期刊名称：Canadian Journal on Image Processing and Computer Vision
印刷版ISSN：1923-1717
出版年度：2011
卷号：2
期号：1
页码：8-11
出版社：AM Publishers Corporation Canada
摘要：Image Segmentation is an essential step to detect any object in any textural image. This is the hardest task to categorize the texture and any object in the image while without information about the texture. In this paper an algorithm is proposed which segment the image by separating the texture (may be more than two textures) and any object if exist. This algorithm is designed providing flexibility according to different type of textures and then it is able to be apply at all type of textures and gives more better results than available algorithms. An experiment has been done on a sample of color images (some of them are shown), segmentation has been done very efficiently describing the object(s) if exist while image contains different type of textures.
