Vision, Learning and Control (VLC) is a highly numerate group within the Department of Electronics and Computer Science covering much of the central theory in Electronics, Electrical Engineering and Computer Science. Our research covers a rich spread of technological areas over control, machine learning and computer vision, with a sizeable team of leading academics, PhD researchers and postdocs. Our facilities include a biometrics laboratory, a quiet room, and experimental production platforms, as well as high-performance computational and sensing equipment.
VLC’s research in image processing and computer vision spans techniques from preprocessing, to feature extraction and on to image analysis. VLC researchers have a long record in biometrics, pioneering work in gait and facial recognition. Work continues in these areas and VLC are now developing soft biometrics, learning from human labelling to augment or even replace the automatically derived measures. We are also actively working in new areas related to deep convolutional neural networks and feature learning, which cross the boundary with machine learning.
Machine learning in VLC covers a broad range of areas ranging from developing new classification and clustering tools for big data sets, mathematical modelling of complex systems and optimisation. Application areas include biological sequence analysis, gene regulation, text analysis, computer vision, recommender systems and combinatorial optimisation.
VLC researchers’ work on fundamental theory includes behavioural approaches to system theory, system identification particularly using structured low-rank approximations, multidimensional systems theory, robust nonlinear control, iterative learning control, adaptive control and flow control. They use a variety of techniques from linear algebra, functional analysis, partial differential equations and commutative algebra.