浏览全部资源
扫码关注微信
1.宁夏大学 葡萄酒与园艺学院,宁夏 银川 750021
2.宁夏现代设施园艺工程技术研究中心, 宁夏 银川 750021
吴龙国,博士,讲师,研究方向:设施园艺产品无损检测,E-mail:wlg@nxu.edu.cn
收稿日期:2024-07-11,
修回日期:2024-08-29,
录用日期:2024-09-10,
纸质出版日期:2025-03-15
移动端阅览
吴龙国,马玲,张瑶,田雨,朱彦哲,张祎洋.基于高光谱成像技术的包衣甘蓝种子色度检测[J].分析测试学报,2025,44(03):454-463.
WU Long-guo,MA Ling,ZHANG Yao,TIAN Yu,ZHU Yan-zhe,ZHANG Yi-yang.Detection of Coated Cabbage Seeds Color Based on Hyperspectral Imaging Technology[J].Journal of Instrumental Analysis,2025,44(03):454-463.
吴龙国,马玲,张瑶,田雨,朱彦哲,张祎洋.基于高光谱成像技术的包衣甘蓝种子色度检测[J].分析测试学报,2025,44(03):454-463. DOI: 10.12452/j.fxcsxb.240711212.
WU Long-guo,MA Ling,ZHANG Yao,TIAN Yu,ZHU Yan-zhe,ZHANG Yi-yang.Detection of Coated Cabbage Seeds Color Based on Hyperspectral Imaging Technology[J].Journal of Instrumental Analysis,2025,44(03):454-463. DOI: 10.12452/j.fxcsxb.240711212.
采用高光谱成像技术对包衣过程中4个不同品种的包衣甘蓝种子,3个不同浓度包衣剂处理的包衣甘蓝种子的包衣颜色均匀性以及包衣颜色深浅进行分析。提取出240个种子样本的平均光谱反射率,通过4种预处理方法对原始光谱进行预处理和优化,然后用竞争自适应重加权算法(CARS)、连续投影算法(SPA)、无信息变量消除变换法(UVE)、遗传偏最小二乘法(GAPLS)4种方法提取特征波长。基于优选的特征波长建立了偏最小二乘回归(PLSR)、多元线性回归(MLR)以及主成分回归(PCR)模型。结果表明:羽衣甘蓝种子的包衣效果最明显,佳香口感型甘蓝次之,中甘15和紫甘蓝的包衣效果接近;优选Baseline法对色度值
L
*进行预处理,Normalize法对色度值
a
进行预处理,SNV法对色度值
b
进行预处理;GAPLS法提取的特征波长用于建立
L
*、
b
的定量预测模型,UVE法提取的特征波长用于建立色度
a
值的定量预测模型。PLSR建立的
L
*模型效果最优(
R
C
=0.814,
R
p=0.640;RMSEC=1.150,RMSEP=1.852);MLR建立的色度
a
值模型效果更优(
R
c=0.981,
R
p=0.964;RMSEC=2.563,RMSEP=3.243);PCR建立的色度
b
值模型效果最优(
R
C
=0.9
17,
R
p=0.913;RMSEC=2.552,RMSEP=2.589)。研究结果可为种子色度的在线监测提供技术支撑。
Hyperspectral imaging technology was used to analyze the coating color uniformity and the depth of coating color of coated cabbage seeds of 4 different varieties and coated cabbage seeds treated with coating agents at 3 different concentrations during the coating process. The average spectral reflectance of 240 seed samples was extracted. The original spectra were preprocessed and optimized through 4 preprocessing methods. Then,4 methods including the competitive adaptive reweighted sampling algorithm(CARS),successive projections algorithm(SPA),uninformative variable elimination transformation method(UVE),and genetic algorithm partial least squares algorithm(GAPLS) were used to extract the characteristic wavelengths. Partial least squares regression(PLSR),multiple linear regression(MLR) and principal component regression(PCR) were established based on the optimized characteristic wavelengths. The results showed that the coating effect on kale seeds was the most obvious,followed by that on Jiaxiang taste-type cabbage,and the coating effects on Zhonggan 15 and purple cabbage were close. The Baseline method was preferably used to preprocess the chromaticity value
L
*,the Normalize method was used to preprocess the chromaticity value
a
,and the SNV method was used to preprocess the chromaticity value
b
. The characteristic wavelengths extracted by the GAPLS method were used to establish the quantitative prediction models for
L
* and
b
,the characteristic wavelengths extracted by the UVE method were used to establish the quantitative prediction model for the chromaticity value
a
. The
L
* model established by PLSR had the best effect(
R
c=0.814,
R
p=0.640;RMSEC=1.150,RMSEP=1.852),the model for the chromaticity value
a
established by MLR had a better effect(
R
c=0.981,
R
p=0.964;RMSEC=2.563,RMSEP=3.243),and the model for the chromaticity value
b
established by PCR had the best effect(
R
c=0.917,
R
p=0.913;RMSEC=2.552,RMSEP=2.589). The research can provide technical support for the online monitoring of seed chromaticity.
Yang H M , Yan S C . Hebei Agric. Sci. (杨慧民,闫树成. 河北农业科学), 2010 , 14 ( 12 ): 29 - 31 .
Moes J J , Ruijken M M , Gout E , Frijlink H W , Ugwoke M I . Int. J. Pharm. , 2008 , 357 ( 1 ): 108 - 118 .
Buchanan B R , Baxter M A , Chen T S , Qin X Z , Robinson P A . Pharm. Res. , 1996 , 13 ( 4 ): 616 - 621 .
Fukushima E . Annu. Rev. Fluid Mech. , 1999 , 31 ( 1 ): 95 - 123 .
Ristow G H . Europhys. Lett. , 1996 , 34 ( 4 ): 263 - 268 .
Jones J R , Bridgwater J . Int. J. Miner. Process , 1998 , 53 ( 1 ): 29 - 38 .
Chester A W , Kowalski J A , Coles M E , Muegge E L , Muzzio F J , Brone D . Powder Technol. , 1999 , 102 ( 1 ): 85 - 94 .
Madamba M C , Mullett W M , Debnath S , Kwong E . AAPS Pharm . Sci. Tech. , 2007 , 8 ( 4 ): 184 - 190 .
Ho L , Müller R , Römer M , Gordon K C , Heinämäki J , Kleinebudde P , Pepper M , Rades T , Shen Y C , Strachan C J . J . Contr. Release , 2007 , 119 ( 3 ): 253 - 261 .
Brock D , Zeitler J A , Funke A , Knop K , Kleinebudde P . Eur. J. Pharm. Biopharm. , 2013 , 85 ( 3 ): 1122 - 1129 .
Ye Q . Research on Color Measurement Methods Based on Hyperspectral Imaging . Shanghai : University of Chinese Academy of Sciences (叶琦.基于高光谱的颜色测量方法研究. 上海:中国科学院大学), 2018 .
Yu Z C , Zhao C Y , Gao L . Agric. Mech. Res. (喻志成,赵春宇,高璐. 农机化研究), 2017 , 39 ( 12 ): 26 - 31 .
Zhu P Y , Fang W X , Huang M , Zhao X , Chen Y P . Comput . Meas. Control (朱潘雨,方雯昕,黄敏,赵鑫,陈艳萍.计算机测量与控制), 2023 , 31 ( 4 ): 76 - 82 .
Yang H , Luo B , Zhang H , Zhou Y N , Wang C . J. Jiangsu Univ. : Nat . Sci. Ed .(杨欢, 罗斌,张晗,周亚男,王成.江苏大学学报:自然科学版), 2023 , 44 ( 2 ): 159 - 165 .
Lu X , Liao G P , Liu F . Chin . Agric. Sci. Technol. Herald (卢信,廖桂平,刘凡.中国农业科技导报), 2023 , 25 ( 1 ): 92 - 99 .
Wang D , Wang K , Wu J Z , Han P . Spectrosc . Spectral Anal. (王冬,王坤,吴静珠,韩平. 光谱学与光谱分析), 2021 , 41 ( 1 ): 52 - 59 .
Chen L , Wang H . J. Model Anal. , 2023 , 30 ( 2 ): 80 - 95 .
Zhang Y , Li X . Stat. Rev. , 2022 , 45 ( 3 ): 150 - 165 .
Zhang S , Wu Q . Spectrosc. Spectral Anal. , 2023 , 43 ( 2 ): 50 - 65 .
Meng L . Research on the Rapid Detection of Nitrogen and Chlorophyll Contents in Tomato Leaves Based on Hyperspectral Imaging Technology . Yinchuan : Ningxia University (孟露. 基于高光谱成像技术的番茄叶片氮素与叶绿素含量快速检测研究. 银川:宁夏大学), 2021 .
Ma L . Study on Rapid Detection of Physiological Indexes of Muskmelon at Different Stages under Light Environment Regulation . Yinchuan : Ningxia University (马玲. 光环境调控下不同时期甜瓜生理指标的快速检测研究. 银川:宁夏大学), 2023 .
Liu R , Tang G . J. Colorimetry , 2022 , 55 ( 4 ): 120 - 135 .
Wang P , Li K . Adv . Color Res. , 2021 , 28 ( 1 ): 30 - 45 .
0
浏览量
18
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构