Our work crosses many domains including the development of novel machine/ deep learning methodology, solution techniques, pose estimation, medical imaging and forensic identification.



Biometrics and Forensic Identification

Our work focuses on the development of computer vision techniques for the forensic identification of individuals and criminal evidence, primary through photo and video. This multidisciplinary work includes identification through and the study of anatomical variability, age estimation, scene comparison, localisation and transcription of text.

H-Unique

Large Scale Identification in Natural Scenes

Optical Character Recognition

Medical Imaging

Our work in medical imaging focuses on the development of computer vision techniques to automatically analyse and interpret medical images, including tomography and pre-clinical imaging. We have a strong focus on pathology extraction and measurement, diagnosis and technology development in ophthalmic imaging, cancer and COVID-19.

Glaucoma Diagnosis

Breast Cancer

COVID-19 Prognosis

Computer Vision

Computer vision is a field of artificial intelligence (AI) that enables computers and systems to derive meaningful information from digital images, videos and other visual inputs in order to take actions or make recommendations based on that information. Much of our work is centred on the development of computer vision methodology in diverse areas, including pose estimation, pharmaceutical manufacturing, and environmental science.

Pose Estimation

Pharmaceutical Manufacturing

Environmental Science

Machine Learning

Machine learning (ML) is a subfield of AI that is devoted to understanding and building methods that are capable of learning, i.e. they can leverage data to improve performance on a task or set of tasks. Our work in machine learning focuses on algorithm development, efficient methodology, and numerical solution techniques.

Deep Learning

Image Segmentation

Classification

Publications


2022


2021


2020


2019