Department of Image Processing

Invariants to convolution and rotation

Monography Chapter

Zitová Barbara, Flusser Jan

serial: Invariants for Pattern Recognition and Classification, p. 23-46 , Eds: Rodrigues M. A .

publisher: World Scientific, (Singapore 2000)

edition:

research: AV0Z1075907

project(s): GA106/97/0827, GA ČR, IZ4178, MZ

abstract (eng):

We introduce a new class of moment-based features invariant to image rotation, translation, scaling, contrast changes and also to convolution with an unknown point-spread function. These features can be used for the recognition of objects captured by anonideal imaging system of unknown position and blurring parameters as well as in many other tasks when dealing with non-ideal, blurred and geometrically distorted images. Practical application to satellite image registration is presented.

Cosati: 09K

RIV: JD