SymPaD: Symbolic Patch Descriptor
Bildiriler > Tam Metin Bildiri
Yazarlar: Sinem Aslan, Ceyhun Burak Akgül, Bülent Sankur, Turhan Tunalı
Proceedings of the 10th International Conference on Computer Vision Theory and Applications, , , Uluslararası, Tam Metin Bildiri, ss 266-271
Özet
We 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.