高光谱成像结合SIS与RFS的蓝莓腐烂病检测

何宽; 田有文; 乔世成; 姚萍; 古文君

doi:10.3788/fgxb20194003.0413

您当前的位置：

首页 >

文章列表页 >

高光谱成像结合SIS与RFS的蓝莓腐烂病检测

发光学应用及交叉前沿 | 更新时间：2020-08-12

- 高光谱成像结合SIS与RFS的蓝莓腐烂病检测
- Detection of Rot Blueberry Disease by Hyperspectral Imaging with SIS and RFS
- 发光学报 2019年40卷第3期页码：413-421
- 作者机构：
  
  1. 沈阳农业大学信息与电气工程学院,辽宁沈阳,110866
  2. 辽宁省农业信息化工程技术研究中心,辽宁沈阳,110866
- 作者简介：
- 基金信息：
  
  国家自然科学基金（31601219）;辽宁省科学事业公益研究基金（20170039）资助项目
- DOI：10.3788/fgxb20194003.0413
  中图分类号： TP391.41
- 纸质出版日期：2019-3-5，
  
  网络出版日期：2018-10-11，
  
  收稿日期：2018-7-17，
  
  修回日期：2018-10-10，
扫描看全文
何宽, 田有文, 乔世成等. 高光谱成像结合SIS与RFS的蓝莓腐烂病检测[J]. 发光学报, 2019,40(3): 413-421

HE Kuan, TIAN You-wen, QIAO Shi-cheng etc. Detection of Rot Blueberry Disease by Hyperspectral Imaging with SIS and RFS[J]. Chinese Journal of Luminescence, 2019,40(3): 413-421
何宽, 田有文, 乔世成等. 高光谱成像结合SIS与RFS的蓝莓腐烂病检测[J]. 发光学报, 2019,40(3): 413-421 DOI： 10.3788/fgxb20194003.0413.

HE Kuan, TIAN You-wen, QIAO Shi-cheng etc. Detection of Rot Blueberry Disease by Hyperspectral Imaging with SIS and RFS[J]. Chinese Journal of Luminescence, 2019,40(3): 413-421 DOI： 10.3788/fgxb20194003.0413.

摘要

为了能够快速、无损地检测采后蓝莓腐烂病害，利用高光谱成像技术对采后蓝莓腐烂病进行检测。本研究提出光谱信息分割法（SIS）对866.5 nm波段图像蓝莓病害区域进行分割，取得了较好效果。另外根据正常蓝莓光谱曲线和病害蓝莓光谱曲线，提出区域特征筛选法（RFS），并结合竞争适应重加权采样（CARS）和连续投影（SPA）算法对可见光第一区域波段、近红外第二区域波段分别筛选特征波长。最后，采用相关向量机（RVM）模型和径向基（RBF）神经网络模型对蓝莓腐烂病害进行检测。检测结果表明，第一区域与第二区域特征波长组合建立的CARS-RBF模型检测效果最好，特征波长为655.8，710.9，752.2，759.9，761.2，866.5，969.7 nm，训练集和测试集正常蓝莓与病害蓝莓检测准确率分别为98.3%、98.6%和97.5%、98.75%。本研究提出的光谱信息分割法（SIS）和区域特征筛选法（RFS）检测蓝莓病害，为蓝莓在线检测和分拣提供了一种新的参考方法。

Abstract

In order to detect the rot disease of postharvest blueberries quickly

effectively and accurately

the rot disease of postharvest blueberries was detected by hyperspectral imaging technology with different detection models. According to analyse the difference of the spectral relative reflectance between the normal blueberries and the disease blueberries

the spectral Information segmentation(SIS) was proposed to segment the disease regions of blueberries to solve the problem that the conventional threshold segmentation method is difficult to accurately segment blueberry disease regions due to the indistinct color characteristics of the normal blueberries regions and the disease blueberries regions. According to the difference of spectrum in 450 nm to 1 000 nm

the regional feature selection(RFS) was put forward that divided the spectral relative reflectance(450-1 000 nm) into the two regions. The first region was in visible spectrum ranges 450-780 nm and the second region in near infrared ranges 780-1 000 nm.Then CARS and SPA were used to extract the characteristic wavelengths from spectral data in two regions. Finally

relevance vector machines(RVM) model and radial basis function(RBF) model were used to detect the rot disease of blueberries. By comparing the detection effects of different models

the CARS-RBF model in the combined regions of first region and second region had best detection effect and the characteristic wavelengths were 655.8

710.9

752.2

759.9

761.2

866.5

969.7 nm. The detection accuracy of the normal blueberries and the disease blueberries in the training sets and the testing sets were 98.3%

98.6% and 97.5%

98.75%

respectively. According to the result of the detection

we can draw a conclusion that the spectral information segmentation(SIS) and regional feature selection(RFS) were used to detect blueberry diseases effectively

which provide a new reference method for on-line detection and sorting of blueberries.

关键词

高光谱成像蓝莓腐烂病光谱信息分割法区域特征筛选法无损检测

Keywords

hyperspectral imagingrot disease of postharvest blueberriesspectral information segmentationregional feature selectionnondestructive detection

references

方仲相,胡君艳,江波,等. 蓝莓研究进展[J]. 浙江农林大学学报, 2013,30(4):599-606. FANG Z X,HU J Y,JIANG B,et al..Research progress on blueberry(Vaccinium spp.)[J]. J. Zhejiang A&F Univ., 2013,30(4):599-606. (in Chinese)

傅俊范,严雪瑞,李亚东. 小浆果病虫害防治原色图谱[M]. 北京:中国农业出版社, 2010:65-72. FU J F,YAN X R,LI Y D. A Color Atlas of Small Fruits Diseases and Pests Control[M]. Beijing:China Agricultural Press, 2010:65-72. (in Chinese)

刘华. 蓝莓贮藏加工技术研究[D]. 金华:浙江师范大学, 2012. LIU H. Studies on Storage and Processing Technology of Blueberry[D]. Jinhua:Zhejiang Normal University, 2012. (in Chinese)

蔡健荣,王建黑,黄星奕,等. 高光谱图像技术检测柑橘果锈[J]. 光电工程, 2009,36(6):26-30. CAI J R,WANG J H,HUANG X Y,et al.. Detection of rust in citrus with hyperspectral imaging technology[J]. Opto-Elect. Eng., 2009,36(6):26-30. (in Chinese)

刘燕德,肖怀春,孙旭东,等. 基于高光谱成像的柑橘黄龙病无损检测[J]. 农业机械学报, 2016,47(11):231-238. LIU Y D,XIAO H C,SUN X D,et al.. Non-destructive detection of citrus Huanglong disease using hyperspectral image technique[J]. Trans. Chin. Soc. Agric. Mach., 2016,47(11):231-238. (in Chinese)

温淑娴,李绍稳,金秀,等. 基于高光谱的砀山酥梨炭疽病害等级分类研究[J]. 计算机科学, 2017,44(S1):216-219. WEN S X,LI S W,JIN X,et al.. Research on anthrax disease classification of Dangshan Pear based on hyperspectral imaging technology[J]. Comput. Sci., 2017,44(S1):216-219. (in Chinese)

STEGMAYER G,MILONE D H,GARRAN S,et al.. Automaticrecognition of quarantine citrus diseases[J]. Exp. Syst. Appl., 2013,40(9):3512-3517.

KASHID S A,SHIRSIKARS G,PATILJ M. Detection of diseases and grading in pomegranate fruit using digital image processing[C]. Proceedings of The 4th International Conference on Science,Technology & Management,Pune,Maharashtra,India, 2017.

DESHPANDET,SENGUPTA S,RAGHUVANSHIK S. Grading & identification of disease in pomegranate leaf and fruit[J]. Int. J. Comput. Sci. Inf. Technol., 2014,5(3):4638-4645.

CUBERO S,ALEIXOS N,MOLT E,et al.. Advances in machine vision applications for automatic inspection and quality evaluation of fruits and vegetables[J]. Food Bioprocess Technol., 2011,4(4):487-504.

HU M H,DONGQ L,LIU B L,et al.. The potential of double K-means clustering for banana image segmentation[J]. J. Food Process Eng., 2014,37(1):10-18.

李江波,饶秀勤,应义斌. 农产品外部品质无损检测中高光谱成像技术的应用研究进展[J]. 光谱学与光谱分析, 2011,31(8):2021-2026. LI J B,RAO X Q,YING Y B. Advance on application of hyperspectral imaging to nondestructive detection of agricultural products external quality[J]. Spectrosc. Spect. Anal., 2011,31(8):2021-2026. (in Chinese)

LORENTED,ALEIXOS N,GMEZ-SANCHIS J,et al.. Recent advances and applications of hyperspectral imaging for fruit and vegetable quality assessment[J]. Food Bioprocess Technol., 2012,5(4):1121-1142.

SIEDLISKA A,BARANOWSKI P,MAZUREK W. Classification models of bruise and cultivar detection on the basis of hyperspectral imaging data[J]. Comput. Electron. Agric., 2014,106:66-74.

PAN L Q,ZHANG Q,ZHANG W,et al.. Detection of cold injury in peaches by hyperspectral reflectance imaging and artificial neural network[J]. Food Chem., 2015,192:134-141.

MUNERA S,BESADA C,ALEIXOS N,et al.. Non-destructive assessment of the internal quality of intact persimmon using colour and VIS/NIR hyperspectral imaging[J]. Food Sci. Technol., 2017,77:241-248.

HU M H,DONG Q L,LIU B L,et al.. Prediction of mechanical properties of blueberry using hyperspectral interactance imaging[J]. Postharvest Biol. Technol., 2016,115:122-131.

LI J B,HUANG W Q,TIAN X,et al.. Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectralimaging[J]. Comput. Electron. Agric., 2016,127:582-592.

LORENTE D,ZUDE M,REGEN C,et al.. Early decay detection in citrus fruit using laser-light backscattering imaging[J]. Postharvest Biol. Technol., 2013,86:424-430.

SUN Y,XIAO H,TU S C,et al.. Detecting decayed peach using a rotating hyperspectral imaging testbed[J]. LWT, 2018,87:326-332.

FOLCH-FORTUNY A,PRATS-MONTALBN J M,CUBERO S,et al.. VIS/NIR hyperspectral imaging and N-way PLS-DA models for detection of decay lesions in citrus fruits[J]. Chemometr. Intell. Lab. Syst., 2016,156:241-248.

刘思伽,田有文,张芳,等. 采用二次连续投影法和BP人工神经网络的寒富苹果病害高光谱图像无损检测[J]. 食品科学, 2017,38(8):277-282. LIU S J,TIAN Y W,ZHANG F,et al.. Hyperspectral imaging for nondestructive detection of Hanfu apple diseases using successive projections algorithm and BP neural network[J]. Food Sci., 2017,38(8):277-282. (in Chinese)

黄锋华,张淑娟,杨一,等. 油桃外部缺陷的高光谱成像检测[J]. 农业机械学报, 2015,46(11):252-259. HUANG F H,ZHANG S J,YANG Y,et al.. Application of hyperspectral imaging for detection of defective features in nectarine fruit[J]. Trans. Chin. Soc. Agric. Mach., 2015,46(11):252-259. (in Chinese)

李江波,郭志明,黄文倩,等. 应用CARS和SPA算法对草莓SSC含量NIR光谱预测模型中变量及样本筛选[J]. 光谱学与光谱分析, 2015,35(2):372-378. LI J B,GUO Z M,HUANG W Q,et al.. Near-infrared spectra combining with CARS and SPA algorithms to screen the variables and samples for quantitatively determining the soluble solids content in strawberry[J]. Spectrosc.Spect.Anal., 2015,35(2):372-378. (in Chinese)

袁莹,王伟,褚璇,等. 光谱特征波长的SPA选取和基于SVM的玉米颗粒霉变程度定性判别[J]. 光谱学与光谱分析, 2016,36(1):226-230. YUAN Y,WANG W,CHU X,et al.. Selection of characteristic wavelengths using SPA and qualitative discrimination of mildew degree of corn kernels based on SVM[J]. Spectrosc. Spect. Anal., 2016,36(1):226-230. (in Chinese)

于雷,朱亚星,洪永胜,等. 高光谱技术结合CARS算法预测土壤水分含量[J]. 农业工程学报, 2016,32(22):138-145. YU L,ZHU Y X,HONG Y S,et al.. Determination of soil moisture content by hyperspectral technology with CARS algorithm[J]. Trans. Chin. Soc. Agric. Eng., 2016,32(22):138-145. (in Chinese)

杨国鹏,周欣,余旭初. 稀疏贝叶斯模型与相关向量机学习研究[J]. 计算机科学, 2010,37(7):225-228. YANG G P,ZHOU X,YU X C. Research on sparse Bayesian model and the relevance vector machine[J]. Comput. Sci., 2010,37(7):225-228. (in Chinese)

何勇,刘飞,李晓丽,等. 光谱及成像技术在农业中的应用[M]. 北京:科学出版社, 2016:146-152. HE Y,LIU F,LI X L,et al.. Spectroscopy and Imaging Technology in Agriculture[M]. Beijing:Science Press, 2016:146-152. (in Chinese)

LEIVA-VALENZUELA G A,AGUILERA J M. Automatic detection of orientation and diseases in blueberries using image analysis to improve their postharvest storage quality[J]. Food Control, 2013,33(1):166-173.

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

基于高光谱漫透射成像可视化检测脐橙可溶性固形物

基于高光谱图像信息融合的红提糖度无损检测

可见/近红外高光谱成像技术对长枣中葡萄糖含量的无损检测

基于高光谱成像技术的土壤水分机理研究及模型建立

基于高光谱成像提取苹果糖度与硬度最佳波长