摘要
通过数字图像技术可以自动提取烟叶的颜色和形状特征,而不同特征值对分部位、颜色和等级的决定程度不同,文章结合广义回归神经网络定性分析各种不同特征对部位或颜色分级的影响,分别得到对分部位、颜色和等级有决定影响的特征量,通过建立不同神经网络得到最终等级。
The digital image technology is used to extract the leaf color features and shape features. A generalized regression neural network is employed to determine its grade, and by analyzing different features＇ influence on parts and color, we got some decisive features to parts and color respective, and get final grade by creating different neural networks.
出处
《计算机与数字工程》
2012年第7期122-124,共3页
Computer & Digital Engineering
关键词
图像处理
神经网络
特征分析
image processing
neural networks
feature analysis
