39 KB255 KB23 KB200020242005Tian, JieWang, Xiaoxiangštevilka:1letnik:247 stranistr. 1-7ISSN:1580-3139COBISSID:20442585URN:URN:NBN:SI:doc-BJFDJ3NZenDruštvo za stereologijo in kvantitativno analizo slike, Medicinska fakultetaImage analysis and stereologyImage Processing, Computer-AssistedMagnetic Resonance ImagingMagnetna resonanca slikovnaobdelava slikSlika, obdelava z računalnikomstereologijaTomografija radiografska, računalniškaTomography, X-Ray ComputedImage registration based on maximization of gradient code mutual information|Herein one proposes a mutual information-based registration method using pixelgradient information rather than pixel intensity information. Special care is paid to finding the global maximum of the registration function. In particular, one uses simulated annealing method speeded up by including a statistical analysis to reduce the next search space across the cooling, schedule. An additional speed up is obtained by combining this numerical strategy with hill-climbing method. Experimental results obtained on a limiteddatabase of biological images illustrate that the proposed method for image registration is relatively fast and performs well as the overlap betweenthe floating and reference images is decreased and/or the image resolution is coarsenedTEXTznanstveno časopisjejournalsSlovenian National E-content AggregatorNational and University Library of SloveniaDruštvo za stereologijo in kvantitativno analizo slike