摘要
利用高光谱(400~1700 nm)成像技术扫描得到3个部位(上B、中C、下X)烤后烟叶的高光谱图像,并提取其高光谱数据。采用相关性分析、主成分分析及方差分析研究了3个部位烟叶的高光谱特征,并构建5种识别烟叶部位的判别模型(SVM、KNN、RF、LightGBM和XGBoost)。结果表明,3个部位烟叶的光谱反射率为C>X>B(400~750 nm),B>C>X(750~1400 nm),C>B≈X(1400~1700 nm)。3个部位烟叶的高光谱数据存在较强相关性,总体上可见光以及近红外波段在各自区域内相关性较强,而两者之间相关性较弱。共提取得到7个特征值大于1的主成分,方差累计贡献率接近1.00。3个部位烟叶的光谱反射率在450~550 nm和750~1400 nm区域相互之间存在明显差异,中部叶在550~850 nm和1400~1700nm分别与上、下部叶具有明显差异,上部叶在400~450 nm分别与中、下部叶差异明显,下部叶在680 nm附近分别与上、中部叶差异显著。SVM判别不同部位烟叶的表现最好,准确率、精确率、召回率和F1分数均达95%以上,LightGBM表现居中,各项指标在90%~95%,RF、KNN和XGBoost相对较差,各项指标在90%以下。
Hyperspectral images of three parts(upper B,middle C and lower X)of flue-cured tobacco leaves were obtained by scan⁃ning with hyperspectral imaging technique(400~1700 nm),and their hyperspectral data were extracted.The hyperspectral character⁃istics of the three parts of tobacco leaves were studied by correlation analysis,principal component analysis and variance analysis,and five discriminant models(SVM,KNN,RF,LightGBM and XGBoost)for identifying tobacco leaf parts were constructed.The results showed that the spectral reflectance of the three parts of tobacco leaves was C>X>B(400~750 nm),B>C>X(750~1400 nm),and C>B≈X(1400~1700 nm).The hyperspectral data of the three parts of tobacco leaves had a strong correlation.In general,the correlation between the visible light and near-infrared bands was strong in their respective regions,while the correlation between the two was weak.A total of 7 principal components with eigenvalues greater than 1 were extracted,and the cumulative contribution rate of vari⁃ance was close to 1.00.The spectral reflectance of the three parts of tobacco leaves was significantly different in 450~550 nm and 750~1400 nm regions.The middle leaves had significant differences from the upper and lower leaves at 550~850 nm and 1400~1700 nm,respectively.The upper leaves had significant differences from the middle and lower leaves at 400~450 nm,respectively.The lower leaves had significant differences from the upper and middle leaves at around 680 nm.SVM performed best in distinguishing tobacco leaves in different parts,with accuracy,precision,recall and F1 scores all reaching above 95%,LightGBM performed in the middle,with various indicators between 90%and 95%,RF,KNN and XGBoost performed relatively poorly,with various indicators below 90%.
作者
闫鼎
张义志
程森
蔡宪杰
董祥洲
杨悦章
岳耀稳
王大彬
林润英
YAN Ding;ZHANG Yi-zhi;CHENG Sen;CAI Xian-jie;DONG Xiang-zhou;YANG Yue-zhang;YUE Yao-wen;WANG Da-bin;LIN Run-ying(Shanghai Tobacco Group Co.,Ltd.,Shanghai 200082,China;Tobacco Research Institute of Chinese Academy of Agricultural Sciences,Qingdao 266101,Shandong,China;Anhui Wannan Tobacco Co.,Ltd.,Xuancheng 242000,Anhui,China;Huahuan International Tobacco Co.,Ltd.,Chuzhou 233121,Anhui,China;Longyan Branch of Fujian Tobacco Company,Longyan 364000,Fujian,China)
出处
《湖北农业科学》
2024年第8期140-146,共7页
Hubei Agricultural Sciences
基金
中国农业科学院科技创新工程项目(ASTIP-TRIC06)
上海烟草集团有限责任公司科技项目(K2021-1-033P)。
关键词
高光谱特征
烤后烟叶
模型构建
部位识别
hyperspectral characteristics
flue-cured tobacco
model construction
position recognition
