Show simple item record

dc.contributor.advisorWilliams, Christopher
dc.contributor.authorAllan, Moray
dc.date.accessioned2008-08-08T13:40:41Z
dc.date.available2008-08-08T13:40:41Z
dc.date.issued2007
dc.identifier.urihttp://hdl.handle.net/1842/2430
dc.descriptionInstitute for Adaptive and Neural Computation
dc.description.abstractThis 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.en
dc.format.extent15244331 bytes
dc.format.extent87548017 bytes
dc.format.mimetypeapplication/pdf
dc.format.mimetypeapplication/octet-stream
dc.language.isoenen
dc.subjectInformaticsen
dc.subjectComputer Scienceen
dc.subjectmachine learningen
dc.subjectobject recognitionen
dc.subjectobject localisationen
dc.subjectimage interpretationen
dc.titleSprite Learning and Object Category Recognition using Invariant Featuresen
dc.typeThesis or Dissertationen
dc.type.qualificationlevelDoctoralen
dc.type.qualificationnamePhD Doctor of Philosophyen


Files in this item

This item appears in the following Collection(s)

Show simple item record