On the Foundations of Probabilistic Relaxation with Product Support

Traditional probabilistic relaxation, as proposed by Rosenfeld, Hummel and Zucker, uses a support function which is a double sum over neighboring nodes and labels. Recently, Pelillo has shown the relevance of the Baum-Eagon theorem to the traditional formulation. Traditional probabilistic relaxation is now well understood in an optimization framework.Kittler and Hancock have suggested a form of probabilistic relaxation with product support, based on an evidence combining formula. In this paper we present a formal basis for Kittler and Hancocks probabilistic relaxation. We show that it too has close links with the Baum-Eagon theorem, and may be understood in an optimization framework. We provide some proofs to show that a stable stationary point must be a local maximum of an objective function.We present a new form of probabilistic relaxation that can be used as an approximate maximizer of the global labeling with maximum posterior probability.

[1]  Marcello Pelillo,et al.  Learning Compatibility Coefficients for Relaxation Labeling Processes , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Josef Kittler,et al.  A New Algorithm for Probabilistic Relaxation Based on the Baum Eagon Theorem , 1995, CAIP.

[3]  William J. Christmas,et al.  Structural Matching in Computer Vision Using Probabilistic Relaxation , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[5]  Josef Kittler,et al.  Probabilistic Relaxation as an Optimizer , 1995, BMVC.

[6]  R. Kirby.  A product rule relaxation method , 1980 .

[7]  Marcello Pelillo,et al.  The Dynamics of Nonlinear Relaxation Labeling Processes , 1997, Journal of Mathematical Imaging and Vision.

[8]  Olivier D. Faugeras,et al.  Improving Consistency and Reducing Ambiguity in Stochastic Labeling: An Optimization Approach , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Josef Kittler,et al.  On compatibility and support functions in probabilistic relaxation , 1986, Comput. Vis. Graph. Image Process..

[10]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[11]  James S. Duncan,et al.  Reinforcement of Linear Structure using Parametrized Relaxation Labeling , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Robert M. Haralick,et al.  An interpretation for probabilistic relaxation , 1983, Computer Vision Graphics and Image Processing.

[13]  J. P. Lasalle.  The stability and control of discrete processes , 1986 .

[14]  Josef Kittler,et al.  Combining Evidence in Probabilistic Relaxation , 1989, Int. J. Pattern Recognit. Artif. Intell..

[15]  L. Baum,et al.  Growth transformations for functions on manifolds. , 1968 .

[16]  Richard Szeliski,et al.  Bayesian modeling of uncertainty in low-level vision , 2011, International Journal of Computer Vision.

[17]  E. V. Krishnamurthy,et al.  Relaxation Processes forScene Labeling: Convergence, Speed, andStability , 1978 .

[18]  Eugene Charniak,et al.  A Simplex-Like Algorithm for the Relaxation Labeling Process , 1989 .

[19]  Wen-Hsiang Tsai,et al.  Relaxation by the Hopfield neural network , 1992, Pattern Recognit..

[20]  J. Kittler,et al.  RELAXATION LABELING ALGORITHMS - A REVIEW , 1985 .

[21]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[22]  Jiri Matas,et al.  On representation and matching of multi-coloured objects , 1995, Proceedings of IEEE International Conference on Computer Vision.

[23]  Shimon Ullman,et al.  Relaxation and constrained optimization by local processes , 1979 .

[24]  Josef Kittler,et al.  Relaxation labelling algorithms - a review , 1986, Image Vis. Comput..

[25]  S. A. Lloyd.  An optimization approach to relaxation labelling algorithms , 1983, Image Vis. Comput..

[26]  James S. Duncan,et al.  Relaxation labeling using continuous label sets , 1989, Pattern Recognit. Lett..

[27]  Josef Kittler,et al.  Edge-Labeling Using Dictionary-Based Relaxation , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  L. Baum,et al.  An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology , 1967 .

[29]  Richard Szeliski,et al.  Tracking with Kalman snakes , 1993 .

[30]  Demetri Terzopoulos,et al.  Regularization of Inverse Visual Problems Involving Discontinuities , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Demetri Terzopoulos.  Regularization ofInverseVisualProblemsInvolving Discontinuities , 1986 .

[32]  Bart M. ter Haar Romeny,et al.  Geometry-Driven Diffusion in Computer Vision , 1994, Computational Imaging and Vision.

[33]  Keith E. Price,et al.  Relaxation Matching Techniques-A Comparison , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Azriel Rosenfeld,et al.  Scene Labeling by Relaxation Operations , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[36]  Shmuel Peleg,et al.  A New Probabilistic Relaxation Scheme , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Jan-Olof Eklundh,et al.  Some properties of stochastic labeling procedures , 1982, Comput. Graph. Image Process..

[38]  Marcello Pelillo,et al.  On the dynamics of relaxation labeling processes , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).