数学形态学的纹理图像分割方法  

Image Segmentation Method about Mathematical Morphology Based on Textural Features

作　　者：赵福君[1] 李景文[1] 陈大克[1] 刘卉卉[1] 

机构地区：[1]桂林工学院,广西桂林541004

出　　处：《计算机技术与发展》2008年第5期112-114,共3页Computer Technology and Development

基　　金：国家自然科学基金资助项目(40574002);广西自然科学基金资助项目(0448076)

摘　　要：一幅图像往往包含许多区域,但在对图像的理解和分析时,往往只需要其中的某个部分。因此,为方便使用常需要对目标区域进行提取。从目标区域的整体纹理特征出发,根据纹理特征的不同多次使用数学形态学的基本运算,从而达到图像区域分割的方法。该方法通过一幅具有多种纹理图案的图像为例验证了方法的可行性和有效性。运用canny算子对该图像进行边缘检测,从检测的结果可看出,该方法优于基于边缘检测的图像分割方法。In order to facilitate to understand and analyse the picture, often needs to extract the target sector, so that this has become one of the most important and difficult in picture processing and recognition. Based on these, a method has been proposed in article, it is based on the different regions which have the different texture, and synthetically used the method of the mathematics morphology, like ireopen, imclose, fusion and so on. Given a representational example in article, the picture has the similitude but difference textures, so that the feasibility and the validity of this method can be shown clearly.

关 键 词：数学形态学 纹理特征 区域提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]