Download Computer Vision: Models, Learning, and Inference by Simon J.D. Prince, This modern treatment of computer vision focuses on learning and inference in probabilistic models as a unifying theme. It shows the way to use training data to find out the relationships between the determined image data and also the aspects of the world that we would like to estimate, like the 3D structure or the object class, and how to take advantage of these relationships to form new inferences regarding the world from new image data. Download the pdf from below to explore all topic and start learning.


I Probability
Introduction to probability
Common probability distributions
Fitting probability models
The normal distribution

II Machine learning for machine vision
Learning and inference in vision
Modeling complex data densities
Regression models
Classification models

III Connecting local models
Graphical models
Models for chains and trees
Models for grids

IV Preprocessing
Image preprocessing and feature extraction

V Models for geometry
The pinhole camera
Models for transformations
Multiple cameras

VI Models for vision
Models for shape
Models for style and identity
Temporal models
Models for visual words

VII Appendices
A Notation
B Optimization
C Linear algebra