摘要
细胞图像中经常出现重叠(或者粘连)现象,利用红细胞是近似圆形的这一先验知识,用粒度测量来获取红细胞半径R,对重叠区域轮廓上的每个非凹陷点,估计其所对应的圆心点,这些圆心点聚集成各个细胞的中心区域,对每一个中心区域,采用半径为R的圆形结构元进行一次膨胀操作,然后和原二值图像进行交集运算,将其结果作为对各个细胞形状的估计。实验结果表明,该方法能得到比较满意的分离效果,亦适用于其他近似圆形的细胞或者颗粒的重叠区域图像的分离。
Overlapping appears frequently is all images. The algorithm based on the knowledge that red blood cells are disk-shaped. Granulometry is employed to estimate cell’s radius R. Every contour point corresponds to center point of a circle with radius R estimated with the information of radius and chain code, which will assemble central areas of every single cell. Then, morphological dilation with a disk-shaped structuring element of radius R is applied to every central area. The intersection of the result of dilation operation and the original binary image is used to estimate the shape of every single cell. Experiments show the algorithm can obtain acceptable separating result. It can also be used for images of other kind of disk-shaped cells and granules.
出处
《中国图象图形学报》
CSCD
北大核心
2005年第6期736-740,共5页
Journal of Image and Graphics
基金
浙江省科技厅资助项目(2003C11022)
关键词
细胞图像
图像分割
重叠
分离
cell image, image segmentation, overlapping, separating
