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 vis...
| Main Authors: | , , |
|---|---|
| Corporate Author: | |
| Format: | Electronic |
| Language: | English |
| Published: |
London :
Springer London,
2009.
|
| Series: | Computational Imaging and Vision,
39 |
| Subjects: | |
| Online Access: | https://ezaccess.library.uitm.edu.my/login?url=http://dx.doi.org/10.1007/978-1-84882-491-1 |
Table of Contents:
- 1. Introduction
- Part I Background
- 2. Linear Filters and Frequency Analysis
- 3. Outline of the Visual System
- 4. Multivariate Probability and Statistics
- Part II Statistics of Linear Features
- 5. Principal Components and Whitening
- 6. Sparse Coding and Simple Cells
- 7. Independent Component Analysis
- 8. Information-Theoretic Interpretations
- Part III Nonlinear Features and Dependency of Linear Features
- 9. Energy Correlation of Linear Features and Normalisation
- 10. Energy Detectors and Complex Cells
- 11. Energy Correlations and Topographic Organisation
- 12. Dependencies of Energy Detectors; Beyond V1
- 13. Overcomplete and Non-Negative Models
- 14. Lateral Interactions and Feedback
- Part IV Time, Colour and Stereo
- 15. Colour and Stereo Images
- 16. Temporal Sequences of Natural Images
- Part V Conclusion
- 17. Conclusion and Future Prospects
- Part VI Appendix: Supplementary Mathematical Tools
- 18. Optimisation Theory and Algorithms
- 19. Crash Course on Linear Algebra
- 20. The Discrete Fourier Transform
- 21. Estimation of Non-Normalised Statistical Models
- Index
- References.