基于自适应加权中值滤波的二维Otsu图像分割算法

摘要

The traditional two-dimensional Otsu image segmentation algorithm got ineffectively result in the image segmentation while the image contains lots of noise. To solve the problem, this paper proposed a new two-dimensional Otsu image segmentation algorithm based on adaptive weighted median filter. This method firstly preprocessed the image with noise by a new adaptive weighted median filter,then transferred the region division in two-dimensional histogram of median image from four partitions into two partitions,finally segmented the image accurately by an improved two-dimensional Otsu algorithm. The experimental results show that the proposed algorithm has better anti-noise performance and better segmentation result for image with noise.%为解决传统二维Otsu算法在含噪声较多的图像应用中分割效果较差这一问题,提出一种基于自适应加权中值滤波的二维Otsu图像分割算法.该算法首先利用一种新的自适应加权中值滤波对噪声图像中值滤波；然后将中值图像的二维直方图区域划分由四分法改为二分法；最后利用改进的二维Otsu算法对图像作精确分割.实验结果表明,该算法对灰度噪声图像具有更强的抗噪性且分割效果也更为理想.