Performance Characterization in Computer Vision

I General Issues.- Experiences with Empirical Evaluation of Computer Vision Algorithms.- Evaluation and Validation of Computer Vision Algorithms.- Databases for Performance Characterization.- Quality in Computer Vision.- II Methodical Aspects.- The Role of Theory in the Evaluation of Image Motion Algorithms.- Motion Extraction.- Principles of Constructing a Performance Evaluation Protocol for Graphics Recognition Algorithms.- Dissimilarity Measures Between Gray-Scale Images as a Tool for Performance Assessment.- III Statistical Aspects.- Propagating Covariance in Computer Vision.- Input Guided Performance Evaluation.- Uncertainty Propagation in Shape Reconstruction and Moving Object Detection From Optical Flow.- IV Comparative Studies.- Performance Characteristics of Low-level Motion Estimators in Spatiotemporal Images.- Evaluation of Numerical Solution Schemes for Differential Equations.- Experimental Comparative Evaluation of Feature Point Tracking Algorithms.- V Selected Methods and Algorithms.- Evaluation of an Optical Flow Method for Measuring 2D and 3D Corn Seedling Growth.- Unsupervised Learning for Robust Texture Segmentation.- Confidence of Ground Control for Validating Stereo Terrain Reconstruction.- Performance Analysis of Shape Recovery by Random Sampling and Voting.- Multigrid Convergence Based Evaluation of Surface Approximations.- Sensitivity Analysis of Projective Geometry 3D Reconstruction.- A Systematic Approach to Error Sources for the Evaluation and Validation of a Binocular Vision System for Robot Control.- VI Domain-specific Evaluation: Medical Imaging.- Error Metrics for Quantitative Evaluation of Medical Image Segmentation.- Performance Characterization of Landmark Operators.- Model-based Evaluation of Image Segmentation Methods.