Here are my project suggestions for PartII or Diploma students in the academic year 2004/2005. Some of the information on last year's suggestions may also be relevant.
The platform of choice for implementation of the projects is Matlab, which is available in most Colleges and in the CL. Matlab has excellent facilities for numerical computations and visualisation, and there are many useful toolboxes (e.g. for image processing, statistics, optimisation, neural networks). For reasons of runtime efficiency it might however be appropriate to implement part of the required functionality in a lower level compiled language such as C++ and integrate such modules into Matlab by means of the Matlab compiler package. There are various free computer vision packages available which use C/C++. Probably the best (in terms of features and support) of these are Intel's OpenCV and the VXL libraries.
No previous experience of image and video processing is required, just enthusiasm. The projects are challenging in that they address interesting research problems, but plenty of support will be available. Apart from an interest in the project, a reasonable grounding in continuous mathematics and probability theory would be helpful, as would proficiency with high level programming languages such as C++ or the Matlab environment.
As regards general references, I particularly recommend the textbook by Forsyth and Ponce on computer vision. References on image processing, such as the book by Gonzales and Woods, and on numerical methods, such as Numerical Recipes in C++, might also be handy. Useful online resources for computer vision include CVonline and the Computer Vision Homepage at CMU. One of the best tools for finding papers etc. apart from Google is Citeseer. There are many online tutorials for Matlab, this is a local one at CUED. Eventually you might want to use Tex/LaTex to produce your dissertation, here is a basic introduction and further information can be found here and here.
The goal of this project is to derive a description of a face by fitting a 3D mesh type model of a face to a 2D image through generating a rendered image of the model.
The method used will probably follow Paterson or Blanz.
It is desired that the model be able to estimate pose, gaze direction, eye colour etc.
The goal of this project is to build a series of classifiers that will recognise structural elements on the facades of buildings. These will include: doors, windows, roof lines, columns and pebble-dashing.
The method used to parse an image will be to extract regions and strong straight edges or curves and group these into "salient groupings" on the basis of geometric relations between segments. Region information will be used to determine how salient groupings relate to each other. Knowledge about the likely visual appearance of sky will be used to isolate roof-line features.
Semantic labels will be applied to recognised feature groupings e.g. "window" or "dirty brickwork". The grouping and labelling methods will likely follow Huet or Sarkar
The goal of this project is to build image processing that will allow facial expression to be estimated in 2D images of faces.
The method used will follow that of Cootes and Taylor and may use an approach akin to Lowe to find distinctive features within a face image as anchor points for the active appearance model of Cootes and Taylor.