基于属性论的肺癌细胞识别  

Lung Cancer Cells' Recognition Based on Attribute Theory

作　　者：冯嘉礼[1] 毕经迎[1] 

机构地区：[1]上海海事大学信息工程学院,上海200135

出　　处：《广西师范大学学报（自然科学版）》2011年第3期183-186,共4页Journal of Guangxi Normal University:Natural Science Edition

基　　金：国家自然科学基金资助项目(60075016)

摘　　要：目前的图像诊断系统,大多数采用形态学和色度学特征并结合专家系统,对癌细胞进行分析和诊断。为了更好地对肺癌细胞进行识别,本文利用图像处理的相关知识对肺癌细胞图像进行形态学和色彩学的特征提取,在此基础上利用属性论中的定性映射与转化程度函数对肺癌细胞进行分类识别。实验结果证明本文提出的方法可以取得较好的结果,说明属性论方法在模式识别领域还是具有应用价值的。The current image diagnosis system mainly uses morphological and colorimetric characteristics,combining the expert system,to analyze and diagnose cells of lung cancer.In order to gain high recognition rate of cells of lung cancer,features of cells of lung cancer＇s morphological and chromatics are extracted by using related knowledge of mage processing.Then,the system identifies the cells based on qualitative mapping and conversion degree function.Experimental result shows that the proposed method can achieve good results and also proved that the attribute theory still has application value in pattern recognition field.

关 键 词：形态学 色彩学 定性映射 转化程度函数 

分 类 号：TP391.7[自动化与计算机技术—计算机应用技术]