Natural Image Statistics: A Probabilistic Approach to Early Computational Vision. / Edition 1

by Aapo Hyvärinen, Jarmo Hurri, Patrick O. Hoyer

Overview

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 reffections 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 field in a single book, providing a unified 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 field for students in related disciplines.

Product Details

ISBN-13:	9781849968447
Publisher:	Springer London
Publication date:	12/16/2010
Series:	Computational Imaging and Vision , #39
Edition description:	Softcover reprint of hardcover 1st ed. 2009
Pages:	448
Product dimensions:	6.10(w) x 9.25(h) x 0.04(d)

Table of Contents

Background.- Linear Filters and Frequency Analysis.- Outline of the Visual System.- Multivariate Probability and Statistics.- Statistics of Linear Features.- Principal Components and Whitening.- Sparse Coding and Simple Cells.- Independent Component Analysis.- Information-Theoretic Interpretations.- Nonlinear Features and Dependency of Linear Features.- Energy Correlation of Linear Features and Normalization.- Energy Detectors and Complex Cells.- Energy Correlations and Topographic Organization.- Dependencies of Energy Detectors: Beyond V1.- Overcomplete and Non-negative Models.- Lateral Interactions and Feedback.- Time, Color, and Stereo.- Color and Stereo Images.- Temporal Sequences of Natural Images.- Conclusion.- Conclusion and Future Prospects.- Appendix: Supplementary Mathematical Tools.- Optimization Theory and Algorithms.- Crash Course on Linear Algebra.- The Discrete Fourier Transform.- Estimation of Non-normalized Statistical Models.

Editorial Reviews

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)

From the Publisher