Computer Analysis of Images and Patterns: 15th International Conference, CAIP 2013, York, UK, August 27-29, 2013, Proceedings, Part I

ISBN-13: 9783642402609 / Angielski / Miękka / 2013 / 601 str.

Richard Wilson;Edwin Hancock;Adrian Bors

Opis

The two volume set LNCS 8047 and 8048 constitutes the refereed proceedings of the 15th International Conference on Computer Analysis of Images and Patterns, CAIP 2013, held in York, UK, in August 2013. The 142 papers presented were carefully reviewed and selected from 243 submissions. The scope of the conference spans the following areas: 3D TV, biometrics, color and texture, document analysis, graph-based methods, image and video indexing and database retrieval, image and video processing, image-based modeling, kernel methods, medical imaging, mobile multimedia, model-based vision approaches, motion analysis, natural computation for digital imagery, segmentation and grouping, and shape representation and analysis.

Spis treści

Table of Contents – Part I.-Biomedical Imaging: A Computer Vision Perspective.- Rapid Localisation and Retrieval of Human Actions with Relevance Feedback.- Deformable Shape Reconstruction from Monocular Video with Manifold Forests.- Multi-SVM Multi-instance Learning for Object-Based Image Retrieval.- Maximizing Edit Distance Accuracy with Hidden Conditional Random Fields.- Background Recovery by Fixed-Rank Robust Principal Component Analysis.- Manifold Learning and the Quantum Jensen-Shannon Divergence Kernel.- Spatio-temporal Manifold Embedding for Nearly-Repetitive Contents in a Video Stream.- Spatio-temporal Human Body Segmentation from Video Stream.- Sparse Depth Sampling for Interventional 2-D/3-D Overlay: Theoretical Error Analysis and Enhanced Motion Estimation.- Video Synopsis Based on a Sequential Distortion Minimization Method.- A Graph Embedding Method Using the Jensen-Shannon Divergence.- Mixtures of Radial Densities for Clustering Graph.- Analysis of Wave Packet Signature of a Graph.- Hearing versus Seeing Identical Twins.- Voting Strategies for Anatomical Landmark Localization Using the Implicit Shape Model.- Evaluating the Impact of Color on Texture Recognition.- Temporal Self-Similarity for Appearance-Based Action Recognition in Multi-View Setups.- Adaptive Pixel/Patch-Based Stereo Matching for 2D Face Recognition.- A Machine Learning Approach for Displaying Query Results in Search Engines.- A New Pixel-Based Quality Measure for Segmentation Algorithms Integrating Precision, Recall and Specificity.- A Novel Border Identification Algorithm Based on an “Anti-Bayesian” Paradigm.- Assessing the Effect of Crossing Databases on Global and Local Approaches for Face Gender Classification.- BRDF Estimation for Faces from a Sparse Dataset Using a Neural Network.- Comparison of Leaf Recognition by Moments and Fourier Descriptors.- Dense Correspondence of Skull Models by Automatic Detection of Anatomical Landmarks.- Detection of Visual Defects in Citrus Fruits: Multivariate Image Analysis vs Graph Image Segmentation.- Domain Adaptation Based on Eigen-Analysis and Clustering, for Object Categorization.- Estimating Clusters Centres Using Support Vector Machine: An Improved Soft Subspace Clustering Algorithm.- Fast Approximate Minimum Spanning Tree Algorithm Based on K-Means.- Fast EM Principal Component Analysis Image Registration Using Neighbourhood Pixel Connectivity.- Fast Unsupervised Segmentation Using Active Contours and Belief Functions.- Flexible Hypersurface Fitting with RBF Kernels.- Gender Classification Using Facial Images and Basis Pursuit.- Graph Clustering through Attribute Statistics Based Embedding.- Graph-Based Regularization of Binary Classifiers for Texture Segmentation.- Hierarchical Annealed Particle Swarm Optimization for Articulated Object Tracking.- High-Resolution Feature Evaluation Benchmark.- Fully Automatic Segmentation of AP Pelvis X-rays via Random Forest Regression and Hierarchical Sparse Shape Composition.- Language Adaptive Methodology for Handwritten Text Line Segmentation.- Learning Geometry-Aware Kernels in a Regularization Framework.- Motion Trend Patterns for Action Modelling and Recognition.- On Achieving Near-Optimal “Anti-Bayesian” Order Statistics-Based Classification for Asymmetric Exponential Distributions.- Optimizing Feature Selection through Binary Charged System Search.- Outlines of Objects Detection by Analogy.- PaTHOS: Part-Based Tree Hierarchy for Object Segmentation.- Tracking System with Re-identification Using a Graph Kernels Approach.- Recognizing Human-Object Interactions Using Sparse Subspace Clustering.- Scale-Space Clustering on the Sphere.- The Importance of Long-Range Interactions to Texture Similarity.- Unsupervised Dynamic Textures Segmentation.- Voting Clustering and Key Points Selection.- Motor Pump Fault Diagnosis with Feature Selection and Levenberg-Marquardt Trained Feedforward Neural Network.- Unobtrusive Fall Detection at Home Using Kinect Sensor.- “BAM!” Depth-Based Body Analysis in Critical Care.- 3-D Feature Point Matching for Object Recognition Based on Estimation of Local Shape Distinctiveness.- 3D Human Tracking from Depth Cue in a Buying Behavior Analysis Context.- A New Bag of Words LBP (BoWL) Descriptor for Scene Image Classification.-Accurate Scale Factor Estimation in 3D Reconstruction.- Affine Colour Optical Flow Computation.- Can Salient Interest Regions Resume Emotional Impact of an Image?.- Contraharmonic Mean Based Bias Field Correction in MR Images.- Correlation between Biopsy Confirmed Cases and Radiologist’s Annotations in the Detection of Lung Nodules by Expanding the Diagnostic Database Using Content Based Image Retrieval.- Enforcing Consistency of 3D Scenes with Multiple Objects Using Shape-from-Contours.- Expectation Conditional Maximization-Based Deformable Shape Registration.- Facial Expression Recognition with Regional Features Using Local Binary Patterns.- Global Image Registration Using Random Projection and Local Linear Method.- Image Segmentation by Oriented Image Foresting Transform with Geodesic Star Convexity.- Multi-run 3D Streetside Reconstruction from a Vehicle.- Interactive Image Segmentation via Graph Clustering and Synthetic Coordinates Modeling.