Computer vision and image processing

Our research centres on the general question of how computers can efficiently extract useful information from images, videos and associated data

We research artificial intelligence and machine learning, including deep learning, for multi-modal image and video processing. We develop algorithms and software for tasks such as detection, segmentation, recognition, reconstruction, inference, prediction, and assessment.

We collaborate extensively with researchers in other fields and with companies to develop computational methods that impact on a wide range of application areas such as healthcare, biomedical imaging, space exploration, spatial-omics and biometrics.