EE4-62 Machine Learning for Computer VisionLecturer(s): Dr T-K Kim
The course aims to introduce the concepts, theories and state-of-the-art algorithms for visual learning and recognition. The first half of the module, for formulations and theories of machine learning techniques, consists of discriminative classifier learning, probabilistic generative models, online learning and sampling methods. The latter half leads to the topics of visual recognition by the machine learning techniques learnt, including object detection, object categorisation, face recognition, action/activity recognition, visual tracking and semantic segmentation. Each topic is illustrated with case studies.
Students will be able to earn knowledge and understanding about theories and concepts of visual recognition, contemporary machine learning techniques, application of machine learning to computer vision, and skills of Matlab software by demonstration, and practical views of current and future application domains.
Machine learning techniques: Prob. decision theory, Clustering and EM, Boosting, Randomised decision forests, Ensemble learning, Sparse kernel machine, Gaussian process, Manifold learning, Markov random fields, Hidden markov models, Sampling methods.
Visual learning and recognition: Object detection, Bag of words, Object categorisation, Pose estimation, Face recognition, Semantic segmentation, Activity/action recognition, Visual tracking
Coursework contribution: 0%
Closed or Open Book (end of year exam): N/A
Oral Exam Required (as final assessment): N/A
Prerequisite: None required
Course Homepage: http://www.iis.ee.ic.ac.uk/~tkkim/mlcv.htm