Color In Computer Vision: Fundamentals And Applications

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.

THEO GEVERS, PhD, is Professor of Computer Science in the Intelligent Systems Lab at the University of Amsterdam in the Netherlands, and CVC Full Professor at the Computer Vision Center in Barcelona, Spain.

ARJAN GIJSENIJ, PhD, was a postdoctoral researcher in the Intelligent Systems Lab at the University of Amsterdam, the Netherlands, while writing this book.

JOOST van de WEIJER, PhD, is a Ramon y Cajal Fellow at the Universitat Autonoma de Barcelona, Spain.

JAN-MARK GEUSEBROEK, PhD, was assistant professor in the Intelligent Systems Lab at the University of Amsterdam, the Netherlands, while writing this book.

Preface xv
1 Introduction 11.1 From Fundamental to Applied 21.2 Part I: Color Fundamentals 31.3 Part II: Photometric Invariance 31.4 Part III: Color Constancy 41.5 Part IV: Color Feature Extraction 51.6 Part V: Applications 71.7 Summary 9
PART I Color Fundamentals 11
2 Color Vision 132.1 Introduction 132.2 Stages of Color Information Processing 142.3 Chromatic Properties of the Visual System 182.4 Summary 24
3 Color Image Formation 263.1 Lambertian Reflection Model 283.2 Dichromatic Reflection Model 293.3 Kubelka-Munk Model 323.4 The Diagonal Model 343.5 Color Spaces 363.6 Summary 44
PART II Photometric Invariance 47
4 Pixel-Based Photometric Invariance 494.1 Normalized Color Spaces 504.2 Opponent Color Spaces 524.3 The HSV Color Space 524.4 Composed Color Spaces 534.5 Noise Stability and Histogram Construction 584.6 Application: Color-Based Object Recognition 644.7 Summary 68
5 Photometric Invariance from Color Ratios 695.1 Illuminant Invariant Color Ratios 715.2 Illuminant Invariant Edge Detection 735.3 Blur-Robust and Color Constant Image Description 745.4 Application: Image Retrieval Based on Color Ratios 775.5 Summary 80
6 Derivative-Based Photometric Invariance 816.1 Full Photometric Invariants 846.2 Quasi-Invariants 1016.3 Summary 111
7 Photometric Invariance by Machine Learning 1137.1 Learning from Diversified Ensembles 1147.2 Temporal Ensemble Learning 1197.3 Learning Color Invariants for Region Detection 1207.4 Experiments 1247.5 Summary 134
PART III Color Constancy 135
8 Illuminant Estimation and Chromatic Adaptation 1378.1 Illuminant Estimation 1398.2 Chromatic Adaptation 141
9 Color Constancy Using Low-level Features 1439.1 General Gray-World 1439.2 Gray-Edge 1469.3 Physics-Based Methods 1509.4 Summary 151
10 Color Constancy Using Gamut-Based Methods 15210.1 Gamut Mapping Using Derivative Structures 15510.2 Combination of Gamut Mapping Algorithms 15710.3 Summary 160
11 Color Constancy Using Machine Learning 16111.1 Probabilistic Approaches 16111.2 Combination Using Output Statistics 16211.3 Combination Using Natural Image Statistics 16311.4 Methods Using Semantic Information 16711.5 Summary 171
12 Evaluation of Color Constancy Methods 17212.1 Data Sets 17212.2 Performance Measures 17512.3 Experiments 18012.4 Summary 185
PART IV Color Feature Extraction 187
13 Color Feature Detection 18913.1 The Color Tensor 19113.2 Color Saliency 20513.3 Conclusions 218
14 Color Feature Description 22114.1 Gaussian Derivative-Based Descriptors 22514.2 Discriminative Power 22914.3 Level of Invariance 23514.4 Information Content 23614.5 Summary 243
15 Color Image Segmentation 24415.1 Color Gabor Filtering 24515.2 Invariant Gabor Filters Under Lambertian Reflection 24715.3 Color-Based Texture Segmentation 24715.4 Material Recognition Using Invariant Anisotropic Filtering 24915.5 Color Invariant Codebooks and Material-Specific Adaptation 25615.6 Experiments 25815.7 Image Segmentation by Delaunay Triangulation 26315.8 Summary 268
PART V Applications 269
16 Object and Scene Recognition 27116.1 Diagonal Model 27216.2 Color SIFT Descriptors 27316.3 Object and Scene Recognition 27616.4 Results 28016.5 Summary 285
17 Color Naming 28717.1 Basic Color Terms 28817.3 Color Names from Uncalibrated Data 30417.4 Experimental Results 31317.5 Conclusions 316
18 Segmentation of Multispectral Images 31818.1 Reflection and Camera Models 31918.2 Photometric Invariant Distance Measures 32118.3 Error Propagation 32518.4 Photometric Invariant Region Detection by Clustering 32818.5 Experiments 33018.6 Summary 338
Citation Guidelines 339
References 341
Index 363