Handling Gaussian Blur without Deconvolution

0522528 - ÚTIA 2021 RIV GB eng J - Článek v odborném periodiku
Kostková, Jitka - Flusser, Jan - Lébl, Matěj - Pedone, M.
Handling Gaussian Blur without Deconvolution.
Pattern Recognition. Roč. 103, č. 1 (2020), č. článku 107264. ISSN 0031-3203. E-ISSN 1873-5142
Grant CEP: GA ČR GA18-07247S
Institucionální podpora: RVO:67985556
Klíčová slova: Gaussian blur * Semi-group * Projection operator * Blur invariants * Image moments * Affine transformation * Combined invariants
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impakt faktor: 7.740, rok: 2020
Způsob publikování: Omezený přístup
http://library.utia.cas.cz/separaty/2020/ZOI/kostkova-0522528.pdf https://www.sciencedirect.com/science/article/pii/S0031320320300698

The paper presents a new theory of invariants to Gaussian blur. Unlike earlier methods, the blur kernel may be arbitrary oriented, scaled and elongated. Such blurring is a semi-group action in the image space, where the orbits are classes of blur-equivalent images. We propose a non-linear projection operator which extracts blur-insensitive component of the image. The invariants are then formally defined as moments of this component but can be computed directly from the blurred image without an explicit construction of the projections. Image description by the new invariants does not require any prior knowledge of the blur kernel parameters and does not include any deconvolution. The invariance property could be extended also to linear transformation of the image coordinates and combined affine-blur invariants can be constructed. Experimental comparison to three other blur-invariant methods is given. Potential applications of the new invariants are in blur/position invariant image recognition and in robust template matching.
Trvalý link: http://hdl.handle.net/11104/0307360