This project is available suitable for a 1-year MSc in Physics. The project does not currently have funding attached, students must be able to fund the fees and their living costs either through their own funds or a scholarship. Current information on fees is available here.
Supervisor: Adrian Bradu; Co-supervisor: Konstantin Kapinchev
Machine learning is a new branch in computer science with significant impact in areas including speech recognition, computer vision, self-driving vehicles, medical diagnosis and many others. There is a very high demand for machine learning experts, both in academia and the industry. This project will provide students with the opportunity to develop their skills and prepare them for future employment. The project is focused on the development of machine learning solutions in image processing. These solutions will be applied for pattern recognition, image segmentation, registration, noise reduction and not only.
The programs will process data delivered in real-time by imaging instruments developed within the Applied Optics Group such as Optical Coherence Tomography or/and Photo-acoustics Tomography devices. Their performance is essential for the overall real-time operation of the instruments. Therefore, the solutions will be implemented by using high-performance GPU-based parallel environments, such as NVIDIA CUDA C++ and OpenCL. Throughout the project, the student will have the opportunity to: – gain knowledge and skills in using programming environments and languages, such as C/C++, NVIDIA CUDA and OpenCL – understand how signal processing algorithms are applied in science and engineering – work with state-of-the-art equipment – integrate own software solutions into working imaging systems – improve the ability to solve real-life problems – publish their results in world-leading journals and conferences.
The project will manly involve computational work in C/C++ (CUDA) and extensive interaction with researchers in the Applied Optics Group. It would therefore suit graduates with a background in computing. However, graduates in engineering, physics, or a related subject are also encouraged to apply if they have strong computational skills.
There is no deadline for the project – applicants will be assessed on a rolling basis – although please note any separate deadlines for scholarships or funding. For further information or informal enquiries, please contact Dr Adrian Bradu (A.Bradu@kent.ac.uk).