Title :
Combined invariants to convolution and rotation
Author :
Zitová, Barbara ; Flusser, Jan
Author_Institution :
Inst. of Inf. Theory & Autom., Czechoslovak Acad. of Sci., Prague, Czech Republic
Abstract :
A new class of moment-based features invariant to image rotation and to convolution with an unknown point-spread function is introduced. These features can be used for the recognition of objects captured by a nonideal imaging system of unknown position and blurring parameters. Practical application to satellite image registration is presented
Keywords :
convolution; image registration; object recognition; optical transfer function; combined invariants; convolution; image rotation; moment-based features; nonideal imaging system; object recognition; satellite image registration; unknown point-spread function; Additive noise; Automation; Convolution; Geometry; Image analysis; Image recognition; Image registration; Information theory; Satellites; Solid modeling;
Conference_Titel :
Image and Signal Processing and Analysis, 2000. IWISPA 2000. Proceedings of the First International Workshop on
Conference_Location :
Pula
Print_ISBN :
953-96769-2-4
DOI :
10.1109/ISPA.2000.914896