Techniques and Applications of Hyperspectral

Techniques and Applications of Hyperspectral Image Analysis gives an introduction to the field of image analysis using hyperspectral techniques, and includes definitions and instrument descriptions. Other imaging topics that are covered are segmentation, regression and classification. The book discusses how high quality images of large data files can be structured and archived. Imaging techniques also demand accurate calibration, and are covered in sections about multivariate calibration techniques. The book explains the most important instruments for hyperspectral imaging in more technical detail. A number of applications from medical and chemical imaging are presented and there is an emphasis on data analysis including modeling, data visualization, model testing and statistical interpretation.

Paul Geladi received a Ph.D. in chemistry at the University of Antwerp in 1979. In 1990, he became associate professor at Umeå University, with interests in multivariate calibration, multivariate image analysis and multiway analysis. He was awarded the EAS award for Chemometrics in 2002. Currently he is head of research for NIRCE centered in Umeå and Vasa. Paul Geladi has coauthored about 90 scientific papers and some 20 book chapters and has given many invited lectures throughout Europe and North America. He was European editor of Journal of Chemometrics from 1989 - 1995, and has been review editor of the journal since 1999. He served as a member of the Editorial Board of Chemometrics and Intelligent Laboratory Systems from 1986 to 1991.

Hans F Grahn received his Ph.D. in Physical Organic Chemistry in 1986. Following several years of work abroad he began MRI studies in the laboratory of Dr Zeverenyi at SUNY Health Center, NY. At this time (1988) Hans also began to collaborate with Paul Geladi and the MIA (Multivariate Image Analysis) software for MRI multivariate images was written. In 1990 Hans received funding from the Swedish Natural Science Foundation for 2D NMR work at Umeå University. In 1991 he began a 3 year project at AstraZeneca. During this period he continued to collaborate with the pharmaceutical industry and the Karolinska Institute, where he received a position as a preclinical researcher and associate Professor at a new MRI -centre. Hans has more than 35 coauthored scientific papers and book chapters. He is now active as Business Developer in the Medical Imaging business and is also active in his own company.

Preface	p. xiii
List of Contributors	p. xvii
List of Abbreviations	p. xix
Multivariate Images, Hyperspectral Imaging: Background and Equipment	p. 1
Introduction	p. 1
Digital Images, Multivariate Images and Hyperspectral Images	p. 1
Hyperspectral Image Generation	p. 5
Introduction	p. 5
Point Scanning Imaging	p. 6
Line Scanning Imaging	p. 7
Focal Plane Scanning Imaging	p. 8
Essentials of Image Analysis Connecting Scene and Variable Spaces	p. 9
References	p. 14
Principles of Multivariate Image Analysis (MIA) in Remote Sensing, Technology and Industry	p. 17
Introduction	p. 17
MIA Approach: Synopsis	p. 18
Dataset Presentation	p. 18
Master Dataset: Rationale	p. 18
Montmorency Forest, Quebec, Canada: Forestry Background	p. 19
Tools in MIA	p. 21
MIA Score Space Starting Point	p. 21
Colour-slice Contouring in Score Cross-plots: a 3-D Histogram	p. 24
Brushing: Relating Different Score Cross-plots	p. 24
Joint Normal Distribution (or Not)	p. 26
Local Models/Local Modelling: a Link to Classification	p. 27
MIA Analysis Concept: Master Dataset Illustrations	p. 28
A New Topographic Map Analogy	p. 28
MIA Topographic Score Space Delineation of Single Classes	p. 31
MIA Delineation of End-member Mixing Classes	p. 33
Which to Use? When? How?	p. 38
Scene-space Sampling in Score Space	p. 39
Conclusions	p. 40
References	p. 41
Clustering and Classification in Multispectral Imaging for Quality Inspection of Postharvest Products	p. 43
Introduction to Multispectral Imaging in Agriculture	p. 43
Measuring Quality	p. 43
Spectral Imaging in Agriculture	p. 44
Unsupervised Classification of Multispectral Images	p. 46
Unsupervised Classification with FCM	p. 46
FCM Clustering	p. 47
cFCM Clustering	p. 48
csiFCM	p. 49
Combining Spectral and Spatial Information	p. 51
sgPCM Clustering	p. 52
Supervised Classification of Multispectral Images	p. 54
Multivariate Image Analysis for Training Set Selection	p. 55
FEMOS	p. 57
Experiment with a Multispectral Image of Pine and Spruce Wood	p. 58
Clustering with FEMOS Procedure	p. 60
Visualization and Coloring of Segmented Images and Graphs: Class Coloring	p. 62
Conclusions	p. 64
References	p. 65
Self-modeling Image Analysis with SIMPLISMA	p. 69
Introduction	p. 69
Materials and Methods	p. 70
FTIR Microscopy	p. 70
SIMS Imaging of a Mixture of Palmitic and Stearic Acids on Aluminum foil	p. 71
Data Analysis	p. 73
Theory	p. 73
Results and Discussion	p. 75
FTIR Microscopy Transmission Data of a Polymer Laminate	p. 75
FTIR Reflectance Data of a Mixture of Aspirin and Sugar	p. 80
SIMS Imaging of a Mixture of Palmitic and Stearic Acids on Aluminum Foil	p. 80
Conclusions	p. 85
References	p. 87
Multivariate Analysis of Spectral Images Composed of Count Data	p. 89
Introduction	p. 89
Example Datasets and Simulations	p. 92
Component Analysis	p. 95
Orthogonal Matrix Factorization	p. 96
PCA and Related Methods	p. 97
PCA of Arbitrary Factor Models	p. 102
Maximum Likelihood PCA (MLPCA)	p. 104
Weighted PCA (WPCA)	p. 105
Principal Factor Analysis (PFA)	p. 107
Selecting the Number of Components	p. 108
Maximum Likelihood Based Approaches	p. 113
Poisson Non-negative Matrix Factorization (PNNMF)	p. 114
Iteratively Weighted Least Squares (IWLS)	p. 117
NNMF: Gaussian Case (Approximate Noise)	p. 118
Factored NNMF: Gaussian Case (Approximate Data)	p. 119
Alternating Least Squares (ALS)	p. 120
Performance Comparisons	p. 121
Conclusions	p. 124
Acknowledgements	p. 125
References	p. 125
Hyperspectral Image Data Conditioning and Regression Analysis	p. 127
Introduction	p. 127
Terminology	p. 128
Multivariate Image Regression	p. 128
Regression Diagnostics	p. 130
Differences between Normal Calibration and Image Calibration	p. 132
Data Conditioning	p. 132
Reflectance Transformation and Standardization	p. 133
Spectral Transformations	p. 135
Data Clean-up	p. 137
Data Conditioning Summary	p. 138
PLS Regression Optimization	p. 138
Data Subset Selection	p. 138
Pseudorank Determination	p. 139
Regression Examples	p. 140
Artificial Ternary Mixture	p. 142
Commercial Cheese Samples	p. 146
Wheat Straw Wax	p. 149
Conclusions	p. 150
Acknowledgements	p. 152
References	p. 152
Principles of Image Cross-validation (ICV): Representative Segmentation of Image Data Structures	p. 155
Introduction	p. 155
Validation Issues	p. 156
2-way	p. 156
MIA/MIR	p. 158
Case Studies	p. 160
Case 1: Full Y-image	p. 163
Case 2: Critical Segmentation Issues	p. 165
Case 3: Y-composite	p. 168
Case 4: Image Data Structure Sampling	p. 173
Discussion and Conclusions	p. 177
Reflections on 2-way Cross-validation	p. 178
References	p. 180
Detection, Classification, and Quantification in Hyperspectral Images Using Classical Least Squares Models	p. 181
Introduction	p. 181
CLS Models	p. 182
CLS	p. 183
ELS	p. 187
GLS	p. 189
Detection, Classification, and Quantification	p. 192
Detection	p. 194
Classification	p. 196
Quantification	p. 197
Conclusions	p. 200
Acknowledgements	p. 200
References	p. 201
Calibration Standards and Image Calibration	p. 203
Introduction	p. 203
The Need for Calibration in General	p. 203
The Need for Image Calibration	p. 204
Resolution in Hyperspectral Images	p. 205
Spectroscopic Definitions	p. 207
Calibration Standards	p. 209
Calibration in Hyperspectral Images	p. 213
Conclusions	p. 219
References	p. 219
Multivariate Movies and their Applications in Pharmaceutical and Polymer Dissolution Studies	p. 221
Introduction	p. 221
Introducing the Time Axis	p. 222
Data Structure and Reduction	p. 223
Compression of Spectra	p. 224
Space Dimensions	p. 227
Time Dimension	p. 231
Simultaneous Compression of all Variables	p. 235
Applications: Solvent Diffusion and Pharmaceutical Studies	p. 237
Solvent Diffusion in Polymers	p. 238
Optical and NMR Studies	p. 242
Line Imaging	p. 245
Global MIR Imaging Studies of Solvent Intake	p. 246
Drug Release	p. 249
ATR-FTIR Imaging	p. 251
Conclusions	p. 254
Acknowledgement	p. 255
References	p. 255
Multivariate Image Analysis of Magnetic Resonance Images: Component Resolution with the Direct Exponential Curve Resolution Algorithm (DECRA)	p. 261
Introduction	p. 261
DECRA Approach	p. 264
DECRA Algorithm	p. 269
[superscript 1]H Relaxation	p. 270
T[subscript 1] Transformation	p. 271
Imaging Methods	p. 271
Phantom Images	p. 273
T[subscript 2] Series	p. 273
T[subscript 1] Series	p. 277
Brain Images	p. 278
T[subscript 2] Series	p. 278
T[subscript 1] Series	p. 281
Regression Analysis	p. 282
Conclusions	p. 285
References	p. 285
Hyperspectral Imaging Techniques: an Attractive Solution for the Analysis of Biological and Agricultural Materials	p. 289
Introduction	p. 289
Sample Characterization and Chemical Species Distribution	p. 291
Analysis of Fruit	p. 291
Analysis of Kernels	p. 294
Analysis of Food and Feed Mixtures	p. 296
Detecting Contamination and Defects in Agro-food Products	p. 297
Detecting Contamination in Meat Products	p. 297
Detecting Contamination and Defects in Fruit	p. 298
Detecting Contamination and Defects in Cereals	p. 301
Detecting Contamination in Compound Feed	p. 302
Other Agronomic and Biological Applications	p. 304
Conclusion	p. 306
References	p. 307
Application of Multivariate Image Analysis in Nuclear Medicine: Principal Component Analysis (PCA) on Dynamic Human Brain Studies with Positron Emission Tomography (PET) for Discrimination of Areas of Disease at High Noise Levels	p. 313
Introduction	p. 313
PET	p. 315
History	p. 315
Principles	p. 315
Scanning Modes in PET	p. 317
Analysis of PET Data/Images	p. 318
PCA	p. 319
History	p. 319
Definition	p. 319
Pre-processing and Scaling	p. 320
Noise Pre-normalization	p. 321
Application of PCA in PET	p. 322
SWPCA	p. 323
VWPCA	p. 326
MVWPCA	p. 327
Conclusions	p. 330
References	p. 332
Near Infrared Chemical Imaging: Beyond the Pictures	p. 335
Introduction	p. 335
Data Measurement	p. 338
Selection of Samples and Acquisition Schemes	p. 340
What, How Much and Where	p. 343
Data Analysis and the Underlying Structure of the Data	p. 344
Imaging with Statistically Meaningful Spatial Dimensions	p. 348
Chemical Contrast	p. 350
Measure, Count and Compare	p. 355
Correlating Data to Sample Performance and/or Behavior: the Value of NIRCI Data	p. 359
Conclusions	p. 360
References	p. 361
Index	p. 363
Table of Contents provided by Ingram. All Rights Reserved.

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.

FREE SHIPPING

Amazon no longer offers textbook rentals. We do!

Techniques and Applications of Hyperspectral Image Analysis

Summary

Author Biography

Table of Contents

Supplemental Materials