摘要
该文讨论并建立了一真彩色白细胞显微图像微机自动识别系统。针对传统组合优化方法用于特征选择的种种缺陷,提出了基于遗传算法的特征选择策略。根据细胞特征,笔者对传统的遗传算法做了相应的改进。最后运用选择特征子集来训练BP神经网络作为分类器。结果证明该方法对于分类系统的性能优化有明显效果。
This paper discusses to develop automatic classification system for true color Leukocyte image.In view of the deficiencies of traditional combination optimization method,a new method based on genetic algorithm is proposed.According to the specific situation of cells classification,this paper makes some modifications.Finally neural network with error back -propagation is training using the selected feature sets.The result shows that this method optimizes the classification performance.
出处
《计算机工程与应用》
CSCD
北大核心
2003年第7期213-215,共3页
Computer Engineering and Applications
