[1]闫明壮,王浩云,吴媛媛,等.基于光谱与纹理特征融合的绿萝叶绿素含量检测[J].南京农业大学学报,2021,44(3):568-575.[doi:10.7685/jnau.202006013]
 YAN Mingzhuang,WANG Haoyun,WU Yuanyuan,et al.Detection of chlorophyll content of Epipremnum aureum based on fusion of spectrum and texture features[J].Journal of Nanjing Agricultural University,2021,44(3):568-575.[doi:10.7685/jnau.202006013]
点击复制

基于光谱与纹理特征融合的绿萝叶绿素含量检测()
分享到:

《南京农业大学学报》[ISSN:1000-2030/CN:32-1148/S]

卷:
44卷
期数:
2021年3期
页码:
568-575
栏目:
食品与工程
出版日期:
2021-05-10

文章信息/Info

Title:
Detection of chlorophyll content of Epipremnum aureum based on fusion of spectrum and texture features
作者:
闫明壮 王浩云 吴媛媛 曹雪莲 徐焕良
南京农业大学信息科学技术学院, 江苏 南京 210095
Author(s):
YAN Mingzhuang WANG Haoyun WU Yuanyuan CAO Xuelian XU Huanliang
College of Information Science and Technology, Nanjing Agricultural University, Nanjing 210095, China
关键词:
绿萝叶绿素SPAD值高光谱特征纹理特征特征融合
Keywords:
Epipremnum aureumchlorophyll SPAD valuehyperspectral featurestexture featurefusion features
分类号:
TS217
DOI:
10.7685/jnau.202006013
摘要:
[目的] 本文旨在快速测定植物体内叶绿素含量,以提高无损测定叶绿素的准确性。[方法] 以绿萝叶片为研究对象,提出一种串联融合高光谱特征与纹理特征的叶绿素SPAD值的无损检测方法。采集320片绿萝叶片样本在400~900 nm波段的光谱信息,使用Savitzky-Golay卷积平滑对原始高光谱图像进行预处理,利用连续投影算法(successive projections algorithm,SPA)选取出10个特征波段,对绿萝叶片高光谱图像中的RGB图像采用灰度共生矩阵算法(gray-level co-occurrence matrix,GLCM)提取其纹理特征,采用串联方法融合高光谱特征与纹理特征得到融合特征,分别建立单一特征和融合特征的误差反向传输人工神经网络(back propagation artificial neural network,BPANN)和支持向量机回归(support vector machine regression,SVR)模型。[结果] 单一使用特征光谱数据或图像纹理数据作为特征值建立的预测模型,综合性能不稳定;基于串联融合特征的预测模型准确率有明显提升。基于串联融合特征的SVR模型具有最佳的预测结果,校正集决定系数R2为0.961 2,预测集决定系数R2为0.957 1。[结论] 高光谱特征与纹理特征的融合特征可以提高叶绿素回归预测模型的准确性,为叶绿素含量无损检测提供了重要参考。
Abstract:
[Objectives] The main goal of the article is to quickly obtain the chlorophyll content in plants and improve the accuracy of non-destructive measurement of chlorophyll. [Methods] Taking the leaves of Epipremnum aureum as the research object,a non-destructive detection method of chlorophyll SPAD value combining hyperspectral and texture features in series was proposed,the spectral information of 320 leaf samples of E.aureum in the wavelength range(400-900 nm) was collected,original hyperspectral image was preprocessed by Savitzky-Golay convolution smoothing,and 10 characteristic wavelengths were selected through successive projections algorithm(SPA);At the same time,gray-level co-occurrence matrix(GLCM) was used to extract texture features of RGB images in hyperspectral images;Finally,the concatenation method was used to fuse the hyperspectral feature and the texture feature to obtain the fusion feature. The back propagation artificial neural network(BPANN) and the support vector machine regression(SVR) models of single feature and fusion feature were established respectively. [Results] The test results showed that the prediction model established by using feature spectrum data or image texture data as feature values alone had unstable comprehensive performance and that the accuracy of the prediction model based on series fusion features had been significantly improved. The SVR model established after fusing features had the best prediction result,the correction set decision coefficient R2 was 0.961 2,and the prediction set decision coefficient R2 was 0.957 1. [Conclusions] This study proves that the fusion of hyperspectral features and texture features can improve the accuracy of the chlorophyll regression prediction model,and provides an important reference for the non-destructive detection of chlorophyll content.

参考文献/References:

[1] Ghasemi M,Arzani K,Yadollahi A,et al. Estimate of leaf chlorophyll and nitrogen content in Asian pear(Pyrus serotina Rehd.) by CCM-200[J]. Notulae Scientia Biologicae,2011,3(1):91-94.
[2] 鲁敏,景荣荣,赵洁,等. 苯污染胁迫下室内植物叶绿素含量变化分析研究[J]. 山东建筑大学学报,2016,31(1):1-6. Lu M,Jing R R,Zhao J,et al. Analysis of indoor plant chlorophyll content in benzene pollution stress[J]. Journal of Shandong Jianzhu University,2016,31(1):1-6(in Chinese with English abstract).
[3] 刘燕德,张光伟,蔡丽君. 基于高光谱的GA和SPA算法对赣南脐橙叶绿素定量分析[J]. 光谱学与光谱分析,2012,32(12):3377-3380. Liu Y D,Zhang G W,Cai L J. Analysis of chlorophyll in Gannan navel orange with algorithm of GA and SPA based on hyperspectral[J]. Spectroscopy and Spectral Analysis,2012,32(12):3377-3380(in Chinese with English abstract).
[4] 朱军伟,张彦娥,王晓敏,等. 基于图像纹理的玉米叶片叶绿素含量分析研究[J]. 微计算机信息,2010,26(10):106-108. Zhu J W,Zhang Y E,Wang X M,et al. Analysis and research of chlorophyll content in maize leaf based on image texture[J]. Microcomputer Information,2010,26(10):106-108(in Chinese with English abstract).
[5] Mishra P,Cordella C B Y,Rutledge D N,et al. Application of independent components analysis with the JADE algorithm and NIR hyperspectral imaging for revealing food adulteration[J]. Journal of Food Engineering,2016,168:7-15.
[6] 孙俊,金夏明,毛罕平,等. 基于高光谱图像光谱与纹理信息的生菜氮素含量检测[J]. 农业工程学报,2014,30(10):167-173. Sun J,Jin X M,Mao H P,et al. Detection of nitrogen content in lettuce leaves based on spectroscopy and texture using hyperspectral imaging technology[J]. Transactions of the Chinese Society of Agricultural Engineering,2014,30(10):167-173(in Chinese with English abstract).
[7] Cheng W W,Sun D W,Pu H B,et al. Integration of spectral and textural data for enhancing hyperspectral prediction of K value in pork meat[J]. LWT-Food Science and Technology,2016,72:322-329.
[8] Zhang C,Guo C T,Liu F,et al. Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine[J]. Journal of Food Engineering,2016,179:11-18.
[9] 于慧春,王润博,殷勇,等. 基于高光谱图像光谱与纹理信息的枸杞多糖及总糖含量检测[J]. 核农学报,2018,32(3):523-531. Yu H C,Wang R B,Yin Y,et al. Prediction of polysaccharide and total sugar in wolfberry based on spectral and texture information from hyperspectral image[J]. Journal of Nuclear Agricultural Sciences,2018,32(3):523-531(in Chinese with English abstract).
[10] Yao H B,Lewis D. Spectral preprocessing and calibration techniques[M]//Hyperspectral Imaging for Food Quality Analysis and Control. Amsterdam:Elsevier,2010:45-78.
[11] 张保华,李江波,樊书祥,等. 高光谱成像技术在果蔬品质与安全无损检测中的原理及应用[J]. 光谱学与光谱分析,2014,34(10):2743-2751. Zhang B H,Li J B,Fan S X,et al. Principles and applications of hyperspectral imaging technique in quality and safety inspection of fruits and vegetables[J]. Spectroscopy and Spectral Analysis,2014,34(10):2743-2751(in Chinese with English abstract).
[12] 孙俊,卫爱国,毛罕平,等. 基于高光谱图像及ELM的生菜叶片氮素水平定性分析[J]. 农业机械学报,2014,45(7):272-277. Sun J,Wei A G,Mao H P,et al. Discrimination of lettuce leaves’ nitrogen status based on hyperspectral imaging technology and ELM[J]. Transactions of the Chinese Society for Agricultural Machinery,2014,45(7):272-277(in Chinese with English abstract).
[13] 王文秀,彭彦昆,郑晓春,等. 便携式猪肉营养组分无损实时检测装置研究[J]. 农业机械学报,2017,48(9):303-311. Wang W X,Peng Y K,Zheng X C,et al. Portable nondestructive detection device for nutrient components of pork[J]. Transactions of the Chinese Society for Agricultural Machinery,2017,48(9):303-311(in Chinese with English abstract).
[14] 雍婧姣,王霞,石思佳,等. 基于R语言的近红外光谱对甘草中指标成分定量分析[J]. 中国实验方剂学杂志,2019,25(9):176-181. Yong J J,Wang X,Shi S J,et al. Quantitative analysis of index components in glycyrrhizae radix et khizoma by near infrared spectroscopy based on R software[J]. Chinese Journal of Experimental Traditional Medical Formulae,2019,25(9):176-181(in Chinese with English abstract).
[15] 褚小立,袁洪福,陆婉珍. 近红外分析中光谱预处理及波长选择方法进展与应用[J]. 化学进展,2004,16(4):528-542. Chu X L,Yuan H F,Lu W Z. Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique[J]. Progress in Chemistry,2004,16(4):528-542(in Chinese with English abstract).
[16] 芦永军,曲艳玲,宋敏. 近红外相关光谱的多元散射校正处理研究[J]. 光谱学与光谱分析,2007,27(5):877-880. Lu Y J,Qu Y L,Song M. Research on the correlation chart of near infrared spectra by using multiple scatter correction technique[J]. Spectroscopy and Spectral Analysis,2007,27(5):877-880(in Chinese with English abstract).
[17] 熊智新,马璞璠,梁龙,等. 近红外光谱结合连续投影算法检测综纤维素含量[J]. 中国造纸学报,2019,34(4):46-51. Xiong Z X,Ma P F,Liang L,et al. Determination of holocellulose content using near infrared spectroscopy and successive projections algorithm[J]. Transactions of China Pulp and Paper,2019,34(4):46-51(in Chinese with English abstract).
[18] 许敬诚,吕新,林皎,等. 基于叶片纹理特征的棉花蚜害诊断模型研究[J]. 棉花学报,2020,32(2):133-142. Xu J C,Lü X,Lin J,et al. The diagnostic model of cotton aphids based on leaf textural features[J]. Cotton Science,2020,32(2):133-142(in Chinese with English abstract).
[19] 牛鲁燕,张晓艳,郑纪业,等. 葡萄叶片叶绿素含量高光谱估测模型研究[J]. 山东农业科学,2018,50(7):152-156. Niu L Y,Zhang X Y,Zheng J Y,et al. Study on high spectral estimation model of chlorophyll content in grape leaves[J]. Shandong Agricultural Sciences,2018,50(7):152-156(in Chinese with English abstract).

备注/Memo

备注/Memo:
收稿日期:2020-06-11。
基金项目:国家自然科学基金项目(31601545);江苏省重点研发计划项目(L201704);中央高校基本科研业务费专项资金(KYLH202006);大学生创新创业训练计划专项(S20190025)
作者简介:闫明壮,硕士研究生。
通信作者:徐焕良,教授,博导,研究方向为物联网技术及应用,E-mail:huanliangxu@njau.edu.cn。
更新日期/Last Update: 1900-01-01