The project will investigate the intersection of AI, natural language processing (NLP) and computer vision, specifically targeting the automated visual analysis of scanned physical documents using deep neural networks.
The PhD will develop new tools to summarise the content of documents in natural language, including characteristics of document layout, text, graphics on the page as well as any hand-made annotations on the physical document. The aim of the PhD is to develop AI algorithms to assist in summarising documents, their layout and changes made during a document’s lifecycle. The applications of this technology could include high volume document processing solutions (e.g. in finance) where anomalous changes to printed contracts (e.g. cross-throughs and corrections) need to be succinctly summarised in natural language, or in the improvement of accessible documents e.g. for visually impaired individuals who would benefit from the automated summarisation of text, graphics and charts in a physical document. The PhD is co-supervised between the Centre for Vision Speech and Signal Processing (CVSSP) and Xceptor a commercial company based on Surrey’s Research Park.
This project will start on the 1st April 2019 and will finish on the 30th September 2022.
Entry requirements: A first class or 2:1 honours degree (or equivalent overseas qualification) in an appropriate discipline (e.g. engineering, computer science, signal processing, applied mathematics, and physics) or MSc with Distinction (or 70% in average). IELTS 6.5 or above (or equivalent) with no sub-test of less than 6.