This project aims to explain some statistical properties of natural images via a fundamental hypothesis that images are made up of objects. Object-based modelling and mutual information will be used to develop a novel approach for explaining non-Gaussianity of images. Internal features of natural images will be investigated mathematically and statistically with the aim of creating new mathematical tools to be incorporated into real digital devices.

Project staff and support

Nassir Mohammad (Postgraduate Associate, Cardiff University)
Alexander Balinsky (Academic supervisor, Cardiff University)
Stephen Pollard (Industrial supervisor, HP Labs)
Vera Hazelwood (Technology Translator, Industrial Mathematics KTN)

This project is being carried out at Cardiff University, in conjunction with HP Labs. It is supported by an EPSRC industrial CASE award, made available through the Knowledge Transfer Network for Industrial Mathematics. Start date: October 2007; duration: 3.5 years.