Natural Image Statistics A Probabilistic Approach to Early Computational Vision /

• Κύριοι συγγραφείς: Hyvärinen, Aapo (Συγγραφέας), Hurri, Jarmo (Συγγραφέας), Hoyer, Patrik O. (Συγγραφέας)
• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: London : Springer London, 2009.
• Σειρά: Computational Imaging and Vision, 39
• Θέματα: Medicine.; Neurosciences.; Computer graphics.; Biomedicine.; Computer Imaging, Vision, Pattern Recognition and Graphics.; Signal, Image and Speech Processing.

 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. 

 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.