Theory and applications of image registration. (2017)

• Record Type: Book
• Further Information: Note: A. Ardeshir Goshtasby.
• Authors: Goshtasby, Ardeshir
• Contents: Contributors xv Acknowledgments xvii About the Companion Website xix 1 Introduction 1 1.1 Organization of the Book 3 1.2 Further Reading 5 References 5 2 Image Orientation Detection 9 2.1 Introduction 9 2.2 Geometric Gradient and Geometric Smoothing 13 2.2.1 Calculating Geometric Gradients 15 2.3 Comparison of Geometric Gradients and Intensity Gradients 18 2.4 Finding the Rotational Difference between Two Images 21 2.5 Performance Evaluation 23 2.5.1 Reliability 23 2.5.2 Accuracy 31 2.5.3 Computational Complexity 32 2.6 Registering Images with a Known Rotational Difference 34 2.7 Discussion 36 2.8 Further Reading 37 References 40 3 Feature Point Detection 43 3.1 Introduction 43 3.2 Variant Features 44 3.2.1 Central Moments 44 3.2.2 Uniqueness 48 3.3 Invariant Features 50 3.3.1 Rotation-Invariant Features 50 3.3.1.1 Laplacian of Gaussian (LoG) Detector 51 3.3.1.2 Entropy 53 3.3.1.3 InvariantMoments 55 3.3.2 SIFT: A Scale-and Rotation-Invariant Point Detector 58 3.3.3 Radiometric-Invariant Features 60 3.3.3.1 Harris Corner Detector 60 3.3.3.2 Hessian Corner Detector 63 3.4 Performance Evaluation 64 3.5 Further Reading 68 References 68 4 FeatureLineDetection 75 4.1 Hough Transform Using Polar Equation of Lines 79 4.2 Hough Transform Using Slope and y-Intercept Equation of Lines 82 4.3 Line Detection Using Parametric Equation of Lines 86 4.4 Line Detection by Clustering 89 4.5 Line Detection by Contour Tracing 92 4.6 Line Detection by Curve Fitting 95 4.7 Line Detection by Region Subdivision 101 4.8 Comparison of the Line Detection Algorithms 106 4.8.1 Sensitivity to Noise 106 4.8.2 Positional and Directional Errors 106 4.8.3 Length Accuracy 109 4.8.4 Speed 109 4.8.5 Quality of Detected Lines 109 4.9 Revisiting Image Dominant Orientation Detection 117 4.10 Further Reading 121 References 125 5 Finding Homologous Points 133 5.1 Introduction 133 5.2 Point Pattern Matching 134 5.2.1 Parameter Estimation by Clustering 137 5.2.2 Parameter Estimation by RANSAC 141 5.3 Point Descriptors 146 5.3.1 Histogram-Based Descriptors 147 5.3.2 SIFT Descriptor 148 5.3.3 GLOH Descriptor 151 5.3.4 Composite Descriptors 152 5.3.4.1 Hu InvariantMoments 152 5.3.4.2 Complex Moments 152 5.3.4.3 Cornerness Measures 153 5.3.4.4 Power Spectrum Features 154 5.3.4.5 Differential Features 155 5.3.4.6 Spatial Domain Features 155 5.4 SimilarityMeasures 160 5.4.1 Correlation Coefficient 160 5.4.2 Minimum Ratio 161 5.4.3 Spearman’s 161 5.4.4 Ordinal Measure 162 5.4.5 Correlation Ratio 162 5.4.6 Shannon Mutual Information 164 5.4.7 Tsallis Mutual Information 165 5.4.8 F-Information 166 5.5 Distance Measures 167 5.5.1 Sum of Absolute Differences 167 5.5.2 Median of Absolute Differences 167 5.5.3 Square Euclidean Distance 168 5.5.4 Intensity-Ratio Variance 168 5.5.5 Rank Distance 169 5.5.6 Shannon Joint Entropy 169 5.5.7 Exclusive F-Information 170 5.6 TemplateMatching 170 5.6.1 Coarse-to-Fine Matching 171 5.6.2 MultistageMatching 172 5.6.3 Rotationally InvariantMatching 173 5.6.4 Gaussian-Weighted TemplateMatching 174 5.6.5 Template Matching in Different Modality Rotated Images 175 5.7 Robust Parameter Estimation 178 5.7.1 Ordinary Least-Squares Estimator 180 5.7.2 Weighted Least-Squares Estimator 182 5.7.3 Least Median of Squares Estimator 184 5.7.4 Least Trimmed Squares Estimator 184 5.7.5 Rank Estimator 185 5.8 Finding Optimal Transformation Parameters 193 5.9 Performance Evaluation 193 5.10 Further Reading 197 References 200 6 Finding Homologous Lines 215 6.1 Introduction 215 6.2 Determining Transformation Parameters from Line Parameters 215 6.3 Finding Homologous Lines by Clustering 221 6.3.1 Finding the Rotation Parameter 222 6.3.2 Finding the Translation Parameters 223 6.4 Finding Homologous Lines by RANSAC 229 6.5 Line Grouping Using Local Image Information 232 6.6 Line Grouping Using Vanishing Points 235 6.6.1 Methods Searching the Image Space 235 6.6.2 Methods Searching the Polar Space 236 6.6.3 Methods Searching the Gaussian Sphere 236 6.6.4 A Method Searching Both Image and Gaussian Sphere 237 6.6.5 Measuring the Accuracy of Detected Vanishing Points 244 6.6.6 Discussion 247 6.7 Robust Parameter Estimation Using Homologous Lines 253 6.8 Revisiting Image Dominant Orientation Detection 255 6.9 Further Reading 256 References 257 7 Nonrigid Image Registration 261 7.1 Introduction 261 7.2 Finding Homologous Points 262 7.2.1 Coarse-to-Fine Matching 262 7.2.2 Correspondence by Template Matching 269 7.3 Outlier Removal 274 7.4 Elastic Transformation Models 278 7.4.1 Surface Spline (SS) Interpolation 280 7.4.2 Piecewise Linear (PWL) Interpolation 282 7.4.3 Moving Least Squares (MLS) Approximation 283 7.4.4 Weighted Linear (WL) Approximation 285 7.4.5 Performance Evaluation 287 7.4.6 Choosing the Right Transformation Model 291 7.5 Further Reading 292 References 293 8 Volume Image Registration 299 8.1 Introduction 299 8.2 Feature Point Detection 301 8.2.1 Central Moments 301 8.2.2 Entropy 302 8.2.3 LoG Operator 302 8.2.4 First-Derivative Intensities 303 8.2.5 Second-Derivative Intensities 304 8.2.6 Speed-Up Considerations in Feature Point Detection 305 8.2.7 Evaluation of Feature Point Detectors 305 8.3 Finding Homologous Points 307 8.3.1 Finding Initial Homologous Points Using Image Descriptors 310 8.3.2 Finding Initial Homologous Points by Template Matching 313 8.3.3 Finding Final Homologous Points from Coarse to Fine 315 8.3.4 Finding the Final Homologous Points by Outlier Removal 320 8.4 Transformation Models for Volume Image Registration 321 8.4.1 Volume Spline 323 8.4.2 Weighted Rigid Transformation 325 8.4.3 Computing the Overall Transformation 327 8.5 Performance Evaluation 330 8.5.1 Accuracy 330 8.5.2 Reliability 333 8.5.3 Speed 333 8.6 Further Reading 335 References 337 9 Validation Methods 343 9.1 Introduction 343 9.2 Validation Using Simulation Data 344 9.3 Validation Using a Gold Standard 345 9.4 Validation by an Expert Observer 347 9.5 Validation Using a Consistency Measure 348 9.6 Validation Using a Similarity/DistanceMeasure 350 9.7 Further Reading 351 References 352 10 Video Image Registration 357 EdgardoMolina, Wai Lun Khoo, Hao Tang, and Zhigang Zhu 10.1 Introduction 357 10.2 Motion Modeling 358 10.2.1 The Motion Field of Rigid Objects 358 10.2.2 Motion Models 360 10.2.2.1 Pure Rotation and a 3-D Scene 361 10.2.2.2 General Motion and a Planar Scene 362 10.2.2.3 TranslationalMotion
• Edition: 1st
• Publisher Details: Hoboken, New Jersey : John Wiley & Sons, Inc
• Publication Date: 2017
• Extent: 1 online resource
• Subjects: 621.367; Image registration
• Languages: English
• ISBNs: 9781119171737; 9781119171720
• Related ISBNs: 9781119171713
• Notes: Note: Description based on CIP data; resource not viewed.
• Access Rights: Legal Deposit; Only available on premises controlled by the deposit library and to one user at any one time; The Legal Deposit Libraries (Non-Print Works) Regulations (UK).
• Access Usage: Restricted: Printing from this resource is governed by The Legal Deposit Libraries (Non-Print Works) Regulations (UK) and UK copyright law currently in force.