Vai al contenuto principale della pagina
Titolo: | Energy Minimization Methods in Computer Vision and Pattern Recognition [[electronic resource] ] : 7th International Conference, EMMCVPR 2009, Bonn, Germany, August 24-27, 2009, Proceedings / / edited by Daniel Cremers, Yuri Boykov, Andrew Blake, Frank R. Schmidt |
Pubblicazione: | Berlin, Heidelberg : , : Springer Berlin Heidelberg : , : Imprint : Springer, , 2009 |
Edizione: | 1st ed. 2009. |
Descrizione fisica: | 1 online resource (X, 494 p.) |
Disciplina: | 006.6 |
006.37 | |
Soggetto topico: | Optical data processing |
Pattern recognition | |
Computer software—Reusability | |
Algorithms | |
Data mining | |
Image Processing and Computer Vision | |
Pattern Recognition | |
Performance and Reliability | |
Algorithm Analysis and Problem Complexity | |
Computer Imaging, Vision, Pattern Recognition and Graphics | |
Data Mining and Knowledge Discovery | |
Persona (resp. second.): | CremersDaniel |
BoykovYuri | |
BlakeAndrew | |
SchmidtFrank R | |
Note generali: | Includes index. |
Nota di contenuto: | Discrete Optimization and Markov Random Fields -- Multi-label Moves for MRFs with Truncated Convex Priors -- Detection and Segmentation of Independently Moving Objects from Dense Scene Flow -- Efficient Global Minimization for the Multiphase Chan-Vese Model of Image Segmentation -- Bipartite Graph Matching Computation on GPU -- Pose-Invariant Face Matching Using MRF Energy Minimization Framework -- Parallel Hidden Hierarchical Fields for Multi-scale Reconstruction -- General Search Algorithms for Energy Minimization Problems -- Partial Differential Equations -- Complex Diffusion on Scalar and Vector Valued Image Graphs -- A PDE Approach to Coupled Super-Resolution with Non-parametric Motion -- On a Decomposition Model for Optical Flow -- A Schrödinger Wave Equation Approach to the Eikonal Equation: Application to Image Analysis -- Computing the Local Continuity Order of Optical Flow Using Fractional Variational Method -- A Local Normal-Based Region Term for Active Contours -- Segmentation and Tracking -- Hierarchical Pairwise Segmentation Using Dominant Sets and Anisotropic Diffusion Kernels -- Tracking as Segmentation of Spatial-Temporal Volumes by Anisotropic Weighted TV -- Complementary Optic Flow -- Parameter Estimation for Marked Point Processes. Application to Object Extraction from Remote Sensing Images -- Three Dimensional Monocular Human Motion Analysis in End-Effector Space -- Robust Segmentation by Cutting across a Stack of Gamma Transformed Images -- Shape Optimization and Registration -- Integrating the Normal Field of a Surface in the Presence of Discontinuities -- Intrinsic Second-Order Geometric Optimization for Robust Point Set Registration without Correspondence -- Geodesics in Shape Space via Variational Time Discretization -- Image Registration under Varying Illumination: Hyper-Demons Algorithm -- Hierarchical Vibrations: A Structural Decomposition Approach for Image Analysis -- Inpainting and Image Denoising -- Exemplar-Based Interpolation of Sparsely Sampled Images -- A Variational Framework for Non-local Image Inpainting -- Image Filtering Driven by Level Curves -- Color Image Restoration Using Nonlocal Mumford-Shah Regularizers -- Reconstructing Optical Flow Fields by Motion Inpainting -- Color and Texture -- Color Image Segmentation in a Quaternion Framework -- Quaternion-Based Color Image Smoothing Using a Spatially Varying Kernel -- Locally Parallel Textures Modeling with Adapted Hilbert Spaces -- Global Optimal Multiple Object Detection Using the Fusion of Shape and Color Information -- Statistics and Learning -- Human Age Estimation by Metric Learning for Regression Problems -- Clustering-Based Construction of Hidden Markov Models for Generative Kernels -- Boundaries as Contours of Optimal Appearance and Area of Support. |
Titolo autorizzato: | Energy Minimization Methods in Computer Vision and Pattern Recognition |
ISBN: | 3-642-03641-4 |
Formato: | Materiale a stampa |
Livello bibliografico | Monografia |
Lingua di pubblicazione: | Inglese |
Record Nr.: | 996465647803316 |
Lo trovi qui: | Univ. di Salerno |
Opac: | Controlla la disponibilità qui |