
EE462, EE9SO25, EE9CS728:
Machine Learning for Computer Vision
• Autumn term 2013: every Monday, at 911am (2hours), in the room 509A, EEE, from 7th Oct to 9th Dec
• Assessment: 3 hour (closed book) exam (100%) in the start of Summer term 2014
• Prerequisite: None
• Lecturer: Dr TaeKyun Kim (office: 1017, email: tk.kim@imperial.ac.uk)
• Course website: http://www.iis.ee.ic.ac.uk/~tkkim/mlcv.htm
• Textbook (optional): Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer
• The course aims to introduce the concepts, theories and stateoftheart algorithms for visual learning and recognition. The first half of the module, for formulations and theories of machine learning techniques, consists of clustering, discriminative classifier learning, and probabilistic generative models. The latter half leads to the topics of visual recognition by the machine learning techniques learnt, including object detection/categorisation, segmentation, face and pose recognition. Each topic is illustrated with case studies.
• Syllabus:
Machine learning techniques: Prob. theory, Polynimial curve fitting, Clustering and EM, Boosting, Randomised decision forests, Maximum margin classifier, Markov random fields, Manifold learning and Gaussian process.
Visual learning and recognition: Image clustering, Object detection, Bag of words, Object recognition/categorisation, Segmentation, Face recognition and Pose estimation.
• Lecture 12: Course Overview / Background
[Lecture note in ppt]
[Supplementary document]
• Lecture 34: Clustering and EM
[Lecture note in ppt]
[Supplementary document]
[Statistical Pattern Recognition Toolbox for Matlab]
• Lecture 56: Object Detection / Boosting
[Lecture note in ppt]
[Supplementary document]
• Lecture 78: Random Forest and Example paper
[Lecture note in ppt]
[Example paper]
• Lecture 910: Object Recognition, Categorisation / Maximum Margin Classifier
[Lecture note in ppt]
[Supplementary document]
[Statistical Pattern Recognition Toolbox for Matlab]
• Lecture 1112: Segmentation / Markov Random Fields
[Lecture note in ppt]
[Supplementary document]
[Matlab demo code for image denoising by MRFs]
• Lecture 1314: Face Recognition / Manifold Learning
[Lecture note in ppt]
[Supplementary document]
[Matlab demo code for face recognition by PCA]
• Lecture 1516: Pose Estimation / Gaussian Process
[Lecture note in ppt]
[Supplementary document]
[Matlab toolbox for GP]
• Lecture 1718: Summary and Example paper
[Exam paper 2011/2012, 2012/2013]
*Please register the course, announcements will be made by the course emaillist.

