Abstract
The object of this paper is to present a formulation for the segmentation and restoration problem using flexible models with a robust regularized network (RRN). A two-steps iterative algorithm is presented. In the first step an approximation of the classification is computed by using a local minimization algorithm, and in the second step the parameters of the RRN are updated. The use of robust potentials is motivated by (a) classification errors that can result from the use of local minimizer algorithms in the implementation, and (b) the need to adapt the RN using local image gradient information to improve fidelity of the model to the data.
Chapter PDF
Similar content being viewed by others
References
Li, S.Z.: Markov Random Field Modeling in Image Analysis, Springer-Verlag, New York (2001)
Kirkpatrick, S., Gellatt, C. D., Vecchi, M.P.: Optimization by simulated annealing, Science, 220 (1983) 671–680
Geman, S., Geman, D.: Stochastic relaxation, Gibbs distributions and Bayesian restoration of images, IEEE Trans. Pattern Anal. Machine Intell., 6 (1984) 721–741
Besag, J.: On the statistics analysis of dirty pictures (with discussions), Journal of the Royal Statistical Society, Series B, 48 (1986) 259–302
Peterson C., Soderberg, B. A new method for mapping optimization problems onto neural networks, International Journal of Neural Systems, 1 (1989) 3–22
Geiger D., Girosi, F.: Parallel and deterministic algorithms for MRFs: Surface reconstruction and Integration, IEEE Trans. Pattern Anal. Machine Intell., 12 (1991) 401–412
Zhang, J.: Mean field theory in EM procedures for MRFs,” IEEE Trans. Signal Processing, 40 (1992) 2570–2583
Heitz, F., Perez, P., Bouthermy, P.: Multiscale minimization of global energy functions in some visual recovery problems, Computer Vision, Graphics, and Image Processing: Image Understanding, 59 (1994) 125–136
Faugeras, O., Price, K.: Semantic description of aerial images using stochastic labeling, IEEE Trans. Pattern Anal. Machine Intell., 3 (1981) 638–642
Hummel, R.A., Zucker, S.W.: On the foundations of relaxation labeling process, IEEE Trans. Pattern Anal. Machine Intell., 5 (1983) 267–286
Li, S.Z., MAP image restoration and segmentation by constrained optimization, IEEE Trans. Image Processing, 9 (1998) 1134–1138
Marroquin, J.L., Velazco, F.A., Rivera, M., Nakamura, M.: Gauss-Markov Measure Field Models for low-level vision, IEEE Trans. Pattern Anal. Machine Intell., 23 (2001) 337–348
Darrell, T.J., Pentland, A.P.: Cooperative robust estimation using layers of support, IEEE Trans. Pattern Anal. Machine Intell., 17 (1995) 474–487
Black, M.J., Fleet D.J., Yacoob, Y.: Robustly estimating changes in image appearance, Comput. Vision Image Understand. 78 (2000) 8–31
Marroquin, J.L., Botello, S., Calderon F., Vemuri, B.C.: MPM-MAP for image segmentation, In Procc. ICPR 2000, Barcelona Spain, 4 (2000) 300–310
Samson, C., Blanc-Feraud, L., Aubert, G., Zerubia, J.: A variational model for image classification and restoration, IEEE Trans. Pattern Anal. and Machine Intell., 22 (2000) 460–472
Girosi, F., Jones, M., Poggio, T.: Regularization theory and neural networks architectures, Neural Computing, 7 (1995) 219–269
Rivera, M., Marroquin, J.L.: Efficient Half-Quadratic Regularization with Granularity Control, Technical Report: 05.06.2001, I-01-07 (CC), CIMAT, Mexico (2001)
Geman, S., McClure, D.E.: Bayesian image analysis methods: An application to single photon emission tomography, Proc. Statistical Computation Section, Amer. Statistical Assoc., Washington, DC, (1985) 12–18
Geman, D., Reynolds, G.: Constrained restoration and the recovery of discontinuities, IEEE Trans. Image Processing, 14 (1992) 367–383
Geman, D., Yang, C.: Nonlinear image recovery with half-quadratic regularization, IEEE Trans. Image Processing, 4 (1995) 932–946
Black, M.J., Rangarajan, A.: Unification of line process, outlier rejection, and robust statistics with application in early vision,” Int. J. Comput. Vis., 19, (1996) 57–92
Charbonnier, P., Blanc-Féraud, L., Aubert, G., Barlaud, G.: Deterministic edge-preserving regularization in computer imaging, IEEE Trans. Image Processing, 6 (1997) 298–311
Rivera, M., Marroquin, J.L.: The adaptive rest condition spring model: an edge preserving regularization techinque, in Proc.Interational Conference on Image Processing, IEEE-ICIP 2000, Vol. II, Vancouver, Canada (2000) 805–807
Rivera, M., Marroquin, J.L.: Adaptive Rest Condition Potentilas: Second Order Edge-Preserving Regularization, In Proc. European Conference on Computer Vision, ECCV 2002, Springer-Verlag, Copenhagen, Denmark, May (2002)
Girosi, F., Poggio, T., Caprile B., Extensions of a theory of networks for approximation of and learning: outliers and negative examples,” In R. Lippmann, J. Moody and D. Tourezky, editors, Advances in Neural information processing systems 3, San Mateo, CA, Cambridge University Press (1991)
Girosi, F., Jones, M., Poggio, T.: Priors, stabilizers and basis functions: from regularization to radial, tensor and additive splines, MIT AI Lab Memo, No. 1430, June (1993)
Weickert, J.: Efficient image segmentation using partial differentiable equations and morphology, Pattern Recognition, 34 (2001) 1813–1824
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rivera, M., Gee, J. (2002). Image Segmentation by Flexible Models Based on Robust Regularized Networks. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds) Computer Vision — ECCV 2002. ECCV 2002. Lecture Notes in Computer Science, vol 2352. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-47977-5_41
Download citation
DOI: https://doi.org/10.1007/3-540-47977-5_41
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43746-8
Online ISBN: 978-3-540-47977-2
eBook Packages: Springer Book Archive