融合mean shift和区域显著性的彩色图像分割算法

Color image segmentation by fusion of mean shift and region saliency

提出了一种无监督的提取图像中显著区域的彩色图像分割算法。首先,运用meanshift算法对图像进行分割,得到初始的分割结果;然后,根据给出的区域显著性的定义和区域合并策略,对初始分割结果进行合并,得到最终的分割结果。仿真结果表明,对于大多数测试图像,该算法都能获得很好的分割结果,并且具有较高的运行效率。

This paper proposes a novel unsupervised algorithm for the segmentation of salient regions in color images.Firstly,the initial segmented regions are obtained using mean shift algorithm in the original image.Secondly,it proposes a new definition of region saliency and provides a new region merge strategy,which is used to form the final segment result by merging the initial regions.Experiment results show that the proposed method achieves excellent segmentation performance for most of test images.In addition,the computation is very efficient.