This Article 
 Bibliographic References 
 Add to: 
Self-Adaptive Regularization
June 2004 (vol. 26 no. 6)
pp. 804-809

Abstract—Often an image g(x,y) is regularized and even restored by minimizing the Mumford-Shah functional. Properties of the regularized image u(x,y) depends critically on the numerical value of the two parameters \alpha and \gamma controlling smoothness and fidelity. When \alpha and \gamma are constant over the image, small details are lost when an extensive filtering is used in order to remove noise. In this paper, it is shown how the two parameters \alpha and \gamma can be made self-adaptive. In fact, \alpha and \gamma are not constant but automatically adapt to the local scale and contrast of features in the image. In this way, edges at all scales are detected and boundaries are well-localized and preserved. In order to preserve trihedral junctions \alpha and \gamma become locally small and the regularized image u(x,y) maintains sharp and well-defined trihedral junctions. Images regularized by the proposed procedure are well-suited for further processing, such as image segmentation and object recognition.

[1] G. Aubert and P. Kornprobst, Mathematical Problems in Image Processing. Springer, 2002.
[2] G. Aubert, R. Deriche, and P. Kornprobst, Computing Optical Flow via Variational Techniques SIAM J. Applied Math., vol. 60, no. 1, pp. 156-182, 1999.
[3] R. Battiti and G. Tecchiolli, Learning with First, Second, and No Derivatives: A Case Study in High Energy Physics Neurocomputing, vol. 6, pp. 181-206, 1994.
[4] M. Bertero, T.A. Poggio, and V. Torre, "Ill-posed problems in early vision," Proc. IEEE, vol. 76, no. 8, pp. 869-889, 1988.
[5] A. Blake and A. Zisserman, Visual Reconstruction. MIT Press, 1987.
[6] J.F. Canny, A Computational Approach to Edge Detection IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, pp. 679-698, 1986.
[7] A. Chambolle and G. Dal Maso, Discrete Approximation of the Mumford Shah Functional in Dimension Two Math. Modelling and Numerical Analysis, vol. 33, pp. 651-672, 1999.
[8] A. Chambolle, Finite Differences Discretization of the Mumford-Shah Functional Math. Modelling and Numerical Analysis, vol. 33, pp. 261-288, 1999.
[9] J.H. Elder and S.W. Zucker, Local Scale Control for Edge Detection and Blur Estimation IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 7, pp. 699-716, July 1998.
[10] W. Eric, L. Grimson, and T. Lozano-Perez, Model-Based Recognition and Localization from Sparse Range or Tactile Data Int'l J. Robotics Research, vol. 3, no. 3, pp. 3-35, 1984.
[11] M. Gobbino, Finite Difference Approximation of the Mumford-Shah Functional Comm. Pure and Applied Math., vol. 51, no. 2, pp. 197-228, 1998.
[12] B.K. Horn and B.G. Schunck, Determining Optical Flow Artificial Intelligence, vol. 17, pp. 185-203, 1981.
[13] T. Lindeberg, Edge Detection and Ridge Detection with Automatic Scale Selection Int'l J. Computer Vision, vol. 30, no. 2, 1998.
[14] P. Majer, The Influence of the$\gamma$-Parameter on Feature Detection with Automatic Scale Selection Proc. Third Int'l Conf. Scale-Space, 2001.
[15] J.M. Morel and S. Solimini, Variational Methods in Image Segmentation. Birkhauser, 1995.
[16] M. Morini and M. Negri, Mumford-Shah Functional as$\Gamma$-Limit of Discrete Perona-Malik Energies Math. Models&Methods in Applied Sciences, to be published.
[17] D. Mumford and J. Shah, Optimal Aproximation of Piecewise Smooth Function and Associated Variational Problems Comm. Pure and Applied Math, vol. 42, pp. 577-685, 1989.
[18] M. Negri and M. Paolini, Numerical Minimization of the Mumford-Shah Functional Calcolo, vol. 38, pp. 957-982, 2001.
[19] F.A. Pellegrino, W. Vanzella, and V. Torre, Edge Detection Revisited IEEE Trans. SMC, (in press).
[20] P. Perona and J. Malik, "Scale-Space and Edge Detection Using Anisotropic Diffusion," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 7, pp. 629639, July 1990.
[21] J.M.S. Prewitt, Object Enhancement and Extraction Picture Processing and Psychophysics, A. Rosenfeld and B. S. Lipkin, eds. pp. 75-149, New York: Academic Press, 1970.
[22] T. Poggio, V. Torre, and C. Koch, Computational Vision and Regularization Theory Nature, vol. 317, no. 6035, pp. 314-319, 1985.
[23] L.G. Roberts, Machine Perception of Three Dimensional Solids Optical and Eletrooptical Information Processing, J. Tippett, D. Berkowitz, L. Clapp, C. Koester and A. Vanderburgh, eds. pp. 159-197, MIT Press, 1965.
[24] C. Samson, L. Blanc-Feraud, G. Aubert, and J. Zerubia, A Variational Model for Image Classification and Restoration IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 5, pp. 460-472, May 2000.
[25] C. Schnorr, Determining Optical Flow for Irregular Domains by Minimizing Quadratic Functionals of a Certain Class Int'l J. Computer Vision, vol. 6, no. 1, pp. 25-38, 1991.
[26] D.M. Strong and T.F. Chan, Edge-Preserving and Scale-Dependent Properties of Total Variation Regularization SIAM J. Applied Math., submitted 2000.
[27] V. Torre and T.A. Poggio, On Edge Detection IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, pp. 148-163, 1986.
[28] T.P. Vogl, J.W. Mangis, A.K. Rigler, W.T. Zink, and D.L. Alkon, Accelerating the Convergence of the Back-Propagation Method Biological Cybrnetics, vol. 59, pp. 257-263, 1988.

Index Terms:
Image regularization, Mumford-Shah, variational methods.
Walter Vanzella, Felice Andrea Pellegrino, Vincent Torre, "Self-Adaptive Regularization," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 6, pp. 804-809, June 2004, doi:10.1109/TPAMI.2004.15
Usage of this product signifies your acceptance of the Terms of Use.