The module focuses on application areas of the machine learning tools namely Computer Vision, Robotics and general Patter Recognition. Computer Vision is a field concerned with visual data captured by cameras, while Robotics and Pattern Recognition offer techniques for processing data from diverse types of sensors. Data and signal processing techniques from these two fields are closely related and enable us to automatically extract information so as to solve predictive and decision based tasks. The module also focuses on Compute Vision and Pattern Recognition tasks and methods, and illustrates how these technologies can impact the practical design of intelligent signal analysis.

Upon successful completion of the programme you will be able to: 1. Construct signal and data representations through the applicaiton of fundamental concepts and theoretical principles of computer vision and pattern recognition 2. Develop insight into the problems involved in applying a variety of pattern recognition techniques to deal with practical scenarios 3. Recommend and apply the relevant concepts of visual geometry in selected computer vision applications 4. Consider the strengths and weaknesses of popular approaches 5. Develop various algorithms for a range of CVPR applications through specific programming environments (Matlab, python)

Part 1: Camera model Part 2: Image geometry Part 3: Stereo vision Part 4: Model fitting Part 5: Object Classification, Detection, and Segmentation Part 6: Dimensionality Reduction, Principle Component Analysis (PCA) Part 7: Linear discriminant functions, Discriminant Analysis Part 8: Data representation, Distances Metrics, Clustering algorithms Part 9: Bagging and boosting, Ensemble Learning, Committee Machine Part 10: Sequential (Time Series) Data Analysis