0410420 20240103182212.920060210235959.9 981-02-4278-6 Singapore World Scientific 2000 24 s. Series in Machine Perception and Artificial Intelligence. 42 23-46RodriguesM. A . cav_un_auth*0101238 Zitová Barbara UTIA-B Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101087 Flusser Jan UTIA-B Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. 09K GA106/97/0827 GA ČR cav_un_auth*0005588 IZ4178 MZ CZ cav_un_auth*0026944 AV0Z1075907 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. JD ZOI http://hdl.handle.net/11104/0130509 UTIA-B 20000136 2000 2000 Singapore World Scientific 981-02-4278-6 Invariants for Pattern Recognition and Classification 23 46 Rodrigues M. A . 340