Title :
On affine invariance in the Beltrami framework for vision
Author_Institution :
Dept. of Appl. Math., Tel Aviv Univ., Israel
Abstract :
We use the geometric Beltrami framework to incorporate and explain some of the known invariant flows, e.g., the equi-affine invariant flow. It is also demonstrated that the new concepts put forward in this framework enable us to construct new invariant flows for the case where the codimension is greater than one, e.g., for color images and video
Keywords :
computational geometry; computer vision; image colour analysis; video signal processing; affine invariance; color images; computer vision; equi-affine invariant flow; geometric Beltrami framework; video; Color; Computer vision; Distance measurement; Equations; Geometry; Image recognition; Mathematics; Shape; Surface treatment; Volume measurement;
Conference_Titel :
Variational and Level Set Methods in Computer Vision, 2001. Proceedings. IEEE Workshop on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7695-1278-X
DOI :
10.1109/VLSM.2001.938881
