Computer Vision - ECCV 2004: 8th European Conference on Computer Vision, Prague, Czech Republic, May 11-14, 2004. Proceedings, Part II(3022 Lecture Notes in Computer Science)

The four-volume set comprising LNCS volumes 3021/3022/3023/3024 constitutes the refereed proceedings of the 8th European Conference on Computer Vision, ECCV 2004, held in Prague, Czech Republic, in May 2004.The 190 revised papers presented were carefully reviewed and selected from a total of 555 papers submitted. The four books span the entire range of current issues in computer vision. The papers are organized in topical sections on tracking; feature-based object detection and recognition; geometry; texture; learning and recognition; information-based image processing; scale space, flow, and restoration; 2D shape detection and recognition; and 3D shape representation and reconstruction.

Table of Contents:
Geometry.- A Generic Concept for Camera Calibration.- General Linear Cameras.- A Framework for Pencil-of-Points Structure-from-Motion.- What Do Four Points in Two Calibrated Images Tell Us about the Epipoles?.- Feature-Based Object Detection and Recognition II.- Dynamic Visual Search Using Inner-Scene Similarity: Algorithms and Inherent Limitations.- Weak Hypotheses and Boosting for Generic Object Detection and Recognition.- Object Level Grouping for Video Shots.- Posters II.- Statistical Symmetric Shape from Shading for 3D Structure Recovery of Faces.- Region-Based Segmentation on Evolving Surfaces with Application to 3D Reconstruction of Shape and Piecewise Constant Radiance.- Human Upper Body Pose Estimation in Static Images.- Automated Optic Disc Localization and Contour Detection Using Ellipse Fitting and Wavelet Transform.- View-Invariant Recognition Using Corresponding Object Fragments.- Variational Pairing of Image Segmentation and Blind Restoration.- Towards Intelligent Mission Profiles of Micro Air Vehicles: Multiscale Viterbi Classification.- Stitching and Reconstruction of Linear-Pushbroom Panoramic Images for Planar Scenes.- Audio-Video Integration for Background Modelling.- A Combined PDE and Texture Synthesis Approach to Inpainting.- Face Recognition from Facial Surface Metric.- Image and Video Segmentation by Anisotropic Kernel Mean Shift.- Colour Texture Segmentation by Region-Boundary Cooperation.- Spectral Solution of Large-Scale Extrinsic Camera Calibration as a Graph Embedding Problem.- Estimating Intrinsic Images from Image Sequences with Biased Illumination.- Structure and Motion from Images of Smooth Textureless Objects.- Automatic Non-rigid 3D Modeling from Video.- From a 2D Shape to a String Structure Using the Symmetry Set.- Extrinsic Camera Parameter Recovery from Multiple Image Sequences Captured by an Omni-Directional Multi-camera System.- Evaluation of Robust Fitting Based Detection.- Local Orientation Smoothness Prior for Vascular Segmentation of Angiography.- Weighted Minimal Hypersurfaces and Their Applications in Computer Vision.- Interpolating Novel Views from Image Sequences by Probabilistic Depth Carving.- Sparse Finite Elements for Geodesic Contours with Level-Sets.- Hierarchical Implicit Surface Joint Limits to Constrain Video-Based Motion Capture.- Separating Specular, Diffuse, and Subsurface Scattering Reflectances from Photometric Images.- Temporal Factorization vs. Spatial Factorization.- Tracking Aspects of the Foreground against the Background.- Example-Based Stereo with General BRDFs.- Adaptive Probabilistic Visual Tracking with Incremental Subspace Update.- On Refractive Optical Flow.- Matching Tensors for Automatic Correspondence and Registration.- A Biologically Motivated and Computationally Tractable Model of Low and Mid-Level Vision Tasks.- Appearance Based Qualitative Image Description for Object Class Recognition.- Consistency Conditions on the Medial Axis.- Normalized Cross-Correlation for Spherical Images.- Bias in the Localization of Curved Edges.- Texture.- Texture Boundary Detection for Real-Time Tracking.- A TV Flow Based Local Scale Measure for Texture Discrimination.- Spatially Homogeneous Dynamic Textures.- Synthesizing Dynamic Texture with Closed-Loop Linear Dynamic System.