Energy Minimization Methods in Computer Vision and Pattern Recognition: International Workshop EMMCVPR'97 Venice, Italy, May 21–23, 1997 Proceedings

Description

This book constitutes the refereed proceedings of the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, EMMCVPR'97, held in Venice, Italy, in May 1997. The book presents 29 revised full papers selected from a total of 62 submissions. Also included are four full invited papers and a keynote paper by leading researchers. The volume is organized in sections on contours and deformable models, Markov random fields, deterministic methods, object recognition, evolutionary search, structural models, and applications. The volume is the first comprehensive documentation of the application of energy minimization techniques in the areas of compiler vision and pattern recognition. Uploaded by zhang. Energy Minimization Methods in Computer Vision and Pattern Recognition 1997 Cover Copyrights Preface Contents 2 Reliable computation and related games 3 Characterizing the distribution of completion shapes with corners using a mixture of random processes 4 Adaptive parametrically deformable contours 5 Kona A multi-junction detector using minimum description length principle 6 Restoration of SAR images using recovery of discontinuities and non-linear optimization 7 Geometrically deformable templates for shape-based segmentation and tracking in cardiac MR images 8 Image segmentation via energy minimization on partitions with connected components 9 Restoration of severely blurred high range images using stochastic and deterministic relaxation algorithms in compound gauss Markov random fields 10 Maximum likelihood estimation of Markov Random Field parameters using Markov Chain Monte Carlo algorithms 11 Noniterative manipulation of discrete energy-based models for image analysis 12 Unsupervised image segmentation using Markov Random Field models 13 Adaptive anisotropic parameter estimation in the weak membrane model 14 Twenty questions, focus of attention, and A A theoretical comparison of optimization strategies 15 Deterministic annealing for unsupervised texture segmentation 16 Self annealing Unifying deterministic annealing and relaxation labeling 17 Multidimensional scaling by deterministic annealing 18 Deterministic search strategies for relational graph matching 19 Object localization using color, texture and shape 20 Visual deconstruction Recognizing articulated objects 21 Optimization problems in statistical object recognition 22 Object recognition using stochastic optimization 23 Genetic algorithms for ambiguous labelling problems 24 Toward global solution to MAP image estimation Using Common structure of local solutions 25 Figure-ground separation A case study in energy minimization via evolutionary computing 26 Probabilistic relaxation Potential, relationships and open problems 27 A region-level motion-based graph representation and labeling for tracking a spatial image partition 28 An expectation-maximisation approach to graph matching 29 An energy minimization method for matching and comparing structured object representations 30 Consistent modeling of terrain and drainage using deformable models 31 Integration of confidence information by Markov Random Fields for reconstruction of underwater 3D acoustic images 32 Unsupervised segmentation applied on sonar images 33 SAR image registration and segmentation using an estimated DEM 34 Deformable templates for tracking and analysis of intravascular ultrasound sequences 35 Motion correspondence through energy minimization Author Index