Extensions of independent component analysis for natural image data

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Inki, Mika
dc.date.accessioned 2012-02-13T13:09:51Z
dc.date.available 2012-02-13T13:09:51Z
dc.date.issued 2004-12-10
dc.identifier.isbn 951-22-7363-2
dc.identifier.issn 1459-7020
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/2496
dc.description.abstract An understanding of the statistical properties of natural images is useful for any kind of processing to be performed on them. Natural image statistics are, however, in many ways as complex as the world which they depict. Fortunately, the dominant low-level statistics of images are sufficient for many different image processing goals. A lot of research has been devoted to second order statistics of natural images over the years. Independent component analysis is a statistical tool for analyzing higher than second order statistics of data sets. It attempts to describe the observed data as a linear combination of independent, latent sources. Despite its simplicity, it has provided valuable insights of many types of natural data. With natural image data, it gives a sparse basis useful for efficient description of the data. Connections between this description and early mammalian visual processing have been noticed. The main focus of this work is to extend the known results of applying independent component analysis on natural images. We explore different imaging techniques, develop algorithms for overcomplete cases, and study the dependencies between the components by using a model that finds a topographic ordering for the components as well as by conditioning the statistics of a component on the activity of another. An overview is provided of the associated problem field, and it is discussed how these relatively small results may eventually be a part of a more complete solution to the problem of vision. en
dc.format.extent 63, [98]
dc.format.mimetype application/pdf
dc.language.iso en en
dc.publisher Helsinki University of Technology en
dc.publisher Teknillinen korkeakoulu fi
dc.relation.ispartofseries Dissertations in computer and information science. Report D en
dc.relation.ispartofseries 9 en
dc.relation.haspart Mika Inki, 2003. ICA features of image data in one, two and three dimensions. Proceedings of the Fourth International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2003). Nara, Japan, 1-4 April 2003, pages 861-866. [article1.pdf] © 2003 by author.
dc.relation.haspart Mika Inki and Aapo Hyvärinen, 2002. Two approaches to estimation of overcomplete independent component bases. Proceedings of the International Joint Conference on Neural Networks (IJCNN 2002). Honolulu, Hawaii, USA, 12-17 May 2002, pages 454-459. [article2.pdf] © 2002 IEEE. By permission.
dc.relation.haspart Aapo Hyvärinen and Mika Inki, 2002. Estimating overcomplete independent component bases for image windows. Journal of Mathematical Imaging and Vision 17, number 2, pages 139-152. [article3.pdf] © 2002 Kluwer Academic Publishers. By permission.
dc.relation.haspart Aapo Hyvärinen, Patrik O. Hoyer and Mika Inki, 2001. Topographic independent component analysis. Neural Computation 13, number 7, pages 1527-1558.
dc.relation.haspart Mika Inki, 2003. Examining the dependencies between ICA features of image data. Proceedings of the 13th International Conference on Artificial Neural Networks / 10th International Conference on Neural Information Processing (ICANN/ICONIP 2003). Istanbul, Turkey, 26-29 June 2003, pages 298-301. [article5.pdf] © 2003 by author.
dc.relation.haspart Mika Inki, 2004. A model for analyzing dependencies between two ICA features in natural images. Proceedings of the Fifth International Conference on Independent Component Analysis and Blind Signal Separation (ICA 2004). Granada, Spain, 22-24 September 2004, pages 914-921. [article6.pdf] © 2004 Springer-Verlag. By permission.
dc.relation.haspart Mika Inki, 2004. Natural image patch statistics conditioned on activity of an independent component. Helsinki University of Technology, Publications in Computer and Information Science, Report A79. Espoo, Finland, 28 pages. [article7.pdf] © 2004 by author.
dc.subject.other Computer science en
dc.title Extensions of independent component analysis for natural image data en
dc.type G5 Artikkeliväitöskirja fi
dc.description.version reviewed en
dc.contributor.department Department of Computer Science and Engineering en
dc.contributor.department Tietotekniikan osasto fi
dc.subject.keyword independent component analysis en
dc.subject.keyword latent variable models en
dc.subject.keyword natural image data en
dc.subject.keyword overcomplete models en
dc.subject.keyword topographic mapping en
dc.subject.keyword higher order structures en
dc.identifier.urn urn:nbn:fi:tkk-004597
dc.type.dcmitype text en
dc.type.ontasot Väitöskirja (artikkeli) fi
dc.type.ontasot Doctoral dissertation (article-based) en
dc.contributor.lab Laboratory of Computer and Information Science en
dc.contributor.lab Informaatiotekniikan laboratorio fi


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search archive


Advanced Search

article-iconSubmit a publication

Browse

My Account