摘要
细胞图像分割是医学图像处理的热点研究内容,论文针对传统的阈值分割方法,将最大方差阈值选择函数进行推广,获得双阈值选择函数,实现了免疫细胞图像的自动双阈值分割,并采用数学形态学方法中的开运算进行后处理,有效消除了阈值分割所带来的毛刺及噪声。实验结果表明,该方法简单、快速,分割结果令人满意。
Cell image segmentation is one of important research topics in medical image processing. Aiming at traditional image thresholding method, this study generalizes the single threshold selection function based on Maximum Variance theory to double threshold selection, and achieves the automatic double thresholding of immune cell image. The mathematical morphology method is adopted to eliminate the burr and noises brought from segmentation. Our experiment results proved that the method described in this paper is simple and fast, and the segmentation result is satisfactory.
出处
《中国体视学与图像分析》
2007年第1期59-61,共3页
Chinese Journal of Stereology and Image Analysis
关键词
图像分割
数学形态学
阈值选择函数
image segmentation
mathematical morphology
threshold selection function
