Two PhD studentships at Surrey

Two PhD studentships at Surrey

Posted by Rebecca Martin on Fri, 25/06/2010 - 00:00

Two PhD Studentships
University of Surrey,
Centre for Vision, Speech and Signal Processing (CVSSP)

Transfer learning for sports video understanding

CVSSP are offering an EPSRC funded 3 year PhD studentship in Computer
Vision within the area of Video Understanding and Transfer Learning. The
studentship covers UK/EU tuition fees plus a maintenance grant for three

This PhD shall use video analysis techniques in order build an adaptable
system to provide high level description of game events. Most
importantly, the research will focus on transferring knowledge from one
game modality to another. Multiple cues shall be used. The student will
join a team of people who are already working on different aspects of
this problem, such as player action classification, ball event detection
and audio pattern recognition. This is part of the
ACASVA project (

Pose invariant face recognition

Face recognition is a challenging application for computer vision for a
number of reasons. First of all, faces in a general pose cannot be
easily registered in a consistent manner. Second, illumination tends to
play a dominating influence in assessing the similarity of two face
images. Third, uncontrolled pose often implies poor resolution, which
further complicates the face recognition problem. This PhD project will
tackle these problems with the help of a morphable 3D face model. By
fitting such a model to 2D face image, it should be possible to correct
the pose of the input image and perform the matching in a standard
frontal pose. More over, it should be possible to use the 3D model to
relight the query image to achieve photometric normalisation.

Application procedure

Please send the completed Postgraduate Research Programmes application
form, available from, to Prof J
Kittler by email to Please address any enquiries
to Dr Teo de Campos at T.Decampos(at)

The successful candidates will have strong mathematical background and
programming skills in C++. Research experience in Vision and Machine
Learning will be a plus.

CVSSP is part of the Faculty of Engineering and Physical Sciences, which
received the highest rating of 5**A in the 2001 Research Assessment
Exercise (RAE), and ranked 2nd in the 2008 RAE with the highest number
of research active staff.

Applicants are required to have a First Class (or good 2.1) Honours or
Masters Degree in a related discipline (for example, Electronic
Engineering or Computer Science). The successful candidate will receive
a studentship paying full “Home” (UK/EU) level fees, and a maintenance
grant for three years subject to satisfactory progress.