0411458 20240103182329.120060210235959.9 7 s. 1-70-7695-2454-0Los AlamitosIEEE2005 cervical cancer detection colposcopy digital image processing time analysis cav_un_auth*0213263 Acosta-Mesa H. G. MX 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*0213264 Ríos-Figueroa H. V. MX cav_un_auth*0213265 Cruz-Ramírez N. V. MX cav_un_auth*0213266 Marín-Hernández A. MX cav_un_auth*0213267 Hernández-Jiménez R. MX cav_un_auth*0213268 Cocotle-Ronzón B. E. MX cav_un_auth*0213269 Hernández-Galicia E. MX 09K CEZ:AV0Z10750506 Methodology for analysis of the colposcopic images is presented to help experts to create robust diagnosis of cervical cancer. The image registration was applied using phase correlation followed by a locally applied algorithm based on the normalized cross correlation. Time analysis of the obtained features is realized in the Hough space. Supervised Bayesian learning is used for classification and resulting labels are used for tissue categorization. V nasem clanku je prezentovana metodologie pro analyzu kolposkopickych obrazku, ktera muze napomoci expertum vytvorit kvalitnejsi diagnozu rakoviny cipku. Geometricka registrace snimku je realizovana pomoci fazove korelace, nasledovane lokalne aplikovanou normalizovanou kros-korelaci. Casova analyza ziskanych priznaku je provedena v Hough prostoru. Zaverecna klasifikace tkani vychazi z teorie Bayesovske klasifikace. cav_un_auth*0213270 Mexican International Conference in Computer Science. ENC'05 Puebla MX 26.09.2005-30.09.2005 JD 2010 ZOI http://hdl.handle.net/11104/0131539 2005 Proceedings of the Mexican International Conference on Computer Science ENC'05 0-7695-2454-0 1 7 Los Alamitos IEEE 2005