基于改进的Otsu准则的递归图像分割算法

基于最大类间方差阈值图像分割算法的基本原理,然后结合目标与背景两类之间间距和类内距离对图像分割效果的影响,提出了一种改进的最大类间方差法,运用递归思想局部搜索图像的最佳阈值。这样不但缩短了计算时间,而且具有较好的自适应特点。该算法在图像背景不均匀或者图像的直方图不是简单的单峰、双峰图像的情况下可以进行有效的分割,分割后的图像细节更加丰富,能有效的去除噪声的干扰,有利于分割后的特征提取。本文对理论结果进行了仿真实验,获得了较好的分割效果。

A recursive image segmentation algorithm based on the modified Otsu's rule

Based on the principle of Otsu method with maximum variance between threshold algorithm of image segmentation,an improved method derived from Otsu algorithm is put forward,which combines interclass distance with intraclass distance,a partial recursive algorithm is used to search optimum threshold.lt not only reduces the running time,but also has better self-adaptability.With this algorithm,the image can be segmented effectively even if it is uneven and not the single-modal or bimodal one.The segmentation result has more details,and can remove the disturbance of the noise,which is good to feature extraction.An experiment with the result of theory is made and good result is obtained.