Autor:	Chung-Chi Wang, 王中岐
Rok vydání:	2004
Druh dokumentu:	學位論文 ; thesis
Popis:	92 Many color image segmentation techniques have been developed over the years. In this paper, a segmentation algorithm for color images based on the morphological and K-mean techniques is proposed. First, the morphological opening operation is used to remove noisy and smoothing in color image. Secondly, a unsupervised K-mean algorithm is used to segment different color image in nineteen color spaces .The optimal number of clusters is chosen by this unsupervised K-mean algorithm. Finally, the segmentation results of nature scene color images in different color spaces are compared by visual judgment.
Databáze:	Networked Digital Library of Theses & Dissertations
Externí odkaz:	http://ndltd.ncl.edu.tw/handle/86721206304954126103 Zobrazit plný text záznamu