Computer Engineering and Applications ›› 2013, Vol. 49 ›› Issue (20): 136-140.

Previous Articles     Next Articles

New watershed algorithm based on improved gradient and self-adaptive marker-extraction

DENG Chao, GUAN Geli, WANG Zhiheng   

  1. School of Computer Science and Technique, Henan Polytechnic University, Jiaozuo, Henan 454000, China
  • Online:2013-10-15 Published:2013-10-30

改进梯度和自适应标记提取的分水岭新算法

邓  超,关格利,王志衡   

  1. 河南理工大学 计算机科学与技术学院,河南 焦作 454000

Abstract: A new watershed algorithm based on improved gradient and self-adaptive marker-extraction is proposed to overcome over-segmentation. Two groups of structural elements are used to calculate gradient. The markers of reconstructed gradient are extracted by Otsu algorithm. h-minima transformation is used to modify markers, and the union set of a series of markers is regarded as the final marker image. The watershed transformation of modified gradient is performed. The experimental results show that the proposed algorithm can more efficiently reduce the over-segmentation, obtain meaningful and more reasonable regions than the traditional watershed algorithm.

Key words: watershed algorithm, color image gradients, marker extraction, Otsu algorithm, h-minima transformation

摘要: 为了克服分水岭算法的过分割问题,提出了一种基于改进形态学梯度和自适应标记提取的分水岭新方法。用两组结构元素进行梯度计算;对重构后的梯度图像用Otsu算法提取标记;用h-minima变换修改标记图像,将各尺度下标记点的并集作为最终的标记图像;对修改的梯度图像进行分水岭变换。实验结果表明:与传统分水岭算法相比,该算法对于改善过分割现象有明显的效果,能够获得具有实际意义且更合理的分割区域。

关键词: 分水岭算法, 彩色图像的梯度, 标记提取, Otsu算法, h-minima变换