MathsNet: Research Student Directory

Name Sajib, Anamul H
Group Statistics and Probability
Room A14, Math Sci
Telephone +44 (0) 115 82 32068 [direct dial]
Thesis Title Unlabelled shape analysis
Thesis Abstract Statistical shape analysis involves investigating the statistical properties of objects that are invariant to certain transformations, such as rotations and translations. An added complication arises when the correspondence between points on different objects is unknown and needs to be inferred. This is known as unlabelled shape analysis. This project will involve developing and evaluating Bayesian models to tackle the unlabelled problem. With such models, posterior distributions are often complicated, with multiple modes, so the project will require efficient and effective sampling schemes to be developed. Possible applications to be considered include identifying shapes common to molecules with similar biological activity and analysing the shape outlines of lung images.
School contact information School of Mathematical Sciences
University of Nottingham
University Park
Nottingham, NG7 2RD
Tel: +44 (0) 115 951 4949
Fax: +44 (0) 115 951 4951