高光谱成像技术鉴别菠菜叶片农药残留种类

吉海彦; 任占奇; 饶震红

doi:10.3788/fgxb20183912.1778

您当前的位置：

首页 >

文章列表页 >

高光谱成像技术鉴别菠菜叶片农药残留种类

发光学应用及交叉前沿 | 更新时间：2020-08-12

- 高光谱成像技术鉴别菠菜叶片农药残留种类
- Identification of Pesticide Residue Types in Spinach Leaves Based on Hyperspectral Imaging
- 发光学报 2018年39卷第12期页码：1778-1784
- 作者机构：
  
  1. 中国农业大学现代精细农业系统集成研究教育部重点实验室北京,100083
  2. 中国农业大学农业部农业信息获取技术重点实验室北京,100083
  3. 中国农业大学理学院北京,100083
- 作者简介：
- 基金信息：
  
  &ldquo();十三五&rdquo();国家重点研发计划（2016YFD0200602）资助项目()
- DOI：10.3788/fgxb20183912.1778
  中图分类号： O433.4
- 收稿日期：2018-03-15，
  
  修回日期：2018-06-19，
  
  网络出版日期：2018-07-06，
  
  纸质出版日期：2018-12-05
- 稿件说明：
移动端阅览
吉海彦, 任占奇, 饶震红. 高光谱成像技术鉴别菠菜叶片农药残留种类[J]. 发光学报, 2018,39(12): 1778-1784

JI Hai-yan, REN Zhan-qi, RAO Zhen-hong. Identification of Pesticide Residue Types in Spinach Leaves Based on Hyperspectral Imaging[J]. Chinese Journal of Luminescence, 2018,39(12): 1778-1784
吉海彦, 任占奇, 饶震红. 高光谱成像技术鉴别菠菜叶片农药残留种类[J]. 发光学报, 2018,39(12): 1778-1784 DOI： 10.3788/fgxb20183912.1778.

JI Hai-yan, REN Zhan-qi, RAO Zhen-hong. Identification of Pesticide Residue Types in Spinach Leaves Based on Hyperspectral Imaging[J]. Chinese Journal of Luminescence, 2018,39(12): 1778-1784 DOI： 10.3788/fgxb20183912.1778.

摘要

利用高光谱成像技术无损鉴别菠菜叶片农药残留种类。采用高光谱成像仪采集900~1 700 nm波段内的光谱数据，采用多元散射校正对光谱数据进行预处理。利用主成分分析对不同种类菠菜样品的光谱数据进行分析，结果表明主成分分析能在可视化层面对不同种类的农药残留菠菜样品进行有效判别。另外，将卡方检验特征选择算法分别与支持向量机、朴素贝叶斯、决策树和线性判别分析算法结合，并采用10-fold交叉验证评价方法，筛选出最佳波段和最优判别模型（线性判别模型）。筛选出的8个特征波长为1 439.3，1 442.5，1 445.8，1 449，1 452.3，1 455.5，1 458.7，1 462 nm，模型的预测准确率达到0.993且10次交叉验证的标准差为0.009。结果表明，基于高光谱成像技术能准确地识别菠菜叶片上的农药残留种类。

Abstract

Non-destructive identification of pesticide residues in spinach was studied using hyperspectral imaging. The hyperspectral images between 900 nm and 1 700 nm were obtained with the help of hyperspectral imager. The original spectra were corrected by multivariate scatter correction (MSC). The principal component analysis (PCA) was used to analyze the spectral data of different spinach samples

the results showed that PCA could effectively discriminate different kinds of pesticide residues spinach samples on the visualization level. In addition

chi-squared test feature selection algorithm was separately combined with four learning algorithms (

e.g.

support vector machine

naive Bayes

decision tree and linear discriminant analysis) to get the best bands and optimal discriminant model(linear discriminant model) with the help of 10-fold cross-validation technique. The selected eight characteristic wavelengths are 1 439.3

1 442.5

1 445.8

1 449

1 452.3

1 455.5

1 458.7

1 462 nm and the prediction accuracy by optimal discriminant model is 0.993 and 10 times of cross validation standard deviation is 0.009. The results show that hyperspectral imaging technology can accurately identify the types of pesticide residues on spinach leaves.

关键词

Keywords

references

CHEN J Y, LIN Y J, KUO W C. Pesticide residue removal from vegetables by ozonation[J]. J. Food. Eng., 2013, 114(3):404-411.

RENWICK A G. Pesticide residue analysis and its relationship to hazard characterisation (ADI/ARfD) and intake estimations (NEDI/NESTI)[J]. Pest. Manag. Sci., 2002, 58(10):1073-1082.

孙俊, 张梅霞, 毛罕平, 等. 基于高光谱图像的桑叶农药残留种类鉴别研究[J]. 农业机械学报, 2015, 46(6):251-256. SUN J, ZHANG M X, MAO H P, et al.. Identification of pesticide residues on mulberry leaves based on hyperspectral imaging[J]. Trans. Chin. Soc. Agricult. Mach., 2015, 46(6):251-256. (in Chinese)

李晓婷, 王纪华, 朱大洲, 等. 果蔬农药残留快速检测方法研究进展[J]. 农业工程学报, 2011, 27(s2):363-370. LI X T, WANG J H, ZHU D Z, et al.. Research progress of fast detection methods of fruits and vegetables pesticide residues[J]. Trans. Chin. Soc. Agric. Eng., 2011, 27(s2):363-370. (in Chinese)

FENG Y Z, SUN D W. Application of hyperspectral imaging in food safety inspection and control:a review[J]. Crit. Rev. Food Sci. Nutr., 2012, 52(11):1039-1058.

WU D, SUN D W. Advanced applications of hyperspectral imaging technology for food quality and safety analysis and assessment:a review-Part Ⅱ:applications[J]. Innovat. Food Sci. Emerg. Technol., 2013, 19(1):15-28.

RUMPF T, MAHLEIN A K, STEINER U, et al.. Early detection and classification of plant diseases with support vector machines based on hyperspectral reflectance[J]. Comput. Electron. Agricult., 2010, 74(1):91-99.

DALE L M, THEWIS A, BOUDRY C, et al.. Hyperspectral imaging applications in agriculture and agro-food product quality and safety control:a review[J]. Appl. Spectrosc. Rev., 2013, 48(2):142-159.

李增芳, 楚秉泉, 章海亮, 等. 高光谱成像技术无损检测赣南脐橙表面农药残留研究[J]. 光谱学与光谱分析, 2016, 36(12):4034-4038. LI Z F, CHU B Q, ZHANG H L, et al.. Study on nondestructive detecting gannan navel pesticide residue with hyperspectral imaging technology[J]. Spectrosc. Spect. Anal., 2016, 36(12):4034-4038. (in Chinese)

SHAO Y N, JIANG L J, ZHOU H, et al.. Identification of pesticide varieties by testing microalgae using visible/near infrared hyperspectral imaging technology[J]. Sci. Rep., 2016, 6:24221.

SUN J, JIANG S Y, ZHANG M X, et al.. Detection of pesticide residues in mulberey leaves using VIS-NIR hyperspectral imaging technology[J]. J. Resid. Sci. Technol., 2016, 13:S125-S131.

刘民法, 张令标, 王松磊, 等. 近红外高光谱技术鉴别长枣表面的农药种类[J]. 食品研究与开发, 2014(15):81-86. LIU M F, ZHANG L B, WANG S L, et al.. Discrimination of different pesticides on long jujubes' surface by near-infrared hyperspectral technique[J]. Food Res. Dev., 2014(15):81-86. (in Chinese)

QIAO X J, JIANG J B, QI X T, et al.. Utilization of spectral-spatial characteristics in shortwave infrared hyperspectral images to classify and identify fungi-contaminated peanuts[J]. Food Chem., 2016, 220:393-399.

SUN J, CONG S L, MAO H P, et al.. Quantitative detection of mixed pesticide residue of lettuce leaves based on hyperspectral technique[J]. J. Food Proc. Eng., 2017, 41(2):e12654.

陈欣欣, 郭辰彤, 张初, 等. 高光谱成像技术的库尔勒梨早期损伤可视化检测研究[J]. 光谱学与光谱分析, 2017, 37(1):150-155. CHEN X X, GUO C T, ZHANG C, et al.. Visual detection study on early bruises of korla pear based on hyperspectral imaging technology[J]. Spectrosc. Spect. Anal., 2017, 37(1):150-155. (in Chinese)

HUANG M, TANG J Y, YANG B, et al.. Classification of maize seeds of different years based on hyperspectral imaging and model updating[J]. Comput. Electron. Agricult., 2016, 122:139-145.

BARBIN D, ELMASRY G, SUN D W, et al.. Near-infrared hyperspectral imaging for grading and classification of pork[J]. Meat Sci., 2012, 90(1):259-268.

WU D, SUN D W, HE Y. Application of long-wave near infrared hyperspectral imaging for measurement of color distribution in salmon fillet[J]. Innovat. Food Sci. Emerg. Technol., 2012, 16(39):361-372.

沈燕, 封超年, 李邵, 等. 农药对干旱胁迫下小麦幼苗生理生化特性的影响[J]. 江苏农业科学, 2007(3):16-19. SHEN Y, FENG C N, LI S, et al.. Effects of pesticides on physiological and biochemical characteristics of wheat seedlings under drought stress[J]. Jiangsu Agric. Sci., 2007(3):16-19. (in Chinese)

DE L M, TEROUZI W, KZAIBER F, et al.. Classification of moroccan olive cultivars by linear discriminant analysis applied to ATR-FTIR spectra of endocarps[J]. Int. J. Food Sci. Technol., 2012, 47(6):1286-1292.

梁守真, 施平, 马万栋, 等. 植被叶片光谱及红边特征与叶片生化组分关系的分析[J]. 中国生态农业学报, 2010, 18(4):804-809. LIANG S Z, SHI P, MA W D, et al.. Relational analysis of spectra and red-edge characteristics of plant leaf and leaf biochemical constituent[J]. Chin. J. Eco-Agric., 2010, 18(4):804-809. (in Chinese)

高荣强, 范世福, 严衍禄, 等. 近红外光谱的数据预处理研究[J]. 光谱学与光谱分析, 2004, 24(12):1563-1565. GAO R Q, FAN S F, YAN Y L, et al.. Preprocessing of near infrared spectroscopic data[J]. Spectrosc. Spect. Anal., 2004, 24(12):1563-1565. (in Chinese)

SHI J H, SONG W X. Sparse principal component analysis with measurement errors[J]. J. Stat. Plan. Infer., 2016, 175:87-99.

MILLER R, SIEGMUND D. Maximally selected chi square statistics[J]. Biometrics, 1982, 38(4):1011-1016.

RIVERA N V, GOMEZ S J, CHANONA P J, et al.. Early detection of mechanical damage in mango using NIR hyperspectral images and machine learning[J]. Bioproc. Biosyst. Eng., 2014, 122(3):91-98.

王思玲, 蔡骋, 马惠玲, 等. 基于高光谱成像的苹果水心病无损检测[J]. 北方园艺, 2015(8):124-130. WANG S L, CAI C, MA H L, et al.. Nondestructive detection of apple watercore based on hyperspectral imaging[J]. North. Hortic., 2015(8):124-130. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

高光谱技术结合特征波长筛选的牛肉品种多波段识别

可见/近红外高光谱成像技术对鸡蛋种类无损判别