基于小波包和区域生长的脑组织图像分割

摘要

This paper researches on the image segmentation of using region growing method. It presents a new method of MR brain tissue-image segmentation. This method decomposes the medical-image using wavelet packets,and segments the reconstructed approximate image based on region growing method.This method makes region growing method less sensitive to noise and decreases cavities and stomas of the images.The experimental result shows that the method is effective for MR brain tissue-image segmentation.%对利用区域生长进行图像分割问题进行了研究,提出了一种MR脑组织图像分割的方法.该方法利用小波包对医学图像进行分解,通过对重构后的近似图像采用区域生长法进行分割,降低了区域生长算法对噪声的敏感度,减少了利用区域生长算法分割后图像的空洞和小孔.实验证明了该方法对MR脑组织图像分割可以有效减少分割后的小孔和空洞,取得了良好的分割结果.