. Hebert and R. Leahy, A generalized EM algorithm for 3-D Bayesian reconstruction from Poisson data using Gibbs priors, IEEE Transactions on Medical Imaging, 8, 194-202, 1990.
[21] Roger M. Dufour, Eric L. Miller, Nikolas P. Galatsanos, Template matching based object recognition with unknown geometric parameters. IEEE Transactions on Image Processing, 11(12), 1385-1396, 2002.
[22] Michael J. Black, P. Anandan, The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields, Computer Vision and Image Understanding, 63(1), 75-104, 1996.
[23] P. W. Holland and R. E. Welsch, Robust regression using iteratively reweighed least-squares, Communications in Statistics: Theory and Methods, A6, 813-827, 1977.
[24] H. Farid and E.P. Simoncelli. Optimally rotation-equivariant directional derivative kernels. In Proceedings of International Conference on Computer Analysis of Images and Patterns, pp. 207-214, Berlin, Germany, 1997.
[25] Keith A. Johnson, J. Alex Becker, The whole brain Atlas, http://www.med.harvard.edu/AANLIB/