期刊名称：International Journal of Computer Science & Information Technology (IJCSIT)
印刷版ISSN：0975-4660
电子版ISSN：0975-3826
出版年度：2012
卷号：4
期号：3
页码：61
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：In this paper, we have made improvements in region growing image segmentation. The First one is seedsselect method, we use Harris corner detect theory to auto find growing seeds. Through this method, we canimprove the segmentation speed. In this method, we use the Improved Harris corner detect theory formaintaining the distance vector between the seed pixel and maintain minimum distance between the seedpixels. The homogeneity criterion usually depends on image formation properties that are not known to theuser. We induced a new uncertainty theory called Cloud Model Computing (CMC) to realize automatic andadaptive segmentation threshold selecting, which considers the uncertainty of image and extracts conceptsfrom characteristics of the region to be segmented like human being. Next to region growing operation, weuse canny edge detector to enhance the border of the regions. The method was tested for segmentation onX-rays, CT scan and MR images. We found the method works reliable on homogeneity and regioncharacteristics. Furthermore, the method is simple but robust and it can extract objects and boundarysmoothly.
关键词：region growing; segmentation; seeds selection; homogeneity criterion; cloud model
