A trained spin-glass model for grouping of image primitives

A method is presented that uses grouping to improve local classification of image primitives. The grouping process is based upon a spin-glass system, where the image primitives are treated as possessing a spin. The system is subject to an energy functional consisting of a local and a bilocal part, allowing interaction between the image primitives. Instead of defining the state of lowest energy as the grouping result, the mean state of the system is taken. In this way, instabilities caused by multiple minima in the energy are being avoided. The means of the spins are taken as the a posteriori probabilities for the grouping result. In the paper, it is shown how the energy functional can be learned from example data. The energy functional is defined in such a way that, in case of no interactions between the elements, the means of the spins equal the a priori local probabilities. The grouping process enables the fusion of the a priori local and bilocal probabilities into the a posteriori probabilities. The method is illustrated both on grouping of line elements in synthetic images and on vessel detection in retinal fundus images.

[1]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[2]  David H. Eberly,et al.  Ridges in Image and Data Analysis , 1996, Computational Imaging and Vision.

[3]  J. Marroquín,et al.  A Markovian Random field of piecewise straight lines , 1989, Biological Cybernetics.

[4]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[5]  Pietro Perona,et al.  A Factorization Approach to Grouping , 1998, ECCV.

[6]  Duncan Fyfe Gillies,et al.  Extracting contours by perceptual grouping , 1992, Image Vis. Comput..

[7]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  C. Metz.  Basic principles of ROC analysis. , 1978, Seminars in nuclear medicine.

[9]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[10]  Gérard G. Medioni,et al.  Inferring global perceptual contours from local features , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[11]  D. Greig,et al.  Exact Maximum A Posteriori Estimation for Binary Images , 1989 .

[12]  Radu Horaud,et al.  Figure-Ground Discrimination: A Combinatorial Optimization Approach , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Lance R. Williams,et al.  Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience , 1997, Neural Computation.

[14]  Ehl Emile Aarts,et al.  Simulated annealing and Boltzmann machines , 2003 .

[15]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Emile H. L. Aarts,et al.  Simulated annealing and Boltzmann machines - a stochastic approach to combinatorial optimization and neural computing , 1990, Wiley-Interscience series in discrete mathematics and optimization.

[17]  Steven W. Zucker,et al.  Trace Inference, Curvature Consistency, and Curve Detection , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

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

[19]  Tomaso Poggio,et al.  Probabilistic Solution of Ill-Posed Problems in Computational Vision , 1987 .

[20]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[21]  Yair Weiss,et al.  Segmentation using eigenvectors: a unifying view , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[22]  Max A. Viergever,et al.  A Computational Method for Segmenting Topological Point-Sets and Application to Image Analysis , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Luc Florack,et al.  Image Structure , 1997, Computational Imaging and Vision.

[24]  Steven W. Zucker,et al.  Radial Projection: An Efficient Update Rule for Relaxation Labeling , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[26]  Robert B. Fisher,et al.  Model-driven grouping and recognition of generic object parts from single images , 1997, Robotics Auton. Syst..

[27]  Sunil Arya,et al.  An optimal algorithm for approximate nearest neighbor searching fixed dimensions , 1998, JACM.

[28]  Thierry Pun,et al.  Electromagnetic Models for Perceptual Grouping , 1992, Advances in Machine Vision.

[29]  H. Niemann,et al.  From Markov Random Fields to Associative Memories and Back: Spin-Glass Markov Random Fields , 2007 .

[30]  Max A. Viergever,et al.  Image segmentation and object recognition by Bayesian grouping , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).