局部自适应的细胞图像分割方法  

Based-on Local Adaptive Cell Image's Segmentation

作　　者：陈宇[1] 庞全[1] 

机构地区：[1]杭州电子科技大学自动化学院,浙江杭州310018

出　　处：《杭州电子科技大学学报（自然科学版）》2005年第2期57-60,共4页Journal of Hangzhou Dianzi University：Natural Sciences

基　　金：浙江省自然科学基金资助项目(ZD0205;602127)

摘　　要：针对单一的全局阈值分割方法不能适用于复杂多目标图像的目标提取,该文提出了一种基于局部自适应多阈值的分割算法。该算法的基本思想是将首次分割得到的目标区域按照一定准则进行划分,分为已经正确提取的目标细胞和包含有多个细胞及部分背景的模糊区域,然后将各个模糊区域作为子图像分别进行再次分割,从中提取出目标细胞。实验结果表明,该算法能够稳定地实现目标分割提取,具有较好的鲁棒性。In view of the limitations of traditional simple threshold algorithm under the complicated images, an algorithm for adaptive local segmentation is proposed. The main technique of the algorithm consists in that the object areas resulting from first segmentation are divided into correct goal cell areas and fuzzy areas include a lot of cells and some background according to certain criterion, then regard each fuzzy area as new image go on for the second segmentation respectively, draw out the goal cell from it. The experimental result indicates, the algorithm can realize steadily that the goal is cut apart and drawn, stupid and excellent better.

关 键 词：局部自适应 多阈值 图像分割 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]