Artificial intelligence and visual document analysis
The project will investigate the intersection of artificial intelligence (AI), natural language processing (NLP) and computer vision, specifically targeting the automated visual analysis of scanned physical documents using deep neural networks.
Start date1 April 2019
Funding sourceThe University of Surrey
Funding will provide an annual tax-free stipend of approximately £14,777 and coverage of the home/EU tuition fees for 3.5 years. Funding for this project is available to citizens of EU/UK students only.
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 artificial intelligence (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.
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).
UK/EU students only.