Abstract We describe a new theoretical approach to Image Processing and Vision. Expressed in mathemetical terminology, in our formalism image space is a fibre bundle, and the image itself is the graph of a section on it. This mathematical model has advantages to the conventional view of the image as a function on the plane: Based on the new method we are able to do image processing of the image as viewed by the human visual system, which includes adaptation and perceptual correctness of the results. Our formalism is invariant to relighting and handles seamlessly illumination change. It also explains simultaneous contrast visual illusions, which are intrinsically related to the new covariant approach. Examples include Poisson image editing, Inpainting, gradient domain HDR compression, and others.
Covariant Derivatives and Vision
2006-01-01
14 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Covariant Derivatives and Vision
British Library Conference Proceedings | 2006
|Covariant Buda-Lund particle interferometry
TIBKAT | 1998
|Feature uncertainty arising from covariant image noise
IEEE | 2005
|Rotation and translation covariant match kernels for image retrieval
British Library Online Contents | 2015
|Rotation and translation covariant match kernels for image retrieval
British Library Online Contents | 2015
|