光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
SPECTROSCOPY AND SPECTRAL ANALYSIS
2010年
2期
426-429
,共4页
冯洁%李宏宁%杨卫平%侯德东%廖宁放
馮潔%李宏寧%楊衛平%侯德東%廖寧放
풍길%리굉저%양위평%후덕동%료저방
多光谱成像技术%光谱分类%分类器%园艺作物病害
多光譜成像技術%光譜分類%分類器%園藝作物病害
다광보성상기술%광보분류%분류기%완예작물병해
Multispectral imaging technique%Spectra classification%Classifier%Horticultural plant diseases
选取设施园艺作物黄瓜的主要病害为研究对象,利用窄带滤光片型多光谱成像系统,获取患病黄瓜叶而的14个可见光通道和近红外通道、全色通道的多光谱图像.采用多光谱图像分类技术中的距离分类器、相关系数分类器和BP人工神经网络分类器,将不同病害类型对应的16个波段的反射率看作线性波谱,对210个多光谱数据样本进行识别分类,目的足探讨一个能有效识别黄瓜植株常见病害的多光谱组合分类器.实验结果表明,将人工神经网络和距离分类器有效组合,不仅分类性能明显优于单个分类器的性能,而且能够充分发挥各个分类器的特性,对园艺作物病害进行快速、准确、实时的无损检测.
選取設施園藝作物黃瓜的主要病害為研究對象,利用窄帶濾光片型多光譜成像繫統,穫取患病黃瓜葉而的14箇可見光通道和近紅外通道、全色通道的多光譜圖像.採用多光譜圖像分類技術中的距離分類器、相關繫數分類器和BP人工神經網絡分類器,將不同病害類型對應的16箇波段的反射率看作線性波譜,對210箇多光譜數據樣本進行識彆分類,目的足探討一箇能有效識彆黃瓜植株常見病害的多光譜組閤分類器.實驗結果錶明,將人工神經網絡和距離分類器有效組閤,不僅分類性能明顯優于單箇分類器的性能,而且能夠充分髮揮各箇分類器的特性,對園藝作物病害進行快速、準確、實時的無損檢測.
선취설시완예작물황과적주요병해위연구대상,이용착대려광편형다광보성상계통,획취환병황과협이적14개가견광통도화근홍외통도、전색통도적다광보도상.채용다광보도상분류기술중적거리분류기、상관계수분류기화BP인공신경망락분류기,장불동병해류형대응적16개파단적반사솔간작선성파보,대210개다광보수거양본진행식별분류,목적족탐토일개능유효식별황과식주상견병해적다광보조합분류기.실험결과표명,장인공신경망락화거리분류기유효조합,불부분류성능명현우우단개분류기적성능,이차능구충분발휘각개분류기적특성,대완예작물병해진행쾌속、준학、실시적무손검측.
The research on multispectral data disposal is getting more and more attention with the development of multispectral technique,capturing data ability and application of rnultispectral technique in agriculture practice.In the present paper,a cultivated plant cucumber' familiar disease(Trichothecium roseum,Sphaerotheca f uliginea,Cladosporium cucumerinum,Corynespora cassiicola,Pseudoperonospora cubensis)is the research objects.The cucumber leaves multispectral images of 14 visible light channels,near infrared channel and panchromatic channel were captured using narrow-band multispectral imaging system under standard observation and illumination environment,and 210 multispectral data samples which are the 16 bands spectral reflectance of different cucumber disease were obtained.The 210 samples were classified by distance,relativity and BP neural network to discuss effective combination of classified methods for making a diagnosis.The result shows that the classified effective combination of distance and BP neural network classified methods has superior performance than each method,and the advantage of each method is fully used.And the flow of recognizing horticultural plant diseases using combined classified methods is presented.