Performance Characterization in Computer Vision

ISBN-13: 9789048154876 / Angielski / Miękka / 2010 / 317 str.

Reinhard Klette; H. Siegfried Stiehl; Max A. Viergever

Opis

This edited volume addresses a subject which has been discussed inten- sively in the computer vision community for several years. Performance characterization and evaluation of computer vision algorithms are of key importance, particularly with respect to the configuration of reliable and ro- bust computer vision systems as well as the dissemination of reconfigurable systems in novel application domains. Although a plethora of literature on this subject is available for certain' areas of computer vision, the re- search community still faces a lack of a well-grounded, generally accepted, and--eventually-standardized methods. The range of fundamental problems encoIl passes the value of synthetic images in experimental computer vision, the selection of a representative set of real images related to specific domains and tasks, the definition of ground truth given different tasks and applications, the design of experimental test- beds, the analysis of algorithms with respect to general characteristics such as complexity, resource consumption, convergence, stability, or range of admissible input data, the definition and analysis of performance measures for classes of algorithms, the role of statistics-based performance measures, the generation of data sheets with performance measures of algorithms sup- porting the system engineer in his configuration problem, and the validity of model assumptions for specific applications of computer vision.

Spis treści

Contributors. Preface. I: General issues. Experiences with Empirical Evaluation of Computer Vision Algorithms; K.W. Bowyer. Evaluation and Validation of Computer Vision Algorithms; P. Courtney. Databases for Performance Characterization; A.F. Clark, P. Courtney. Quality in Computer Vision; R. Marík. II: Methodical Aspects. The Role of Theory in the Evaluation of Image Motion Algorithms; S.S. Beauchemin, R. Bajcsy. Motion Extraction; L. Florack. Principles of Constructing a Performance Evaluation Protocol for Graphics Recognition Algorithms; L. Wenyin, D. Dori. Dissimilarity Measures Between Gray-Scale Images as a Tool for Performance Assessment; P. Zamperoni. III: Statistical Aspects. Propagating Covariance in Computer Vision; R.M. Haralick. Input Guided Performance Evaluation; P. Meer, et al. Uncertainty Propagation in Shape Reconstruction and Moving Object Detection From Optical Flow; N. Ohta. IV: Comparative Studies. Performance Characteristics of Low-level Motion Estimators in Spatiotemporal Images; B. Jähne, H. Haussecker. Evaluation of Numerical Solution Schemes for Differential Equations; R. Kozera, R. Klette. Experimental Comparative Evaluation of Feature Point Tracking Algorithms; J. Verestóy, D. Chetverikov. V: Selected Methods and Algorithms. Evaluation of an Optical Flow Method for Measuring 2D and 3D Corn Seedling Growth; J.L. Barron, A. Liptay. Unsupervised Learning for Robust Texture Segmentation; J.M. Buhmann, J. Puzicha. Confidence of Ground Control for Validating Stereo Terrain Reconstruction; G. Gimel'farb. Performance Analysis of Shape Recovery by Random Sampling and Voting; A. Imiya, K. Kawamoto. MultigridConvergence Based Evaluation of Surface Approximations; R. Klette, et al. Sensitivity Analysis of Projective Geometry 3D Reconstruction; M. Petrou, et al. A Systematic Approach to Error Sources for the Evaluation and Validation of a Binocular Vision System for Robot Control; D. Richter. VI: Domain-specific Evaluation: Medical Imaging. Error Metrics for Quantitative Evaluation of Medical Image Segmentation; W.J. Niessen, et al. Performance Characterization of Landmark Operators; K. Rohr, et al. Model-based Evaluation of Image Segmentation Methods; K.L. Vincken, et al. Index.