基于局部灰度占比的粘连细胞分割方法  

Separating algorithm for adhering cell images based on partial gray pixels accounted distribution

作　　者：蒋先刚[1] 崔媛媛[1] 

机构地区：[1]华东交通大学交通信息工程与控制研究所,江西南昌330013

出　　处：《计算机工程与设计》2009年第19期4451-4454,共4页Computer Engineering and Design

基　　金：江西省教育厅基金项目(赣教高[2008]92)

摘　　要：针对医学细胞图像中的粘连现象,对采集到的细胞图像进行均值聚类、二值化、空洞填充、距离变换等预处理操作后,根据距离变换图像的像素灰度值来选取实现粘连细胞分割的最佳阈值,在分析重叠或粘连细胞图像的局部像素特征的基础上,对距离变换处理后图片的局部灰度占比分布进行了全面的分析和处理。实验结果表明,该方法简单易行,具有较好的分割效果。Against the overlapping or adhering biological cells, firstly the collected cell images are carried out a pre-processing, such as K-means clustering, binary, filling the empty and distance transformation, then the best threshold can be selected according to the transformed images pixel gray values to achieve the separation for the overlapping or adhering cells, and the comprehensive analyses and processing are conducted in the light of the accounted distribution of the transformed cell images＇ local gray pixels. The experimental results show that this method has relatively good segmentation results.

关 键 词：细胞图像 K-均值聚类 距离变换 像素灰度值 占比分布 

分 类 号：TP315[自动化与计算机技术—计算机软件与理论]