基于数学形态学的医学图像自动阈值分割  

Automatically Select Thresholding Segmantation for Medical Image Based on Methematical Morphology

作　　者：姜红军[1] 王可佳[1] 海鹰[1] 张德龙[1] 平子良[1] 

机构地区：[1]内蒙古师范大学物理与电子信息学院,内蒙古呼和浩特010022

出　　处：《内蒙古师范大学学报（自然科学汉文版）》2008年第3期397-399,402,共4页Journal of Inner Mongolia Normal University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(60562001);内蒙古师范大学青年基金项目(QN06050);内蒙古师范大学科研基金项目(YJS005010)

摘　　要：提出了一种自动分割癌细胞图像的方法.该方法利用数学形态学开运算型边缘检测算子对图像边缘锐化;利用邻域平均与中值滤波方法平滑图像;利用改进的判别分析法自动选取灰度阈值进行图像自动分割;利用自动分割区域与手动分割区域的误差和平均最短距离对自动分割效果进行评价.用该方法对20幅癌细胞图像进行自动分割实验,证明了其对图像分割的有效性.A method for automatic segmentation of cancerous cell＇s image is proposed. In the method, the cell＇s images are smoothened by neighbor area＇s average and median filtering. The edges of image are sharpened by open detoching algorithm of mathematical morphology. The improved gray scale threshed dis- criminate method is used to select the threshed value and to segment the cell＇s image automatically. Through the analysis of error and mean minimum distance between the regions segmented by this method and the regions segmented by imaginary doctor manually, the effectiveness of the method is evaluated. The segmentation method is applied for cell＇s segmentation of 20 cancerous medical images.

关 键 词：癌细胞图像 自动分割 数学形态学 结构元素 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]