一种组织细胞图象的分割

自动、时实、计算机视学细胞追踪系统需要一种非常有效的细胞图象分割方式．通常一些文献介绍的分割算法在运用于未染色活细胞图象分析时，由于灰度变化和不均匀的光照等，显得非常虚弱．我们研究了分割的两步策略即：（１）选出含有细胞和一部分细胞周围背景的近似区域；（２）从这个区域内的背景中分割出细胞．这种方式能有效降低周围背景灰度和细胞区域上纹理的影响．实验结果表明这种方法作为细胞图象的分割时既快又省力．

Segmentation of Tissue Cell Image

It is an efficient means for segmenting cell images that an automated,real time computer vision based cell tracking system needs.The usual segmentation algorithms proposed in some literatures exhibit weak performance on tissue unstained cell images,which can be characterized as being of low contract,intensity variant,and unevenly illuminated.We propose a two stage segmentation strategy which involves:1)extracting an approximate region containing the cell and part of the background near the cell,and 2)segmenting the cell from the background within this region.The approach effectivtly reduces the influence of peripheral background intensities and texture on the extraction of a cell region.The experimental results show that this approach for segmeting cell images is both fast and robust.