Cover Image

Robust computer vision : theory and applications / by Nicu Sebe and Michael S. Lew.

From the foreword by Thomas Huang: "During the past decade, researchers in computer vision have found that probabilistic machine learning methods are extremely powerful. This book describes some of these methods. In addition to the Maximum Likelihood framework, Bayesian Networks, and Hidden Mar...

Full description

Saved in:
Bibliographic Details
Online Access: Full Text (via Springer)
Main Author: Sebe, Nicu
Other Authors: Lew, Michael S., 1965-
Format: eBook
Language:English
Published: Dordrecht ; Boston : Kluwer Academic, [2003]
Series:Computational imaging and vision ; v. 26.
Subjects:
Computer vision.
Table of Contents:
  • 1 Visual Similarity 2
  • 1.1 Color 4
  • 1.2 Texture 7
  • 1.3 Shape 9
  • 1.4 Stereo 11
  • 1.5 Motion 13
  • 1.6 Facial expression 13
  • 2 Evaluation of Computer Vision Algorithms 16
  • 2. Maximum Likelihood Framework 25
  • 2 Statistical Distributions 26
  • 2.1 Gaussian Distribution 27
  • 2.2 Exponential Distribution 38
  • 2.3 Cauchy Distribution 41
  • 3 Robust Statistics 43
  • 3.1 Outliers 44
  • 4 Maximum Likelihood Estimators 45
  • 5 Maximum Likelihood in Relation to Other Approaches 47
  • 6 Our Maximum Likelihood Approach 50
  • 6.1 Scale Parameter Estimation in a Cauchy Distribution 54
  • 7 Experimental Setup 57
  • 3. Color Based Retrieval 61
  • 2 Colorimetry 64
  • 3 Color Models 64
  • 3.1 RGB Color System 65
  • 3.2 HSV Color System 66
  • 3.3 l[subscript 1]l[subscript 2]l[subscript 3] Color System 67
  • 4 Color Based Retrieval 68
  • 4.1 Color Indexing 69
  • 5 Experiments with the Corel Database 73
  • 5.1 Early Experiments 73
  • 5.2 Usability Issues 74
  • 5.3 Printer-Scanner Noise Experiments 75
  • 5.4 Color Model 76
  • 5.5 Quantization 76
  • 5.6 Distribution Analysis 77
  • 6 Experiments with the Objects Database 79
  • 4. Robust Texture Analysis 83
  • 2 Human Perception of Texture 86
  • 3 Texture Features 87
  • 3.1 Texture Distribution Models 88
  • 3.1.1 Gray-level differences 89
  • 3.1.2 Laws' texture energy measures 89
  • 3.1.3 Center-symmetric covariance measures 89
  • 3.1.4 Local binary patterns and trigrams 91
  • 3.1.5 Complementary feature pairs 91
  • 3.2 Gabor and Wavelet Models 92
  • 4 Texture Classification Experiments 95
  • 4.2 Distribution Analysis 97
  • 4.3 Misdetection Rates 99
  • 5 Texture Retrieval Experiments 104
  • 5.1 Texture Features 105
  • 5.2 Experiments Setup 106
  • 5.3 Similarity Noise for QMF-Wavelet Transform 106
  • 5.4 Similarity Noise for Gabor Wavelet Transform 108
  • 5. Shape Based Retrieval 111
  • 2 Human Perception of Visual Form 113
  • 3 Active Contours 118
  • 3.1 Behavior of Traditional Active Contours 120
  • 3.2 Generalized Force Balance Equations 124
  • 3.3 Gradient Vector Flow 125
  • 4 Invariant Moments 130
  • 5 Experiments 131
  • 6. Robust Stereo Matching and Motion Tracking 135
  • 1.1 Stereoscopic Vision 137
  • 2 Stereo Matching 138
  • 3 Stereo Matching Algorithms 144
  • 3.1 Template Based Algorithm 144
  • 3.2 Multiple Windows Algorithm 146
  • 3.3 Cox' Maximum Likelihood Algorithm 147
  • 4 Stereo Matching Experiments 150
  • 4.1 Stereo Sets 151
  • 4.2 Stereo Matching Results 151
  • 5 Motion Tracking Experiments 157
  • 7. Facial Expression Recognition 163
  • 2 Emotion Recognition 166
  • 2.1 Judgment Studies 167
  • 2.2 Review of Facial Expression Recognition 167
  • 3 Face Tracking and Feature Extraction 171
  • 4 The Static Approach: Bayesian Network Classifiers 173
  • 4.1 Continuous Naive-Bayes: Gaussian and Cauchy Naive Bayes Classifiers 175
  • 4.2 Beyond the Naive-Bayes Assumption: Finding Dependencies among Features Using a Gaussian TAN Classifier 176
  • 5 The Dynamic Approach: Expression Recognition Using Multi-level HMMs 179
  • 5.1 Hidden Markov Models 182
  • 5.2 Expression Recognition Using Emotion-Specific HMMs 183
  • 5.3 Automatic Segmentation and Recognition of Emotions Using Multi-level HMM 184
  • 6 Experiments 187
  • 6.1 Results Using the Chen Database 191
  • 6.1.1 Person-Dependent Tests 191
  • 6.1.2 Person-Independent Tests 193
  • 6.2 Results Using the Cohn-Kanade Database 194.

Similar Items