Show simple item record

dc.contributor.advisor Labrosse, Frédéric
dc.contributor.advisor Neal, Mark Woodland, Alan 2010-04-30T08:16:25Z 2010-04-30T08:16:25Z 2010-03
dc.description.abstract Images of objects (e.g. a rotating teapot, views from a camera mounted on a robot, an actor illuminated from different positions on a hemisphere, etc.) which vary between them by some controlled parameter tend not to be randomly located in the space of all possible w×h pixel images. Instead, with each pixel comprising of c colour components, each image forms one w×h×c dimensional position vector, in a space commonly referred to as image space. Instead of these images being randomly located, small changes in the sampling parameters normally produce neighbouring images in image space. This in turn can form structures, such as curves, surfaces, or more generally manifolds in image space. These are not novel, and commonly referred to as image manifolds in the literature. To date studies of image manifolds have been limited in both scope and application. This work presents an investigation of some of the features of 28 specific collections of images from a diverse range of sources, which potentially form image manifolds. We investigate several properties of these image manifolds — their general shape, and curvature. Image manifolds are well known not to be simple linear structures, instead, as we see in our study they are highly complex shapes. The main contribution of this work however, is a study of two novel approaches to numerical modelling of these image manifolds. Given the highly curved nature of image manifolds, which our investigation into the specific datasets confirmed, our approach is based upon extended versions of two techniques (NURBS and PDE Surfaces) typically used in the field of computer graphics to model curves and surfaces in 3-D space. Our approach is to construct exact geometric models, in image space, of the underlying image manifolds. The number of sample images required to adequately represent the appearance of an object or environment is a complex function of the subject itself. We show that it is possible to produce acceptable (depending on the application, which we discuss briefly), compact representations of objects and environments using our models. Furthermore we show that an awareness of simple geometric properties can improve the construction of such models, by focusing on improving the model in higher curved areas. en
dc.description.sponsorship APRS en
dc.language.iso en en
dc.publisher Aberystwyth University en
dc.title On Modelling and Understanding Image Manifolds en
dc.type Text en
dc.publisher.department Computer Science en
dc.type.qualificationlevel doctoral en
dc.type.qualificationname PhD en
dc.type.publicationtype thesis or dissertation en

Files in this item

Aside from theses and in the absence of a specific licence document on an item page, all works in Cadair are accessible under the CC BY-NC-ND Licence. AU theses and dissertations held on Cadair are made available for the purposes of private study and non-commercial research and brief extracts may be reproduced under fair dealing for the purpose of criticism or review. If you have any queries in relation to the re-use of material on Cadair, contact

This item appears in the following Collection(s)

Show simple item record

Search Cadair

Advanced Search