Ebook: Natural Image Statistics: A Probabilistic Approach to Early Computational Vision

One of the most successful frameworks in computational neuroscience is modelling visual processing using the statistical structure of natural images. In this framework, the visual system of the brain constructs a model of the statistical regularities of the incoming visual data. This enables the visual system to perform efficient probabilistic inference. The same framework is also very useful in engineering applications such as image processing and computer vision.

This book is the first comprehensive introduction to the multidisciplinary field of natural image statistics and its intention is to present a general theory of early vision and image processing in a manner that can be approached by readers from a variety of scientific backgrounds. A wealth of relevant background material is presented in the first section as an introduction to the subject. Following this are five unique sections, carefully selected so as to give a clear overview of all the basic theory, as well as the most recent developments and research. This structure, together with the included exercises and computer assignments, also make it an excellent textbook.

Natural Image Statistics is a timely and valuable resource for advanced students and researchers in any discipline related to vision, such as neuroscience, computer science, psychology, electrical engineering, cognitive science or statistics.

---

One of the most successful frameworks in computational neuroscience is modelling visual processing using the statistical structure of natural images. In this framework, the visual system of the brain constructs a model of the statistical regularities of the incoming visual data. This enables the visual system to perform efficient probabilistic inference. The same framework is also very useful in engineering applications such as image processing and computer vision.

This book is the first comprehensive introduction to the multidisciplinary field of natural image statistics and its intention is to present a general theory of early vision and image processing in a manner that can be approached by readers from a variety of scientific backgrounds. A wealth of relevant background material is presented in the first section as an introduction to the subject. Following this are five unique sections, carefully selected so as to give a clear overview of all the basic theory, as well as the most recent developments and research. This structure, together with the included exercises and computer assignments, also make it an excellent textbook.

Natural Image Statistics is a timely and valuable resource for advanced students and researchers in any discipline related to vision, such as neuroscience, computer science, psychology, electrical engineering, cognitive science or statistics.

---

One of the most successful frameworks in computational neuroscience is modelling visual processing using the statistical structure of natural images. In this framework, the visual system of the brain constructs a model of the statistical regularities of the incoming visual data. This enables the visual system to perform efficient probabilistic inference. The same framework is also very useful in engineering applications such as image processing and computer vision.

This book is the first comprehensive introduction to the multidisciplinary field of natural image statistics and its intention is to present a general theory of early vision and image processing in a manner that can be approached by readers from a variety of scientific backgrounds. A wealth of relevant background material is presented in the first section as an introduction to the subject. Following this are five unique sections, carefully selected so as to give a clear overview of all the basic theory, as well as the most recent developments and research. This structure, together with the included exercises and computer assignments, also make it an excellent textbook.

Natural Image Statistics is a timely and valuable resource for advanced students and researchers in any discipline related to vision, such as neuroscience, computer science, psychology, electrical engineering, cognitive science or statistics.

Content:
Front Matter....Pages i-xix
Introduction....Pages 1-21
Front Matter....Pages 23-23
Linear Filters and Frequency Analysis....Pages 25-49
Outline of the Visual System....Pages 51-66
Multivariate Probability and Statistics....Pages 67-90
Front Matter....Pages 91-91
Principal Components and Whitening....Pages 93-130
Sparse Coding and Simple Cells....Pages 131-150
Independent Component Analysis....Pages 151-175
Information-Theoretic Interpretations....Pages 177-196
Front Matter....Pages 197-197
Energy Correlation of Linear Features and Normalization....Pages 199-211
Energy Detectors and Complex Cells....Pages 213-237
Energy Correlations and Topographic Organization....Pages 239-261
Dependencies of Energy Detectors: Beyond V1....Pages 263-276
Overcomplete and Non-negative Models....Pages 277-293
Lateral Interactions and Feedback....Pages 295-306
Front Matter....Pages 307-307
Color and Stereo Images....Pages 309-323
Temporal Sequences of Natural Images....Pages 325-361
Front Matter....Pages 363-363
Conclusion and Future Prospects....Pages 365-374
Front Matter....Pages 375-375
Optimization Theory and Algorithms....Pages 377-397
Crash Course on Linear Algebra....Pages 399-405
The Discrete Fourier Transform....Pages 407-418
Back Matter....Pages 427-451
Estimation of Non-normalized Statistical Models....Pages 419-426

---

One of the most successful frameworks in computational neuroscience is modelling visual processing using the statistical structure of natural images. In this framework, the visual system of the brain constructs a model of the statistical regularities of the incoming visual data. This enables the visual system to perform efficient probabilistic inference. The same framework is also very useful in engineering applications such as image processing and computer vision.

This book is the first comprehensive introduction to the multidisciplinary field of natural image statistics and its intention is to present a general theory of early vision and image processing in a manner that can be approached by readers from a variety of scientific backgrounds. A wealth of relevant background material is presented in the first section as an introduction to the subject. Following this are five unique sections, carefully selected so as to give a clear overview of all the basic theory, as well as the most recent developments and research. This structure, together with the included exercises and computer assignments, also make it an excellent textbook.

Natural Image Statistics is a timely and valuable resource for advanced students and researchers in any discipline related to vision, such as neuroscience, computer science, psychology, electrical engineering, cognitive science or statistics.

Content:
Front Matter....Pages i-xix
Introduction....Pages 1-21
Front Matter....Pages 23-23
Linear Filters and Frequency Analysis....Pages 25-49
Outline of the Visual System....Pages 51-66
Multivariate Probability and Statistics....Pages 67-90
Front Matter....Pages 91-91
Principal Components and Whitening....Pages 93-130
Sparse Coding and Simple Cells....Pages 131-150
Independent Component Analysis....Pages 151-175
Information-Theoretic Interpretations....Pages 177-196
Front Matter....Pages 197-197
Energy Correlation of Linear Features and Normalization....Pages 199-211
Energy Detectors and Complex Cells....Pages 213-237
Energy Correlations and Topographic Organization....Pages 239-261
Dependencies of Energy Detectors: Beyond V1....Pages 263-276
Overcomplete and Non-negative Models....Pages 277-293
Lateral Interactions and Feedback....Pages 295-306
Front Matter....Pages 307-307
Color and Stereo Images....Pages 309-323
Temporal Sequences of Natural Images....Pages 325-361
Front Matter....Pages 363-363
Conclusion and Future Prospects....Pages 365-374
Front Matter....Pages 375-375
Optimization Theory and Algorithms....Pages 377-397
Crash Course on Linear Algebra....Pages 399-405
The Discrete Fourier Transform....Pages 407-418
Back Matter....Pages 427-451
Estimation of Non-normalized Statistical Models....Pages 419-426
....