基于形态学梯度的细胞图像自动分割  

Automatic Segmentation for Cell's Image Based on Morphological Gradient

作　　者：姜红军[1] 董杰[1] 平子良[2] 

机构地区：[1]内蒙古师范大学科学技术史研究院,内蒙古呼和浩特010020 [2]内蒙古师范大学物理与电子信息学院,内蒙古呼和浩特010020

出　　处：《安徽农业科学》2012年第1期600-602,共3页Journal of Anhui Agricultural Sciences

基　　金：国家自然科学基金项目(61065004)

摘　　要：提出一种自动分割细胞图像的方法,利用数学形态学梯度运算对图像边缘进行锐化。再利用判别分析法自动确定梯度图像阈值,经后处理,可得单像素宽度细胞图像边缘。该边缘可描述医学图像中细胞的有效区域,实现细胞图像自动分割。为验证该方法的有效性,对30幅实际细胞图像进行分割试验。结果表明,该方法对细胞图像分割有较好的适应能力。A method for automatic segmentation of cell＇s image was put forward.The cell＇s images were sharpened by morphological gradient algorithm;then,the discriminant analysis method was adopted to automatically determine the gradient image threshold;after the treatment,the single pixel width of cell＇s image edge was obtained.The edge could describe the effective zone of cell＇s image,realize automatic segmentation.In order to verify the validity of the method,the segmentation method was applied for cells segmentation of 30 medical images.The results showed that the method for cell＇s image segmentation has the better adaptability.

关 键 词：形态学梯度 细胞图像 图像分割 

分 类 号：S126[农业科学—农业基础科学]