Computer Vision Models: Hidden Variables

Monday, June 14, 2010

Hidden Variables

Worked on chapter 6 today which concerns modeling complex density functions using hidden variables and the EM algorithm. Sorted out numerous small mistakes. Made a figure illustrating a regression problem where we try to predict one pose from another. Made a second figure which concerns using hidden variables to register images of digits together.

No comments:

Post a Comment

Contents

Part I: Probability

1. Introduction to probability
2. Probability distributions
3. Fitting probability distributions
4. The multivariate normal

Part II: Machine learning for machine vision

5. Learning and inference
6. Complex probability densities
7. Regression models for vision
8. Classification models for vision

Part III: Connecting local models

9. Graphical models
10. Directed models for images
11. Markov random fields

Part IV: Preprocessing

12. Preprocessing methods

Part V: Models for geometry

13. Pinhole camera model
14. Transformation models
15. Multiple cameras

Part VI: Computer vision models

16. Models for shape
17. Models for identity and style
18. Temporal models
19. Models for visual words

Part VI Appendices

A. Optimization

B. Image preprocessing and feature extraction

C. Linear algebra

D. Algorithms