Pattern Recognition

This book constitutes the refereed proceedings of the 24th Symposium of the German Association for Pattern Recognition, DAGM 2002, held in Zurich, Switzerland, in September 2002. The 74 revised papers presented were carefully reviewed and selected from more than 140 submissions. The papers address all current issues in pattern recognition. The book offers topical sections on tracking, segmentation, 3D shape, optical flow, recognition, and spherical images.

Tracking.- Multimodal Shape Tracking with Point Distribution Models.- Real-Time Tracking of Complex Objects Using Dynamic Interpretation Tree.- Posters I.- On Optimal Camera Parameter Selection in Kalman Filter Based Object Tracking.- Video-Based Handsign Recognition for Intuitive Human-Computer-Interaction.- Quality Enhancement of Reconstructed 3D Models Using Coplanarity and Constraints.- Multispectral Texture Analysis Using Interplane Sum- and Difference-Histograms.- Human Body Reconstruction from Image Sequences.- A Knowledge-Based System for Context Dependent Evaluation of Remote Sensing Data.- Empirically Convergent Adaptive Estimation of Grayvalue Structure Tensors.- Real Time Fusion of Motion and Stereo Using Flow/Depth Constraint for Fast Obstacle Detection.- Polygon Partition into Stable Regions.- Fast ICP Algorithms for Shape Registration.- Appearance Based Generic Object Modeling and Recognition Using Probabilistic Principal Component Analysis.- Skin Patch Detection in Real-World Images.- Logarithmic Tapering Graph Pyramid.- A New and Efficient Algorithm for Detecting the Corners in Digital Images.- Fast Implicit Active Contour Models.- Unsupervised Image Partitioning with Semidefinite Programming.- The Application of Genetic Algorithms in Structural Seismic Image Interpretation.- Unsupervised Image Clustering Using the Information Bottleneck Method.- Efficient Modification of the Central Weighted Vector Median Filter.- Fast Recovery of Piled Deformable Objects Using Superquadrics.- Analysis of Amperometric Biosensor Curves Using Hidden-Markov-Models.- Segmentation.- Unifying Registration and Segmentation for Multi-sensor Images.- Relations between Soft Wavelet Shrinkage and Total Variation Denoising.- Data Resampling for Path Based Clustering.- Statistical Image Sequence Processing for Temporal Change Detection.- Invited Talk.- Single-View Metrology: Algorithms and Applications (Invited Paper).- 3D Shape.- Shape from Single Stripe Pattern Illumination.- Disparity from Monogenic Phase.- A Probabilistic Approach to Building Roof Reconstruction Using Semantic Labelling.- Adaptive Pose Estimation for Different Corresponding Entities.- Posters II.- Properties of a Three-Dimensional Island Hierarchy for Segmentation of 3D Images with the Color Structure Code.- A Real Time Implementation of the Saliency-Based Model of Visual Attention on a SIMD Architecture.- Designing 3-D Nonlinear Diffusion Filters for High Performance Cluster Computing.- Hierarchical Primitives Based Contour Matching.- Application of the Tensor Voting Technique for Perceptual Grouping to Grey-Level Images.- Combined Forward and Backward Anisotropic Diffusion Filtering of Color Images.- Reinforcement Learning to Drive a Car by Pattern Matching.- Robust Point Correspondence for Image Registration Using Optimization with Extremal Dynamics.- Extending Active Shape Models to Incorporate a-priori Knowledge about Structural Variability.- A New Approach for Defect Detection in X-ray CT Images.- Object Tracking with an Adaptive Color-Based Particle Filter.- Analysis of Object Interactions in Dynamic Scenes.- Automatic Monocular 3D-Reconstruction of Indoor Environments Using Mobile Vehicles.- Dense Parameter Fields from Total Least Squares.- A Factorization-Based Method for Projective Reconstruction with Minimization of 2-D Reprojection Errors.- Head Detection and Localization from Sparse 3D Data.- Segmentation of the Date in Entries of Historical Church Registers.- Approach to Object Recognition by Learning Mobile Robots.- Ultrasonic Image Formation Using Wide Angle Sensor Arrays and Cross-Echo Evaluation.- Segmenting Microorganisms in Multi-modal Volumetric Datasets Using a Modified Watershed Transform.- Bayesian Kernel Tracking.- Optical Flow.- Nonlinear Matrix Diffusion for Optic Flow Estimation.- Combining the Advantages of Local and Global Optic Flow Methods.- Mixed OLS-TLS for the Estimation of Dynamic Processes with a Linear Source Term.- Motion Competition: Variational Integration of Motion Segmentation and Shape Regularization.- Recognition.- Fisher Light-Fields for Face Recognition across Pose and Illumination.- A Multimodal System for Object Learning.- Maximum Entropy and Gaussian Models for Image Object Recognition.- Evaluation of Confidence Measures for On-Line Handwriting Recognition.- Posters III.- ViRoom — Low Cost Synchronized Multicamera System and Its Self-calibration.- Real-Time Tracking Using Wavelet Representation.- Hands Tracking from Frontal View for Vision-Based Gesture Recognition.- Automatic Annotation of Tennis Video Sequences.- Fitting of Parametric Space Curves and Surfaces by Using the Geometric Error Measure.- Efficient, Active 3D Acquisition, Based on a Pattern-Specific Snake.- Appearance-Based 3-D Face Recognition from Video.- Direct Method for Motion Estimation: An Alternative to Decomposition of Planar Transformation Matrices.- A Feature-Driven Attention Module for an Active Vision System.- Analytic Reduction of the Kruppa Equations.- Query-Dependent Performance Optimization for Vocabulary-Supported Image Retrieval.- Spherical Images.- Multiscale Image Processing on the Sphere.- Polydioptric Cameras: New Eyes for Structure from Motion.