基于高光谱图像和遗传优化神经网络的茶叶病斑识别

为实现茶叶病害的快速高效识别,提出了基于高光谱成像技术和图像处理技术融合的茶叶病斑识别方法。利用高光谱成像技术采集了炭疽病、赤叶斑病、茶白星病、健康叶片等4类样本的高光谱图像。提取感兴趣区域敏感波段的相对光谱反射率作为光谱特征。通过2次主成分分析,确定第二次主成分分析后的第二主成分图像为特征图像,基于颜色矩和灰度共生矩阵提取特征图像的颜色特征和纹理特征。利用BP神经网络对颜色、纹理和光谱特征向量融合数据进行检验,识别率为89.59%;为提高识别率,提出遗传算法优化BP神经网络的方法,使病斑识别率提高到94.17%,建模时间也缩短至1.7 s。试验结果表明：高光谱成像技术和遗传优化神经网络可以快...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 33; no. 22; pp. 200 - 207
Main Author 张帅堂 王紫烟 邹修国 钱燕 余磊
Format Journal Article
LanguageChinese
Published 南京农业大学工学院/江苏省智能化农业装备重点实验室,南京,210031 2017
Subjects
主成分分析
优化
光谱特征
神经网络
算法
高光谱成像技术
算法
高光谱成像技术
主成分分析
algorithms
optimization
优化
neural networks
spectral characteristics
hyperspectral imaging technology
神经网络
principal component analysis
光谱特征
Online AccessGet full text
ISSN1002-6819
DOI10.11975/j.issn.1002-6819.2017.22.026

Cover

More Information
Summary:为实现茶叶病害的快速高效识别,提出了基于高光谱成像技术和图像处理技术融合的茶叶病斑识别方法。利用高光谱成像技术采集了炭疽病、赤叶斑病、茶白星病、健康叶片等4类样本的高光谱图像。提取感兴趣区域敏感波段的相对光谱反射率作为光谱特征。通过2次主成分分析,确定第二次主成分分析后的第二主成分图像为特征图像,基于颜色矩和灰度共生矩阵提取特征图像的颜色特征和纹理特征。利用BP神经网络对颜色、纹理和光谱特征向量融合数据进行检验,识别率为89.59%;为提高识别率,提出遗传算法优化BP神经网络的方法,使病斑识别率提高到94.17%,建模时间也缩短至1.7 s。试验结果表明：高光谱成像技术和遗传优化神经网络可以快速准确的实现对茶叶病斑的识别,可为植保无人机超低空遥感病害监测提供参考。
Bibliography:11-2047/S
Zhang Shuaitang, Wang Ziyan, Zou Xiuguo, Qian Yan, Yu Lei （College of Engineering/Jiangsu Key Laboratory of Intelligent Agricultural Equipment, Nanjing Agricultural University, NanJing 210031, China）
algorithms; optimization; neural networks; hyperspectral imaging technology; principal component analysis; spectral characteristics
In order to achieve fast and efficient identification of tea diseases, the method of identifying tea diseases based on hyperspectral imaging technology was put forward. Four kinds of samples, including anthracnose, brown leaf spot disease, white star disease and healthy leaf, were collected in Pingshan tea plantation of Nanjing. Hyperspectral images of these samples, ranging from 358 to 1 021 nm, were collected by hyperspectral imaging system. Among them, there were 80 samples of anthracnose, 72 samples of brown leaf spot disease, 80 samples of white star disease and 60 samples of healthy leaves. The region of interest （ROI） was an area of 200 pixels × 200 pixels near the tip
ISSN:1002-6819
DOI:10.11975/j.issn.1002-6819.2017.22.026