Information Services banner Edinburgh Research Archive The University of Edinburgh crest

Edinburgh Research Archive >
Informatics, School of >
Informatics thesis and dissertation collection >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1842/2430

This item has been viewed 15 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
source-files.zipOriginal files are restricted access85.5 MBZipped folder
allan2007-thesis.pdfOpen Access version14.89 MBAdobe PDFView/Open
Title: Sprite Learning and Object Category Recognition using Invariant Features
Authors: Allan, Moray
Supervisor(s): Williams, Christopher
Issue Date: 2007
Abstract: This thesis explores the use of invariant features for learning sprites from image sequences, and for recognising object categories in images. A popular framework for the interpretation of image sequences is the layers or sprite model of e.g.Wang and Adelson (1994), Irani et al. (1994). Jojic and Frey (2001) provide a generative probabilistic model framework for this task, but their algorithm is slow as it needs to search over discretised transformations (e.g. translations, or affines) for each layer. We show that by using invariant features (e.g. Lowe’s SIFT features) and clustering their motions we can reduce or eliminate the search and thus learn the sprites much faster. The algorithm is demonstrated on example image sequences. We introduce the Generative Template of Features (GTF), a parts-based model for visual object category detection. The GTF consists of a number of parts, and for each part there is a corresponding spatial location distribution and a distribution over ‘visual words’ (clusters of invariant features). We evaluate the performance of the GTF model for object localisation as compared to other techniques, and show that such a relatively simple model can give state-of- the-art performance. We also discuss the connection of the GTF to Hough-transform-like methods for object localisation.
Description: Institute for Adaptive and Neural Computation
Keywords: Informatics
Computer Science
machine learning
object recognition
object localisation
image interpretation
URI: http://hdl.handle.net/1842/2430
Appears in Collections:Informatics thesis and dissertation collection

Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2013, and/or the original authors. Privacy and Cookies Policy