改进的分水岭算法在医学图像分割中的应用

针对传统分水岭算法对噪声敏感和易于产生过分割的问题,提出了一种将同态滤波增强与控制标记符分水岭相结合的分割策略.该方法先进行同态滤波增强预处理,再采用改进控制标记符的分水岭分割算法进行分割.仿真实验表明,提出的算法很好地抑制了过分割,实现了有意义的医学图像区域分割,同时还具有较强的区域轮廓定位能力,不需要再进行后续的合并处理,算法简单,并且能够适应医学图像分类与信息提取的需求.

Application of Improved Watershed Algorithm in Image of Medical Image Segmentation

Aimed at resolving the problems of sensitivity to noise and over-segmentation existing in traditional watershed algorithm,an image segmentation strategy on the combination of homomorphic filter and marker controlled watershed is proposed.Firstly,use the big structural elements and small structure elements with respective advantage multi-scale morphology edge detection abate over-segmentation;secondly,use the fuzzy enhancement make original medical image of the edge of degree to get enhancement;finally,the image is segmented with a marker-based watershed algorithm.Simulation experiments show that the algorithm was useful for the reduction of over segmentation and can be applied to the segmentation of digital medical images,don't need to carry on the following merger processing,and segmentation algorithm is simple,and has the characteristics of multiple scales,thus is quite qualified for classification and information extraction of medical sensed imagery.