This course aims to introduce the concepts, basic formulations, methods and applications of Computer Vision and Pattern Recognition.

Upon successful completion of the programme a typical student will be able to:
- Apply fundamental concepts and theoretical principles of computer vision and pattern recognition for building signal and data representations and modelling target functions
- Develop insight into the problems involved in applying a variety of computer vision and pattern recognition techniques to deal with practical scenarios
- Understand and apply the concepts of visual geometry in selected computer vision applications
- Analyse and compare the strengths and weaknesses of popular approaches
- Implement various algorithms in a range of CVPR applications through specific programming environments (Matlab, python)

Pinhole camera model, Homogeneous coordinates, Planar transformations and parameters, Perspective projection, 3D reconstruction
Epipolar geometry, Image Matching, Hough Transform, RANSAC

Dimensionality Reduction, Principle Component Analysis (PCA), Linear discriminant functions, Discriminant Analysis, Data representation, Distances Metrics, Clustering algorithms, Bagging and boosting, Ensemble Learning, Committee Machine, Sequential (Time Series) Data Analysis