Muutke küpsiste eelistusi

Color in Computer Vision: Fundamentals and Applications [Kõva köide]

, , ,
Teised raamatud teemal:
Color in Computer Vision: Fundamentals and ApplicationsSuurem pilt
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780470890844.html
Märksõnad:
While the field of computer vision drives many of todays 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.
Preface xv
1 Introduction
1(10)
1.1 From Fundamental to Applied
2(1)
1.2 Part I: Color Fundamentals
3(1)
1.3 Part II: Photometric Invariance
3(1)
1.3.1 Invariance Based on Physical Properties
4(1)
1.3.2 Invariance By Machine Learning
4(1)
1.4 Part III: Color Constancy
4(1)
1.5 Part IV: Color Feature Extraction
5(2)
1.5.1 From Luminance to Color
5(1)
1.5.2 Features, Descriptors, and Saliency
6(1)
1.5.3 Segmentation
6(1)
1.6 Part V: Applications
7(2)
1.6.1 Retrieval and Visual Exploration
7(1)
1.6.2 Color Naming
7(1)
1.6.3 Multispectral Applications
8(1)
1.7 Summary
9(2)
PART I Color Fundamentals
11(36)
2 Color Vision
13(13)
2.1 Introduction
13(1)
2.2 Stages of Color Information Processing
14(4)
2.2.1 Eye and Optics
14(1)
2.2.2 Retina: Rods and Cones
14(2)
2.2.3 Ganglion Cells and Receptive Fields
16(1)
2.2.4 LGN and Visual Cortex
16(2)
2.3 Chromatic Properties of the Visual System
18(6)
2.3.1 Chromatic Adaptation
18(1)
2.3.2 Human Color Constancy
18(2)
2.3.3 Spatial Interactions
20(3)
2.3.4 Chromatic Discrimination and Color Deficiency
23(1)
2.4 Summary
24(2)
3 Color Image Formation
26(21)
3.1 Lambertian Reflection Model
28(1)
3.2 Dichromatic Reflection Model
29(3)
3.3 Kubelka-Munk Model
32(2)
3.4 The Diagonal Model
34(2)
3.5 Color Spaces
36(8)
3.5.1 XYZ System
36(2)
3.5.2 RGB System
38(2)
3.5.3 Opponent Color Spaces
40(1)
3.5.4 Perceptually Uniform Color Spaces
41(1)
3.5.5 Intuitive Color Spaces
42(2)
3.6 Summary
44(3)
PART II Photometric Invariance
47(88)
4 Pixel-Based Photometric Invariance
49(20)
4.1 Normalized Color Spaces
50(2)
4.2 Opponent Color Spaces
52(1)
4.3 The HSV Color Space
52(1)
4.4 Composed Color Spaces
53(5)
4.4.1 Body Reflectance Invariance
53(2)
4.4.2 Body and Surface Reflectance Invariance
55(3)
4.5 Noise Stability and Histogram Construction
58(6)
4.5.1 Noise Propagation
58(2)
4.5.2 Examples of Noise Propagation through Transformed Colors
60(1)
4.5.3 Histogram Construction by Variable Kernel Density Estimation
61(3)
4.6 Application: Color-Based Object Recognition
64(4)
4.6.1 Dataset and Performance Measure
64(1)
4.6.2 Robustness Against Noise: Simulated Data
65(3)
4.7 Summary
68(1)
5 Photometric Invariance from Color Ratios
69(12)
5.1 Illuminant Invariant Color Ratios
71(2)
5.2 Illuminant Invariant Edge Detection
73(1)
5.3 Blur-Robust and Color Constant Image Description
74(3)
5.4 Application: Image Retrieval Based on Color Ratios
77(3)
5.4.1 Robustness to Illuminant Color
77(1)
5.4.2 Robustness to Gaussian Blur
78(1)
5.4.3 Robustness to Real-World Blurring Effects
78(2)
5.5 Summary
80(1)
6 Derivative-Based Photometric Invariance
81(32)
6.1 Full Photometric Invariants
84(17)
6.1.1 The Gaussian Color Model
84(4)
6.1.2 The Gaussian Color Model by an RGB Camera
88(1)
6.1.3 Derivatives in the Gaussian Color Model
89(1)
6.1.4 Differential Invariants for the Lambertian Reflection Model
90(5)
6.1.5 Differential Invariants for the Dichromatic Reflection Model
95(3)
6.1.6 Summary of Full Color Invariants
98(2)
6.1.7 Geometrical Color Invariants in Two Dimensions
100(1)
6.2 Quasi-Invariants
101(10)
6.2.1 Edges in the Dichromatic Reflection Model
101(2)
6.2.2 Photometric Variants and Quasi-Invariants
103(1)
6.2.3 Relations of Quasi-Invariants with Full Invariants
104(4)
6.2.4 Localization and Discriminative Power of Full and Quasi-Invariants
108(3)
6.3 Summary
111(2)
7 Photometric Invariance by Machine Learning
113(22)
7.1 Learning from Diversified Ensembles
114(5)
7.2 Temporal Ensemble Learning
119(1)
7.3 Learning Color Invariants for Region Detection
120(4)
7.4 Experiments
124(10)
7.4.1 Error Measures
124(1)
7.4.2 Skin Detection: Still Images
125(4)
7.4.3 Road Detection in Video Sequences
129(5)
7.5 Summary
134(1)
PART III Color Constancy
135(52)
8 Illuminant Estimation and Chromatic Adaptation
137(6)
8.1 Illuminant Estimation
139(2)
8.2 Chromatic Adaptation
141(2)
9 Color Constancy Using Low-level Features
143(9)
9.1 General Gray-World
143(3)
9.2 Gray-Edge
146(4)
9.3 Physics-Based Methods
150(1)
9.4 Summary
151(1)
10 Color Constancy Using Gamut-Based Methods
152(9)
10.1 Gamut Mapping Using Derivative Structures
155(2)
10.1.1 Diagonal-Offset Model
155(1)
10.1.2 Gamut Mapping of Linear Combinations of Pixel Values
155(2)
10.1.3 N-Jet Gamuts
157(1)
10.2 Combination of Gamut Mapping Algorithms
157(3)
10.2.1 Combining Feasible Sets
159(1)
10.2.2 Combining Algorithm Outputs
159(1)
10.3 Summary
160(1)
11 Color Constancy Using Machine Learning
161(11)
11.1 Probabilistic Approaches
161(1)
11.2 Combination Using Output Statistics
162(1)
11.3 Combination Using Natural Image Statistics
163(4)
11.3.1 Spatial Image Structures
164(1)
11.3.2 Algorithm Selection
165(2)
11.4 Methods Using Semantic Information
167(4)
11.4.1 Using Scene Categories
167(2)
11.4.2 Using High-Level Visual Information
169(2)
11.5 Summary
171(1)
12 Evaluation of Color Constancy Methods
172(15)
12.1 Data Sets
172(3)
12.1.1 Hyperspectral Data
173(1)
12.1.2 RGB Data
173(1)
12.1.3 Summary
174(1)
12.2 Performance Measures
175(5)
12.2.1 Mathematical Distances
176(1)
12.2.2 Perceptual Distances
176(1)
12.2.3 Color Constancy Distances
177(1)
12.2.4 Perceptual Analysis
178(2)
12.3 Experiments
180(5)
12.3.1 Comparing Algorithm Performance
181(1)
12.3.2 Evaluation
182(3)
12.4 Summary
185(2)
PART IV Color Feature Extraction
187(82)
13 Color Feature Detection
189(32)
13.1 The Color Tensor
191(14)
13.1.1 Photometric Invariant Derivatives
193(2)
13.1.2 Invariance to Color Coordinate Transformations
195(1)
13.1.3 Robust Full Photometric Invariance
196(1)
13.1.4 Color-Tensor-Based Features
197(7)
13.1.5 Experiment: Robust Feature Point Detection and Extraction
204(1)
13.2 Color Saliency
205(13)
13.2.1 Color Distinctiveness
207(1)
13.2.2 Physics-Based Decorrelation
208(3)
13.2.3 Statistics of Color Images
211(1)
13.2.4 Boosting Color Saliency
212(2)
13.2.5 Evaluation of Color Distinctiveness
214(1)
13.2.6 Repeatability
215(3)
13.2.7 Illustrations of Generality
218(1)
13.3 Conclusions
218(3)
14 Color Feature Description
221(23)
14.1 Gaussian Derivative-Based Descriptors
225(4)
14.2 Discriminative Power
229(6)
14.3 Level of Invariance
235(1)
14.4 Information Content
236(7)
14.4.1 Experimental Results
242(1)
14.5 Summary
243(1)
15 Color Image Segmentation
244(25)
15.1 Color Gabor Filtering
245(2)
15.2 Invariant Gabor Filters Under Lambertian Reflection
247(1)
15.3 Color-Based Texture Segmentation
247(2)
15.4 Material Recognition Using Invariant Anisotropic Filtering
249(7)
15.4.1 MR8-NC Filterbank
253(1)
15.4.2 MR8-INC Filterbank
254(1)
15.4.3 MR8-LINC Filterbank
255(1)
15.4.4 MR8-SLINC Filterbank
255(1)
15.4.5 Summary of Filterbank Properties
256(1)
15.5 Color Invariant Codebooks and Material-Specific Adaptation
256(2)
15.6 Experiments
258(5)
15.6.1 Material Classification by Color Invariant Codebooks
258(2)
15.6.2 Color-Texture Segmentation of Material Images
260(2)
15.6.3 Material Classification by Adaptive Color Invariant Codebooks
262(1)
15.7 Image Segmentation by Delaunay Triangulation
263(5)
15.7.1 Homogeneity Based on Photometric Color Invariance
264(1)
15.7.2 Homogeneity Based on a Similarity Predicate
265(1)
15.7.3 Difference Measure
265(2)
15.7.4 Segmentation Results
267(1)
15.8 Summary
268(1)
PART V Applications
269(70)
16 Object and Scene Recognition
271(16)
16.1 Diagonal Model
272(1)
16.2 Color SIFT Descriptors
273(3)
16.3 Object and Scene Recognition
276(4)
16.3.1 Feature Extraction Pipelines
276(1)
16.3.2 Classification
277(1)
16.3.3 Image Benchmark: PASCAL Visual Object Classes Challenge
278(1)
16.3.4 Video Benchmark: Mediamill Challenge
279(1)
16.3.5 Evaluation Criteria
279(1)
16.4 Results
280(5)
16.4.1 Image Benchmark: PASCAL VOC Challenge
280(2)
16.4.2 Video Benchmark: Mediamill Challenge
282(1)
16.4.3 Comparison
283(2)
16.5 Summary
285(2)
17 Color Naming
287(31)
17.1 Basic Color Terms
288(3)
17.2 Color Names from Calibrated Data
291(13)
17.2.1 Fuzzy Color Naming
293(1)
17.2.2 Chromatic Categories
294(4)
17.2.3 Achromatic Categories
298(2)
17.2.4 Fuzzy Sets Estimation
300(4)
17.3 Color Names from Uncalibrated Data
304(9)
17.3.1 Color Name Data Sets
306(1)
17.3.2 Learning Color Names
307(4)
17.3.3 Assigning Color Names in Test Images
311(1)
17.3.4 Flexibility Color Name Data Set
312(1)
17.4 Experimental Results
313(3)
17.5 Conclusions
316(2)
18 Segmentation of Multispectral Images
318(21)
18.1 Reflection and Camera Models
319(2)
18.1.1 Multispectral Imaging
319(1)
18.1.2 Camera and Image Formation Models
319(1)
18.1.3 White Balancing
320(1)
18.2 Photometric Invariant Distance Measures
321(4)
18.2.1 Distance between Chromaticity Polar Angles
321(1)
18.2.2 Distance between Hue Polar Angles
322(3)
18.2.3 Discussion
325(1)
18.3 Error Propagation
325(3)
18.3.1 Propagation of Uncertainties due to Photon Noise
325(1)
18.3.2 Propagation of Uncertainty
326(2)
18.4 Photometric Invariant Region Detection by Clustering
328(2)
18.4.1 Robust K-Means Clustering
328(1)
18.4.2 Photometric Invariant Segmentation
329(1)
18.5 Experiments
330(8)
18.5.1 Propagation of Uncertainties in Transformed Spectra
331(3)
18.5.2 Photometric Invariant Clustering
334(4)
18.6 Summary
338(1)
Citation Guidelines 339(2)
References 341(22)
Index 363
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 Autònoma 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.