Pattern Recognition

Sometimes milestones in the evolution of the DAGM Symposium become immediately visible. The Technical Committee decided to publish the symposium proceedings completely in English. As a consequence we successfully negotiated with Springer Verlag to publish in the international well accepted series "Lecture Notes in Computer Science". The quality of the contributions convinced the editors and the lectors. Thanks to them and to the authors. We received 105 acceptable, good, and even excellent manuscripts. We selected carefully, using three reviewers for each anonymized paper, 58 talks and posters. Our 41 reviewers had a hard job evaluating and especially rejecting contributions. We are grateful for the time and effort they spent in this task. The program committee awarded prizes to the best papers. We are much obliged to the generous sponsors. We had three invited talks from outstanding colleagues, namely Bernhard Nebel (Robot Soccer - A Challenge for Cooperative Action and Perception), Thomas Lengauer (Computational Biology - An Interdisciplinary Challenge for Computational Pattern Recognition), and Nassir Navab (Medical and Industrial Augmented Reality: Challenges for Real Time Vision, Computer Graphics, and Mobile Computing). N. Navab even wrote a special paper for this conference, which is included in the proceedings. We were proud that we could convince well known experts to offer tutorials to our participants: H. P. Seidel, Univ. Saarbrücken - A Framework for the Acquisition, Processing, and Interactive Display of High Quality 3D Models; S. Heuel, Univ. Bonn - Projective Geometry for Grouping and Orientation Tasks; G. Rigoll, Univ.

Inhalt

Image Analysis I.- Model-Based Image Segmentation Using local Self-Adapting Separation Criteria.- SIMBA - Search Images by Appearance.- Texture Defect Detection Using Invariant Textural Features.- Poster.- Segmentation of Spontaneously Splitting Figures into Overlapping Layers.- Writer Adaptation for Online Handwriting Recognition.- Blood Vessel Detection in Retinal Images by Shape-Based Multi-Threshold Probing.- Vehicle Detection in Aerial Images Using Generic Features, Grouping, and Context.- Reconstruction of Image Structure in Presence of Specular Reflections.- 3D-Gathering & Visualization.- Spatio-temporal Analysis of Human Faces Using Multi-Resolution Subdivision Surfaces.- 3D Anisotropic Diffusion Filtering for Enhancing Noisy Actin Filament Fluorescence Images.- A Point Set Registration Algorithm Using a Motion Model Based on Thin-Plate Splines and Point Clustering.- Poster.- Optimal Camera Orientation from Points and Straight Lines.- Points, Lines, and Planes and Their Optimal Estimation.- A Probabilistic Approach to Simultaneous Segmentation, Object Recognition, 3D Localization, and Tracking Using Stereo.- Improving the Robustness in Extracting 3D Point Landmarks Based on Deformable Models.- Efficient 3D Vertex Detection in Range Images Acquired with a Laser Sensor.- Image Processing.- Scale Adaptive Filtering Derived from the Laplace Equation.- One-Sided Stability of Medial Axis Transform.- Poster.- Robust Line Detection in Historical Church Registers.- Similarity Measures for Occlusion, Clutter, and Illumination Invariant Object Recognition.- Affine Point Pattern Matching.- Image Sequence Analysis.- Surface Expansion from Range Data Sequences.- Illumination-invariant Change Detection Using a Statistical Colinearity Criterion.- Memorizing Visual Knowledge for Assembly Process Monitoring.- Poster.- Wavelet Subspace Method for Real-Time Face Tracking.- Reliable Estimates of the Sea Surface Heat Flux from Image Sequences.- Real-Time Motion Based Vehicle Segmentation in Traffic Lanes.- Detection and Tracking of Moving Objects for Mosaic Image Generation.- Acquiring Robust Representations for Recognition from Image Sequences.- Image Sequence Analysis of Satellite NO2 Concentration Maps.- Root Growth Measurements in Object Coordinates.- Classification.- On Fusion of Multiple Views for Active Object Recognition.- Probabilistic Discriminative Kernel Classifiers for Multi-Class Problems.- Appearance-Based Statistical Object Recognition by Heterogeneous Background and Occlusions.- Combining Independent Component Analysis and Self-Organizing Maps for Cell Image Classification.- Poster.- Nonlinear Shape Statistics via Kernel Spaces.- Normalization in Support Vector Machines.- Solving Multi-Class Pattern Recognition Problems with Tree-Structured Support Vector Machines.- Facial Expression Recognition with Pseudo-3D Hidden Markov Models.- Active Vision.- Towards Online Pose Measurement for Robots.- Optimal Camera Parameter Selection for State Estimation with Applications in Object Recognition.- View Planning for Unknown Indoor Scenes Based on a Cost Benefit Analysis.- Cooperative Probabilistic State Estimation for Vision-Based Autonomous Soccer Robots.- Poster.- A New Contour-Based Approach to Object Recognition for Assembly Line Robots.- Where Is the Hole Punch? Object Localization Capabilities on a Specific Bureau Task.- Image Analysis II.- Phenomenology-Based Segmentation of InSAR Data for Building Detection.- Convex Relaxations for Binary Image Partitioning and Perceptual Grouping.- Evaluation of Convex Optimization Techniques for the Weighted Graph-Matching Problem in Computer Vision.- Learning Shape Models from Examples.- 3D-Reconstruction.- Shape from 2D Edge Gradients.- Robust Obstacle Detection from Stereoscopic Image Sequences Using Kalman Filtering.- 3D Model Retrieval with Spherical Harmonics and Moments.- Poster.- Least Squares Orthogonal Distance Fitting of Implicit Curves and Surfaces.- Segmentation of Tubular Structures in 3D Images Using a Combination of the Hough Transform and a Kalman Filter.- Pros and Cons of Euclidean Fitting.- Interaction Virtual with Real Worlds.- Placing Arbitrary Objects in a Real Scene Using a Color Cube for Pose Estimation.- Detecting, Tracking, and Interpretation of a Pointing Gesture by an Overhead View Camera.- Poster.- Recognition of the German Visemes Using Multiple Feature Matching.- Invited Talk.- Medical & Industrial Augmented Reality: Challenges for Real-Time Vision, Computer Graphics and Mobile Computing.