Blur-Invariant Similarity Measurement of Images

0543871 - ÚTIA 2022 RIV US eng J - Článek v odborném periodiku
Lébl, Matěj - Šroubek, Filip - Flusser, Jan
Blur-Invariant Similarity Measurement of Images.
IEEE Transactions on Pattern Analysis and Machine Intelligence. Roč. 43, č. 8 (2021), s. 2882-2884. ISSN 0162-8828. E-ISSN 1939-3539
Grant CEP: GA ČR GA18-07247S
Institucionální podpora: RVO:67985556
Klíčová slova: Blurred image classification * invariant distance * subspace projections * constrained minimization
Obor OECD: Computer hardware and architecture
Impakt faktor: 24.314, rok: 2021
Způsob publikování: Omezený přístup
http://library.utia.cas.cz/separaty/2021/ZOI/sroubek-0543871.pdf https://www.computer.org/csdl/journal/tp/2021/08/09250602/1oxk0p0WumA

This article is a comment on the recent TPAMI paper (Gopalan et al., 2012) that introduced a blur-invariant distance measure between two images. We point out two mistakes of the theory presented in (Gopalan et al., 2012) and propose a correction. We also compare the original and corrected methods experimentally.
Trvalý link: http://hdl.handle.net/11104/0320990