Chris Town

Chris Town

Information on part II/part III/MPhil project suggestions.


I'm an Affiliated Lecturer in the Department of Computer Science and Technology and a Fellow at Wolfson College, where I am also a Tutor and Director of Studies in Computer Science (see "why Wolfson?").

I completed my PhD here at the University of Cambridge Computer Laboratory (Computer Science Department) under the supervision of John Daugman. My PhD thesis was awarded a prize in the BCS Distinguished Dissertation Awards in 2005. Apart from carrying our research (see below), I also continue to supervise undergraduate and Masters students in Computer Science (see here for a list of suggested final year projects). I co-lecture the Part III/ACS Computer Vision module (previously known as LE48, EF12) and I lectured and examined the Part II Computer Vision course (I regularly give guest lectures and supervisions for this course).

My PhD was sponsored by AT&T Labs Research through an Industrial Fellowship from the Royal Commission for the Exhibition of 1851 and various scholarships from Trinity College. Before starting my PhD I completed a pre-doc year at AT&T Laboratories Cambridge and summer internships at AT&T in the USA and Cambridge. Prior to that I received my undergraduate degree with first class honours in Computer Science from the University of Cambridge (Trinity College).


Despite the dramatic growth of digital image and video data in recent years, many challenges remain in enabling computers to interpret visual content. Visual information is inherently ambiguous and semantically impoverished. There consequently exists a wide semantic gap between human interpretations of image and video data and those currently derivable by a computer. My research demonstrates how this gap can be narrowed through the use of ontologies which represent task-specific attributes, objects, and relations, and relate these to the processing modules available for their detection and recognition. Terms in the ontology therefore carry meaning directly related to the appearance of real world objects. Tasks such as image retrieval, automated visual surveillance, and visually mediated human computer interaction can then be carried out by processing sentences in a visual language defined over the ontology. The efficacy of the proposed approach is demonstrated through the development and analysis of solutions to a range of challenging visual analysis problems. Current results are extremely encouraging and open up a range of opportunities for further research.

One avenue for current work is the use of grid computing to allow massively parallelised image analysis and retrieval. This work is being done in collaboration with the University of Cambridge eScience Centre. Content-based image analysis and ontology-based information modeling are starting to revolutionise professional image search and can also be used to greatly speed up time consuming tasks such as image annotation.

I am also actively working on pattern matching algorithms for the biological sciences. A generic image processing and identification tool has been developed by me and ise available for free use by the academic community. It has already been deployed for research in various fields of ecology and zoology, for examples Manta Matcher and NPM.


Peer-reviewed Academic Publications



I have experience supervising many of the Cambridge Computer Science undergraduate courses and teaching the Part III/ACS Computer Vision module and Part II Computer Vision course. In addition, I have thus far supervised about 50 final-year Computer Science projects and dissertations. I have a list of suggested projects suitable for Part II, part III or ACS students which I would be happy to supervise. Please get in touch if you are interested in these.

Contact details


Chris Town, Copyright 2018