Wörgötter, Florentin Andreas

[["dc.bibliographiccitation.firstpage","81"],["dc.bibliographiccitation.journal","Advances in Imaging and Electron Physics"],["dc.bibliographiccitation.lastpage","146"],["dc.bibliographiccitation.volume","131"],["dc.contributor.author","Krüger, Norbert"],["dc.contributor.author","Wörgötter, Florentin"],["dc.contributor.editor","Hawkes, Peter"],["dc.date.accessioned","2017-09-07T11:45:35Z"],["dc.date.available","2017-09-07T11:45:35Z"],["dc.date.issued","2011"],["dc.description.abstract","This chapter presents the examples of the ambiguities of local visual data in different visual domains, such as line extraction, color, stereo, and local motion. This ambiguity can be resolved by the integration of information based on regularities in visual data. The integration takes place across the temporal and spatial domain, but also across different visual modalities. Natural images represent only a tiny subset of the set of possible images. Indeed, if an image would be produced by a random operator, there are no chances that it would look like something resembling a natural image. The image would look like white noise. Events in one frame can be used to predict events in a second frame, provided some information about the motion is collected. There exist two kinds of regularities: deterministic regularities and statistical regularities. Deterministic regularities allow for deterministic predictions that are in general based on analytically describable geometrical relations grounded on different perspectives of a scene or an object."],["dc.identifier.doi","10.1016/s1076-5670(04)31003-7"],["dc.identifier.gro","3151812"],["dc.identifier.uri","https://resolver.sub.uni-goettingen.de/purl?gro-2/8642"],["dc.language.iso","en"],["dc.notes.status","public"],["dc.notes.submitter","chake"],["dc.relation.isbn","978-0-12014-773-1"],["dc.relation.issn","1076-5670"],["dc.title","Statistical and Deterministic Regularities: Utilization of Motion and Grouping in Biological and Artificial Visual Systems"],["dc.type","journal_article"],["dc.type.internalPublication","unknown"],["dc.type.peerReviewed","no"],["dspace.entity.type","Publication"]]