Color in Computer Vision: Fundamentals and Applications

Color in Computer Vision: Fundamentals and Applications

by Theo Gevers, Arjan Gijsenij, Joost van de Weijer, Jan-Mark Geusebroek
Released September 2012
Publisher(s): Wiley
ISBN: 9780470890844

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

While the field of computer vision drives many of today's digital technologies and communication networks, the topic of color has emerged only recently in most computer vision applications. One of the most extensive works to date on color in computer vision, this book provides a complete set of tools for working with color in the field of image understanding.

Based on the authors' intense collaboration for more than a decade and drawing on the latest thinking in the field of computer science, the book integrates topics from color science and computer vision, clearly linking theories, techniques, machine learning, and applications. The fundamental basics, sample applications, and downloadable versions of the software and data sets are also included. Clear, thorough, and practical, Color in Computer Vision explains:

  • Computer vision, including color-driven algorithms and quantitative results of various state-of-the-art methods

  • Color science topics such as color systems, color reflection mechanisms, color invariance, and color constancy

  • Digital image processing, including edge detection, feature extraction, image segmentation, and image transformations

  • Signal processing techniques for the development of both image processing and machine learning

  • Robotics and artificial intelligence, including such topics as supervised learning and classifiers for object and scene categorization Researchers and professionals in computer science, computer vision, color science, electrical engineering, and signal processing will learn how to implement color in computer vision applications and gain insight into future developments in this dynamic and expanding field.

    •

    Table of contents

    1. Cover
    2. Copyright
    3. Series
    4. Title Page
    5. Preface
    6. Chapter 1: Introduction
      1. 1.1 From Fundamental to Applied
      2. 1.2 Part I: Color Fundamentals
      3. 1.3 Part II: Photometric Invariance
      4. 1.4 Part III: Color Constancy
      5. 1.5 Part IV: Color Feature Extraction
      6. 1.6 Part V: Applications
      7. 1.7 Summary
    7. Part I: Color Fundamentals
      1. Chapter 2: Color Vision
        1. 2.1 Introduction
        2. 2.2 Stages of Color Information Processing
        3. 2.3 Chromatic Properties of the Visual System
        4. 2.4 Summary
      2. Chapter 3: Color Image Formation
        1. 3.1 Lambertian Reflection Model
        2. 3.2 Dichromatic Reflection Model
        3. 3.3 Kubelka–Munk Model
        4. 3.4 The Diagonal Model
        5. 3.5 Color Spaces
        6. 3.6 Summary
    8. Part II: Photometric Invariance
      1. Chapter 4: Pixel-Based Photometric Invariance
        1. 4.1 Normalized Color Spaces
        2. 4.2 Opponent Color Spaces
        3. 4.3 The HSV Color Space
        4. 4.4 Composed Color Spaces
        5. 4.5 Noise Stability and Histogram Construction
        6. 4.6 Application: Color-Based Object Recognition
        7. 4.7 Summary
      2. Chapter 5: Photometric Invariance from Color Ratios
        1. 5.1 Illuminant Invariant Color Ratios
        2. 5.2 Illuminant Invariant Edge Detection
        3. 5.3 Blur-Robust and Color Constant Image Description
        4. 5.4 Application: Image Retrieval Based on Color Ratios
        5. 5.5 Summary
      3. Chapter 6: Derivative-Based Photometric Invariance
        1. 6.1 Full Photometric Invariants
        2. 6.2 Quasi-Invariants
        3. 6.3 Summary
      4. Chapter 7: Photometric Invariance by Machine Learning
        1. 7.1 Learning from Diversified Ensembles
        2. 7.2 Temporal Ensemble Learning
        3. 7.3 Learning Color Invariants for Region Detection
        4. 7.4 Experiments
        5. 7.5 Summary
    9. Part III: Color Constancy
      1. Chapter 8: Illuminant Estimation and Chromatic Adaptation
        1. 8.1 Illuminant Estimation
        2. 8.2 Chromatic Adaptation
      2. Chapter 9: Color Constancy Using Low-level Features
        1. 9.1 General Gray-World
        2. 9.2 Gray-Edge
        3. 9.3 Physics-Based Methods
        4. 9.4 Summary
      3. Chapter 10: Color Constancy Using Gamut-Based Methods
        1. 10.1 Gamut Mapping Using Derivative Structures
        2. 10.2 Combination of Gamut Mapping Algorithms
        3. 10.3 Summary
      4. Chapter 11: Color Constancy Using Machine Learning
        1. 11.1 Probabilistic Approaches
        2. 11.2 Combination Using Output Statistics
        3. 11.3 Combination Using Natural Image Statistics
        4. 11.4 Methods Using Semantic Information
        5. 11.5 Summary
      5. Chapter 12: Evaluation of Color Constancy Methods
        1. 12.1 Data Sets
        2. 12.2 Performance Measures
        3. 12.3 Experiments
        4. 12.4 Summary
    10. Part IV: Color Feature Extraction
      1. Chapter 13: Color Feature Detection
        1. 13.1 The Color Tensor
        2. 13.2 Color Saliency
        3. 13.3 Conclusions
      2. Chapter 14: Color Feature Description
        1. 14.1 Gaussian Derivative-Based Descriptors
        2. 14.2 Discriminative Power
        3. 14.3 Level of Invariance
        4. 14.4 Information Content
        5. 14.5 Summary
      3. Chapter 15: Color Image Segmentation
        1. 15.1 Color Gabor Filtering
        2. 15.2 Invariant Gabor Filters Under Lambertian Reflection
        3. 15.3 Color-Based Texture Segmentation
        4. 15.4 Material Recognition Using Invariant Anisotropic Filtering
        5. 15.5 Color Invariant Codebooks and Material-Specific Adaptation
        6. 15.6 Experiments
        7. 15.7 Image Segmentation by Delaunay Triangulation
        8. 15.8 Summary
    11. Part V: Applications
      1. Chapter 16: Object and Scene Recognition
        1. 16.1 Diagonal Model
        2. 16.2 Color SIFT Descriptors
        3. 16.3 Object and Scene Recognition
        4. 16.4 Results
        5. 16.5 Summary
      2. Chapter 17: Color Naming
        1. 17.1 Basic Color Terms
        2. 17.2 Color Names from Calibrated Data
        3. 17.3 Color Names from Uncalibrated Data
        4. 17.4 Experimental Results
        5. 17.5 Conclusions
      3. Chapter 18: Segmentation of Multispectral Images
        1. 18.1 Reflection and Camera Models
        2. 18.2 Photometric Invariant Distance Measures
        3. 18.3 Error Propagation
        4. 18.4 Photometric Invariant Region Detection by Clustering
        5. 18.5 Experiments
        6. 18.6 Summary
    12. Citation Guidelines
    13. References
    14. Index

    Product information

    • Title: Color in Computer Vision: Fundamentals and Applications
    • Author(s): Theo Gevers, Arjan Gijsenij, Joost van de Weijer, Jan-Mark Geusebroek
    • Release date: September 2012
    • Publisher(s): Wiley
    • ISBN: 9780470890844