摘要
针对OTSU方法的局限性 ,提出了一种基于显著性的OTSU局部递归分割算法 .该算法的思路是把一次OTSU分割得到的目标区域作为新的图像进行下一次OTSU分割 ,依次递归下去 ,直到满足一定条件为止 ,然后把每次分割得到的目标区域按照一定加权原则累加起来 ,得到分割结果图像 .实验结果表明 ,在不同的冷背景下 ,基于显著性的OTSU局部递归分割算法能够稳定地实现目标分割提取 。
In view of the limitations of OTSU algorithm, an algorithm for salience based local recursive OTSU segmentation (SBLR OTSU) is proposed. The main technique of SBLR OTSU consists in that the object area resulting from OTSU is regarded as the whole image to be segmented at the next OTSU segmentation. The process goes on sequentially until definite conditions are satisfied. Then all the object areas resulting from OTSU are accumulated to yield the image of segmentation results. It is shown by experimental results that, under different cold background conditions, the algorithm in question is robust against background clutter and capable of realizing object segmentation and extraction.
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2002年第9期57-59,共3页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
基金
武器装备预研基金资助项目
