Performance Characterization in Computer Vision

1. Front Matter

   Pages i-xvi

   PDF

2. General Issues

   1. Front Matter

      Pages 1-1

      PDF

   2. Experiences with Empirical Evaluation of Computer Vision Algorithms

      • Kevin W. Bowyer

      Pages 3-16

   3. Evaluation and Validation of Computer Vision Algorithms

      • Patrick Courtney

      Pages 17-28

   4. Databases for Performance Characterization

      • Adrian F. Clark, Patrick Courtney

      Pages 29-40

   5. Quality in Computer Vision

      • Radek Mařík

      Pages 41-51

3. Methodical Aspects

   1. Front Matter

      Pages 53-53

      PDF

   2. The Role of Theory in the Evaluation of Image Motion Algorithms

      • Steven S. Beauchemin, Ruzena Bajcsy

      Pages 55-67

   3. Motion Extraction

      • Luc Florack

      Pages 69-80

   4. Principles of Constructing a Performance Evaluation Protocol for Graphics Recognition Algorithms

      • Wenyin Liu, Dov Dori

      Pages 81-90

   5. Dissimilarity Measures between Gray-Scale Images as a Tool for Performance Assessment

      • Piero Zamperoni

      Pages 91-92

4. Statistical Aspects

   1. Front Matter

      Pages 93-93

      PDF

   2. Propagating Covariance in Computer Vision

      • Robert M. Haralick

      Pages 95-114

   3. Input Guided Performance Evaluation

      • Peter Meer, Bogdan Matei, Kyujin Cho

      Pages 115-124

   4. Uncertainty Propagation in Shape Reconstruction and Moving Object Detection from Optical Flow

      • Naoya Ohta

      Pages 125-135

5. Comparative Studies

   1. Front Matter

      Pages 137-137

      PDF

   2. Performance Characteristics of Low-Level Motion Estimators in Spatiotemporal Images

      • Bernd Jähne, Horst Haussecker

      Pages 139-152

   3. Evaluation of Numerical Solution Schemes for Differential Equations

      • Ryszard Kozera, Reinhard Klette

      Pages 153-166

   4. Experimental Comparative Evaluation of Feature Point Tracking Algorithms

      • Judit Verestóy, Dmitry Chetverikov

      Pages 167-178

6. Selected Methods and Algorithms

   1. Front Matter

      Pages 179-179

      PDF

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.

• 3D
• Analysis
• Computer Vision
• Image segmentation
• Optical flow
• Performance
• Stereo
• algorithms
• computer
• computer science
• database
• image processing

• Department of Computer Science, Tamaki Campus, The University of Auckland, Auckland, New Zealand

  Reinhard Klette

• Cognitive Systems Research Group, Department of Computer Science, University of Hamburg, Hamburg, Germany

  H. Siegfried Stiehl

• FB Informatik AB Kognitive Systeme, Universität Hamburg, Hamburg, Germany

  H. Siegfried Stiehl

• Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands

  Max A. Viergever, Koen L. Vincken

Policies and ethics