摘要
试验首先提取甘肃大麦病斑的颜色和纹理特征,以特征向量为输入向量来构造大麦病害神经网络分类器模型.然后利用神经网络对采集到的训练集病害图像进行分类模型训练,最后以随机选取的两组测试图像进行了分类试验.结果表明:大麦病害神经网络分类器模型对甘肃大麦病害的整体识别正确率达到86.7%以上.因而,基于神经网络的大麦病害图像识别研究为大麦田间病害归类诊治提供了新型技术,为西北特别是甘肃大麦病害的早期诊断与科学防治奠定了技术基础.
Barley diseases have a great negative impact on the yield and quality.Firstly,disease spot color and texture features were extracted from barley field images in Gansu Province,and the feature vectors were used as input vector to establish barley diseases classifier model.Then,the neural network was applied to train classified model with collected images as training set.Finally,two groups of random selected images as test sets were used to perform classified verification experiments.The experimental results showed that the overall accuracy of barley diseases recognition model was above 86.7%.Therefore,Barley disease image recognition based on neural network provides a new technology for the classified treatment of barley diseases,and also can lay a solid technical foundation for the early diagnosis and the scientific prevention of barley diseases.
出处
《甘肃农业大学学报》
CAS
CSCD
北大核心
2015年第2期173-176,180,共5页
Journal of Gansu Agricultural University
基金
国家自然科学基金项目(61164001)
甘肃省教育厅高等学校科研计划项目(1102-07)
甘肃省干旱生境作物学重点实验室开放基金(1102-11)
关键词
大麦
神经网络
病害
图像处理
识别
barley
neural network
disease
image processing
recognition
作者简介
王临铭（1987-），男，硕士研究生，研究方向为工程检测与智能控制技术．E-mail：904830352@qq．com
通信作者：高晓阳，男，教授，博士，硕士生导师，主要从事农业工程检测与智能控制技术及系统研究．E-mail：gaoxiao1081@sina．com
