Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (4): 230-232.

• 工程与应用 • Previous Articles     Next Articles

Cell image segmentation method based on watershed transformation

BAO Zhen-jian,DI Shu-ling   

  1. Department of Computer Science and Technology,Shijiazhuang Railway Institute,Shijiazhuang 050043,China
  • Received:2007-06-05 Revised:2007-08-12 Online:2008-02-01 Published:2008-02-01
  • Contact: BAO Zhen-jian

一种基于分水岭变换的细胞图像分割方法

包振健,邸书灵   

  1. 石家庄铁道学院 计算机系,石家庄 050043
  • 通讯作者: 包振健

Abstract: A hybrid strategy based on watershed transformation is proposed and applied to bone marrow cell image segmentation.Through the integration of marker-based morphological reconstruction and regional-similarity-based region merging algorithm,the drawback that traditional marker-based watershed transform is vulnerable to the markers,and the problem that region merging algorithm is slow,and inaccurate is overcome.Experimental results show that the method is accurate and efficient for bone marrow cell image segmentation.

Key words: watersheds, marker, grayscale morphological reconstruction, region merging

摘要: 提出了一种混合的分水岭变换策略并应用于骨髓细胞图像分割中。该策略综合运用基于标记的形态学重建和基于区域相似度的区域合并算法,克服了传统的基于标记的分水岭变换对于标记提取敏感的缺点,及区域合并算法速度慢,结果不精确的问题。实验结果表明,该方法能够准确高效地分割骨髓细胞图像。

关键词: 分水岭, 标记, 形态学灰度重建, 区域合并