Natural Image Statistics

1. Front Matter

   Pages i-xix

   PDF

2. Introduction

   1. Introduction

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 1-21

3. Background

   1. Front Matter

      Pages 23-23

      PDF

   2. Linear Filters and Frequency Analysis

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 25-49

   3. Outline of the Visual System

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 51-66

   4. Multivariate Probability and Statistics

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 67-90

4. Statistics of Linear Features

   1. Front Matter

      Pages 91-91

      PDF

   2. Principal Components and Whitening

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 93-130

   3. Sparse Coding and Simple Cells

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 131-150

   4. Independent Component Analysis

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 151-175

   5. Information-Theoretic Interpretations

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 177-196

5. Nonlinear Features and Dependency of Linear Features

   1. Front Matter

      Pages 197-197

      PDF

   2. Energy Correlation of Linear Features and Normalization

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 199-211

   3. Energy Detectors and Complex Cells

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 213-237

   4. Energy Correlations and Topographic Organization

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 239-261

   5. Dependencies of Energy Detectors: Beyond V1

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 263-276

   6. Overcomplete and Non-negative Models

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 277-293

   7. Lateral Interactions and Feedback

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 295-306

6. Time, Color, and Stereo

   1. Front Matter

      Pages 307-307

      PDF

   2. Color and Stereo Images

      • Aapo Hyvärinen, Jarmo Hurri, Patrik O. Hoyer

      Pages 309-323

Aims and Scope This book is both an introductory textbook and a research monograph on modeling the statistical structure of natural images. In very simple terms, “natural images” are photographs of the typical environment where we live. In this book, their statistical structure is described using a number of statistical models whose parameters are estimated from image samples. Our main motivation for exploring natural image statistics is computational m- eling of biological visual systems. A theoretical framework which is gaining more and more support considers the properties of the visual system to be re?ections of the statistical structure of natural images because of evolutionary adaptation processes. Another motivation for natural image statistics research is in computer science and engineering, where it helps in development of better image processing and computer vision methods. While research on natural image statistics has been growing rapidly since the mid-1990s, no attempt has been made to cover the ?eld in a single book, providing a uni?ed view of the different models and approaches. This book attempts to do just that. Furthermore, our aim is to provide an accessible introduction to the ?eld for students in related disciplines.

• Computational Neuroscience
• Excel
• Information
• Machine Learning
• Neuroscience
• Stereo
• Vision
• Visual Neuroscience
• coding
• correlation
• discrete Fourier transform
• image processing
• signal processing

From the reviews:

“The authors did a wonderful job of introducing the field of natural image statistics, comprehensively. The book provides the underlying fundamental mathematics … accessible to a wide audience. … provides exercises and computer assignments at the end of the chapters. … the advanced topics are treated in a similar manner to basic theory, makes the book suitable to be used as a textbook for advanced students and by researchers in any discipline related to computer vision.” (Michael Goldberg and R. Goldberg, ACM Computing Reviews, October, 2010)

Policies and ethics