. . "P(1ET400750407), P(1M0572), P(2C06019), P(GA102/08/0593), Z(AV0Z10750506)" . "Segmentace je z\u00E1kladn\u00ED proces, kter\u00FD rozd\u011Bluje datov\u00FD prostor na smyslupln\u00E9 charakteristick\u00E9 podprostory. Segmentace obrazu z\u00E1sadn\u011B ovliv\u0148uje celkovou spolehlivost ka\u017Ed\u00E9ho automatick\u00E9ho syst\u00E9mu obrazov\u00E9 anal\u00FDzy. Oblasti obrazu, homogenn\u00ED vzhledem k n\u011Bjak\u00E9, obvykle texturn\u00ED nebo spektr\u00E1ln\u00ED m\u00ED\u0159e a kter\u00E9 jsou v\u00FDsledkem segmentace, jsou n\u00E1sledn\u011B analyzov\u00E1ny v interpreta\u010Dn\u00ED \u010D\u00E1sti metod. Kapitola popisuje n\u011Bkolik nov\u00FDch metod ne\u0159\u00EDzen\u00E9 segmentace textur, zalo\u017Een\u00FDch na markovsk\u00FDch prostorov\u00FDch modelech s nezn\u00E1m\u00FDm po\u010Dtem t\u0159\u00EDd. Tyto metody jsou intenzivn\u011B testov\u00E1ny na Pra\u017Esk\u00E9m segmenta\u010Dn\u00EDm benchmarku p\u0159i pou\u017Eit\u00ED b\u011B\u017En\u00FDch segmenta\u010Dn\u00EDch kriteri\u00ED. V\u00FDsledky t\u011Bchto komplexn\u00EDch test\u016F ukazuj\u00ED, \u017Ee na\u0161e metody p\u0159ed\u010D\u00ED n\u011Bkter\u00E9 publikovan\u00E9 alternativn\u00ED segmenta\u010Dn\u00ED metody textur."@cs . "Vienna" . . "[590E262002E3]" . . "In-Tech" . "536"^^ . . . "Ne\u0159\u00EDzen\u00E1 segmentace textur"@cs . "Haindl, Michal" . . . "22"^^ . "RIV/67985556:_____/08:00317725" . "Mike\u0161, Stanislav" . . "texture segmentation; image segmentation; unsupervised segmentation"@en . . "Unsupervised Texture Segmentation"@en . "Ne\u0159\u00EDzen\u00E1 segmentace textur"@cs . "Pattern Recognition" . "RIV/67985556:_____/08:00317725!RIV09-GA0-67985556" . . "401495" . . . "Unsupervised Texture Segmentation" . "Unsupervised Texture Segmentation" . . "2"^^ . . . "Segmentation is the fundamental process which partitions a data space into meaningful salient regions. Image segmentation essentially affects the overall performance of any automated image analysis system thus its quality is of the utmost importance. Image regions, homogeneous with respect to some usually textural or colour measure, which result from a segmentation algorithm are analysed in subsequent interpretation steps. Several new unsupervised multispectral texture segmentation methods based on underlying Markovian spatial models with unknown number of classes are presented in the chapter. The performances of the presented methods are extensively tested on the Prague segmentation benchmark using the commonest segmentation criteria and compares favourably with several alternative texture segmentation methods." . . . . . "Unsupervised Texture Segmentation"@en . "2"^^ . "Segmentation is the fundamental process which partitions a data space into meaningful salient regions. Image segmentation essentially affects the overall performance of any automated image analysis system thus its quality is of the utmost importance. Image regions, homogeneous with respect to some usually textural or colour measure, which result from a segmentation algorithm are analysed in subsequent interpretation steps. Several new unsupervised multispectral texture segmentation methods based on underlying Markovian spatial models with unknown number of classes are presented in the chapter. The performances of the presented methods are extensively tested on the Prague segmentation benchmark using the commonest segmentation criteria and compares favourably with several alternative texture segmentation methods."@en . . "978-953-7619-24-4" .