Energy Minimization Methods in Computer Vision and Pattern Recognition -

Energy Minimization Methods in Computer Vision and Pattern Recognition

4th International Workshop, EMMCVPR 2003, Lisbon, Portugal, July 7-9, 2003, Proceedings
Buch | Softcover
XI, 534 Seiten
2003 | 2003
Springer Berlin (Verlag)
978-3-540-40498-9 (ISBN)
106,99 inkl. MwSt
This volume consists of the 33 papers presented at the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2003)which was held at Instituto Superior T ecnico (IST), the - gineeringSchooloftheTechnicalUniversityofLisbon,PortugalduringJuly7 9, 2003.Thisworkshopwasthefourthinthe serieswhichstartedwithEMMCVPR 1997 held in Venice, Italy in May 1997 and continued with EMMCVPR 1999 held in York, UK in July 1999 and EMMCVPR 2001 held in Sophia-Antipolis, France in September 2001. Many problems in computer vision and pattern recognition (CVPR) are couchedintheframeworkofoptimization.Theminimizationofaglobalquantity, often referred to as the energy, forms the bulwark of most approachesin CVPR. Disparate approaches,such as discrete and probabilistic formulations on the one hand and continuous, deterministic strategies on the other, often have optimi- tion or energy minimization as a common theme. Instances of energy minimi- tion arise in Gibbs/Markov modeling, Bayesian decision theory, geometric and variational approaches and in areas in CVPR such as object recognition and - trieval, image segmentation, registration, reconstruction, classi?cation and data mining. The aim of the EMMCVPR workshops is to bring together researchers with interests in these disparate areas of CVPR but with an underlying commitment to some form of energy minimization. Although the subject is traditionally well representedinmajorinternationalconferencesonCVPR,thisworkshopprovides a forum wherein researchers can report their recent work and engage in more informal discussions.

Unsupervised Learning and Matching.- Stochastic Search for Optimal Linear Representations of Images on Spaces with Orthogonality Constraints.- Local PCA for Strip Line Detection and Thinning.- Curve Matching Using the Fast Marching Method.- EM Algorithm for Clustering an Ensemble of Graphs with Comb Matching.- Information Force Clustering Using Directed Trees.- Watershed-Based Unsupervised Clustering.- Probabilistic Modelling.- Active Sampling Strategies for Multihypothesis Testing.- Likelihood Based Hierarchical Clustering and Network Topology Identification.- Learning Mixtures of Tree-Unions by Minimizing Description Length.- Image Registration and Segmentation by Maximizing the Jensen-Rényi Divergence.- Asymptotic Characterization of Log-Likelihood Maximization Based Algorithms and Applications.- Maximum Entropy Models for Skin Detection.- Hierarchical Annealing for Random Image Synthesis.- On Solutions to Multivariate Maximum ?-Entropy Problems.- Segmentation and Grouping.- Semi-supervised Image Segmentation by Parametric Distributional Clustering.- Path Variation and Image Segmentation.- A Fast Snake Segmentation Method Applied to Histopathological Sections.- A Compositionality Architecture for Perceptual Feature Grouping.- Using Prior Shape and Points in Medical Image Segmentation.- Separating a Texture from an Arbitrary Background Using Pairwise Grey Level Cooccurrences.- Shape Modelling.- Surface Recovery from 3D Point Data Using a Combined Parametric and Geometric Flow Approach.- Geometric Analysis of Continuous, Planar Shapes.- Curvature Vector Flow to Assure Convergent Deformable Models for Shape Modelling.- Definition of a Signal-to-Noise Ratio for Object Segmentation Using Polygonal MDL-Based Statistical Snakes.- Restoration and Reconstruction.-Minimization of Cost-Functions with Non-smooth Data-Fidelity Terms to Clean Impulsive Noise.- A Fast GEM Algorithm for Bayesian Wavelet-Based Image Restoration Using a Class of Heavy-Tailed Priors.- Diffusion Tensor MR Image Restoration.- A MAP Estimation Algorithm Using IIR Recursive Filters.- Estimation of Rank Deficient Matrices from Partial Observations: Two-Step Iterative Algorithms.- Contextual and Non-combinatorial Approach to Feature Extraction.- Graphs and Graph-Based Methods.- Generalizing the Motzkin-Straus Theorem to Edge-Weighted Graphs, with Applications to Image Segmentation.- Generalized Multi-camera Scene Reconstruction Using Graph Cuts.- Graph Matching Using Spectral Seriation.

Erscheint lt. Verlag 26.6.2003
Reihe/Serie Lecture Notes in Computer Science
Zusatzinfo XI, 534 p.
Verlagsort Berlin
Sprache englisch
Maße 155 x 235 mm
Gewicht 776 g
Themenwelt Informatik Grafik / Design Digitale Bildverarbeitung
Schlagworte 3D • algorithm • Algorithm analysis and problem complexity • Algorithmic Learning • algorithms • Clustering • Cognition • computer vision • Energy Minimization • expectation–maximization algorithm • Expectation-Maximization algorithm • Geometric Computing • hidden Markov models • Image Analysis • image classification • Markov Random Fields • Neural networks • optical flow • Optimization • pattern recognition • Textur
ISBN-10 3-540-40498-8 / 3540404988
ISBN-13 978-3-540-40498-9 / 9783540404989
Zustand Neuware
Haben Sie eine Frage zum Produkt?
Mehr entdecken
aus dem Bereich
Modelle für 3D-Druck und CNC entwerfen

von Lydia Sloan Cline

Buch | Softcover (2022)
dpunkt (Verlag)
34,90
Einstieg und Praxis

von Werner Sommer; Andreas Schlenker

Buch | Softcover (2023)
Markt + Technik (Verlag)
19,95