基于区域形态学运算的细胞图像检测边界  

Application of area operators for edge detection

作　　者：秦微微[1] 汪天富[1] 林江莉[1] 李德玉[1] 

机构地区：[1]四川大学生物医学工程系,四川成都610065

出　　处：《西南民族大学学报（自然科学版）》2006年第4期745-747,共3页Journal of Southwest Minzu University(Natural Science Edition)

基　　金：国家自然科学基金(60272060);四川省青年科技基金(05ZQ026-019)

摘　　要：细胞和组织形态特征的分析一直是研究生物细胞学和病理学的主要手段.边界提取是细胞图像识别的第一步,也是关键的一步.针对血液细胞的边界附近的灰度分布梯度较大的特性,对细胞边界的提取可以采用一些比较常用边界检测算子的,如Sobel算子、Laplacian算子等,但都存在一定的缺点.本文采用区域形态学进行细胞图像的边界提取,实验结果表明该方法在保持边界连续性和消除伪边界方面都优于传统的边界检测算法.For a long time,the analysis of the cell and tissue’s shape features has been the main means to study biological cytology and pathology all the time.Edge detection is not only the first step,but also the key step for cell imaging recognition.Distributing the characteristics with greater gradient to the grey level near the edge of the blood cell,we can adopt some more often used edge detecting operators to detect the cell's edge,such as Sobel operator,Laplacian operator.By comparison,we see that using area morphology to detect medical image would make better effect.

关 键 词：边界检测 形态学 细胞图像 

分 类 号：R318[医药卫生—生物医学工程] R329.2[医药卫生—基础医学]