Aslan S.Akgül C.B.Sankur B.Tunalı, Turhan2023-06-162023-06-1620159.79E+12https://doi.org/10.5220/0005361802660271https://hdl.handle.net/20.500.14365/3823Institute for Systems and Technologies of Information, Control and Communication (INSTICC)10th International Conference on Computer Vision Theory and Applications, VISAPP 2015 -- 11 March 2015 through 14 March 2015 -- 112690We propose a new local image descriptor named SymPaD for image understanding. SymPaD is a probability vector associated with a given image pixel and represents the attachment of the pixel to a previously designed shape repertoire. As such the approach is model-driven. The SymPad descriptor is illumination and rotation invariant, and extremely flexible on extending the repertoire with any parametrically generated geometrical shapes and any desired additional transformation types. Copyright © 2015 SCITEPRESS - Science and Technology Publications All rights reserved.eninfo:eu-repo/semantics/openAccessImage featureImage understandingModel-driven visual dictionaryObject recognitionPrimitive structures of natural imagesImage understandingMathematical transformationsObject recognitionGeometrical shapesImage featuresLocal image descriptorsNatural imagesProbability vectorRotation invariantTransformation typesVisual dictionariesPixelsConference Object10.5220/00053618026602712-s2.0-84939554100