摘要
文章介绍了一种基于RBF神经网络七段码识别方法,它是在VC++编程环境下实现的。本系统主要特征是分段线性灰度变换、倾斜度调整、映射归一、特征提取。实验表明这种方法运行速度快、识别率高。这种方法具有一定的实用价值。
The paper introduces a high performance Radial Basis Function （RBF） neural network approach for seven segment display recognition, which is realized in Visual C＋＋ compiling environment. The main features of the system are piecewise linear gray level transformation, slope angle adjustment, mapping and normalization, feature distilling. The experiment shows that the approach is a fast and high accuracy method of digital recognition.The approach is of practical value.
出处
《微电子学与计算机》
CSCD
北大核心
2005年第12期106-109,共4页
Microelectronics & Computer
基金
广东省自然科学基金项目(4009469)
湖南省教育厅资助项目(04C582)
关键词
灰度变换
倾斜度调整
映射归一
特征提取
RBF神经网络
Gray level transformation, Slope angle adjustment, Mapping and normalization, Feature distilling, RBF neural network
