BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:Europe/Paris X-WR-TIMEZONE:Europe/Paris BEGIN:VEVENT UID:5490@i2m.univ-amu.fr DTSTART;TZID=Europe/Paris:20130131T140000 DTEND;TZID=Europe/Paris:20130131T150000 DTSTAMP:20241028T215631Z URL:https://www.i2m.univ-amu.fr/evenements/e-vural-epfl-transformation-inv ariant-analysis-of-visual-signals-with-manifold-models/ SUMMARY: (...): E. Vural (EPFL): Transformation-invariant analysis of visua l signals with manifold models DESCRIPTION:: Transformation-invariant analysis of visual signals with mani fold models\n\nBy Elif Vural\, EPFL.\n\nManifold models provide low-dimens ional representations that are useful for processing and analyzing visual signals in a transformation-invariant way. The set of images generated by the geometric transformations of a reference visual pattern is called the transformation manifold of that pattern. In an image registration applicat ion where the data conforms to a parametrizable geometric transformation m odel\, the registration problem can be formulated as the computation of th e projection of the target image onto a reference transformation manifold. Similarly\, in a classification application where the data has undergone geometric transformations\, the resulting nonlinear structure of data samp les can be captured through the use of pattern transformation manifolds. A pproximating the data samples of each class with a different transformatio n manifold\, one can estimate the class label of a query data sample by co mparing its distance to the candidate class-representative transformation manifolds. In this talk\, we will discuss several aspects of transformatio n-invariant image analysis with manifold models such as the learning and s ampling of transformation manifolds. CATEGORIES:Séminaire,Signal et Apprentissage END:VEVENT BEGIN:VTIMEZONE TZID:Europe/Paris X-LIC-LOCATION:Europe/Paris BEGIN:STANDARD DTSTART:20121028T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET END:STANDARD END:VTIMEZONE END:VCALENDAR