Detection of Thrips Defect on Green-Peel Citrus Using Hyperspectral Imaging Technology Combining PCA and B-Spline Lighting Correction Method

doi:10.1016/S2095-3119(13)60671-1

Journal of Integrative Agriculture ›› 2014, Vol. 13 ›› Issue (10): 2229-2235.DOI: 10.1016/S2095-3119(13)60671-1

Detection of Thrips Defect on Green-Peel Citrus Using Hyperspectral Imaging Technology Combining PCA and B-Spline Lighting Correction Method

DONG Chun-wang, YE Yang, ZHANG Jian-qiang, ZHU Hong-kai , LIU Fei

1、Tea Research Institute, Chinese Academy of Agricultural Sciences, Hangzhou 310008, P.R.China
2、School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, P.R.China

收稿日期:2013-06-19 出版日期:2014-10-01 发布日期:2014-10-10
通讯作者: YE Yang, Tel: +86-571-86653155, E-mail: yeyang@tricaas.com
作者简介:DONG Chun-wang, E-mail: dongchunwang@tricaas.c
基金资助:
This work was supproted by the National Key Technology R&D Program of China (2012BAF07B05).

Detection of Thrips Defect on Green-Peel Citrus Using Hyperspectral Imaging Technology Combining PCA and B-Spline Lighting Correction Method

DONG Chun-wang, YE Yang, ZHANG Jian-qiang, ZHU Hong-kai , LIU Fei

1、Tea Research Institute, Chinese Academy of Agricultural Sciences, Hangzhou 310008, P.R.China
2、School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, P.R.China

Received:2013-06-19 Online:2014-10-01 Published:2014-10-10
Contact: YE Yang, Tel: +86-571-86653155, E-mail: yeyang@tricaas.com
About author:DONG Chun-wang, E-mail: dongchunwang@tricaas.c
Supported by:
This work was supproted by the National Key Technology R&D Program of China (2012BAF07B05).

摘要/Abstract

摘要： In order to find an effective method of detecting thrips defect on green-peel citrus, a defect segmentation method was developed using a single threshold value based on combination of characteristic wavelengths principal component analysis (PCA) and B-spline lighting correction method in this study. At first, four characteristic wavelengths (523, 587, 700 and 768 nm) were obtained using PCA of Vis-NIR (visible and near-infrared) bands and analysis of weighting coefficients; secondarily, PCA was performed using characteristic wavelengths and the second principal component (PC2) was selected to classify images; then, B-spline lighting correction method was proposed to overcome the influence of lighting non-uniform on citrus when thrips defect was segmented; finally, thrips defect on citrus was extracted by global threshold segmentation and morphological image processing. The experimental results show that thrips defect in citrus can be detected with an accuracy of 96.5% by characteristic wavelengths PCA and B-spline lighting correction method. This study shows that thrips defect on green-peel citrus can be effectively identified using hyperspectral imaging technology.

关键词: hyperspectral images , principal component analysis , lighting correction , green-peel citrus , thrips defect

Abstract: In order to find an effective method of detecting thrips defect on green-peel citrus, a defect segmentation method was developed using a single threshold value based on combination of characteristic wavelengths principal component analysis (PCA) and B-spline lighting correction method in this study. At first, four characteristic wavelengths (523, 587, 700 and 768 nm) were obtained using PCA of Vis-NIR (visible and near-infrared) bands and analysis of weighting coefficients; secondarily, PCA was performed using characteristic wavelengths and the second principal component (PC2) was selected to classify images; then, B-spline lighting correction method was proposed to overcome the influence of lighting non-uniform on citrus when thrips defect was segmented; finally, thrips defect on citrus was extracted by global threshold segmentation and morphological image processing. The experimental results show that thrips defect in citrus can be detected with an accuracy of 96.5% by characteristic wavelengths PCA and B-spline lighting correction method. This study shows that thrips defect on green-peel citrus can be effectively identified using hyperspectral imaging technology.

Key words: hyperspectral images , principal component analysis , lighting correction , green-peel citrus , thrips defect

DONG Chun-wang, YE Yang, ZHANG Jian-qiang, ZHU Hong-kai , LIU Fei. Detection of Thrips Defect on Green-Peel Citrus Using Hyperspectral Imaging Technology Combining PCA and B-Spline Lighting Correction Method[J]. Journal of Integrative Agriculture, 2014, 13(10): 2229-2235.

参考文献

Aleixos N, Blasco J, Navarrón F, Molto E. 2002. Multispectralinspection of citrus in real-time using machine vision anddigital signal processors. Computers and Electronics inAgriculture, 33, 121-137

Blasco J, Aleixos N, Gómez-Sanchís J, Molto E. 2009.Recognition and classification of external skin damage incitrus fruits using multispectral data and morphologicalfeatures. Biosystems Engineering, 103, 137-145

Blasco J, Aleixos N, Moltó E. 2007. Computer vision detectionof peel defects in citrus by means of a region orientedsegmentation algorithm. Journal of Food Engineering,81, 384-393

Cai J R, Wang J H, Chen Q S, Zhao J W. 2009. Detection of rust in citrus by hyperspectral imaging technology andband ratio algorithm. Transactions of the Chinese Societyof Agricultural Engineering, 25, 127-131 (in Chinese)

ElMasry G, Wang N, Vigneault C. 2009. Detecting chillinginjury in Red Delicious apple using hyperspectral imagingand neural networks. Postharvest Biology and Technology,52, 1-8

Huang S P, Hong T S, Yue X J 2013. Hyperspecrtal estimationmodel of tatal phosphorus content for certus leaves.Transactions of the Chinese Society for AgriculturalMachinery, 44, 202-207

Huang W Q, Chen L Q, Li J B. 2013. Effective wavelengthsdetermination for detection of slight bruises on applesbased on hyperspectral imaging. Transactions of theChinese Society of Agricultural Engineering, 29, 272-277

Jiang X F, Pan G W, Tao C K. 2007. Cloud elimination methodin remote sensing image based on spline curve. LaserTechnology, 6, 581-583

Kim D G, Burks T F, Qin J W, Bulanonm D M. 2009.Classification of grapefruit peel diseases using color texturefeature analysis. International Journal of Agricultural &Biological Engineering, 2, 41-50

Li J B, Rao X Q, Wang F J, Wu W, Ying Y B. 2013. Automaticdetection of common surface defects on oranges usingcombined lighting transform and image ratio methods.Postharvest Biology and Technology, 86, 59-69

Li J B, Rao X Q, Ying Y B. 2011. Detection of commondefects on oranges using hyperspectral reflectance imaging.Computers and Electronics in Agriculture, 78, 38-48

Li J B, Rao X Q, Ying Y B. 2012. Development of algorithmsfor detecting citrus canker based on hyperspectralreflectance imaging. Journal of the Science of Food andAgriculture, 92, 125-134

Li J B, Rao X Q, Ying Y B, Ma B X, Guo J X. 2009.Background and external defects segmentation of navelorange based on mask and edge gray value compensationalgorithm. Transactions of the Chinese Society ofAgricultural Engineering, 25, 133-137 (in Chinese)

Liu Y, Chen Y R, Kim M S, Chan D E, Lefcourt A M. 2007.Development of simple algorithms for the detection offecal contaminants on apples from visible/near infraredhyperspectral reflectance imaging. Journal of FoodEngineering, 81, 412-418

López-García F, Andreu-García G, Blasco J, Aleixos N,Valiente J. 2010. Automatic detection of skin defects incitrus fruits using a multivariate image analysis approach.Computers and Electronics in Agriculture, 71, 189-197

Lorente D, Aleixis N, Gomez-Sanchis J, Cubero S, Garcia-Navarrete O L, Blasco J. 2012. Recent advancesand applications of hyperspectral imaging for fruitand vegetable quality assessment. Food BioprocessTechnology, 5, 1121-1142

Qian Y R, Yu J, Jia Z H. 2013. Extraction and analysis ofhyperspecrtal data from typical desert grassland in xinjiang.Acta Prataculturae Sinica, 22, 157-166 (in Chinese)

Qin J W, Burks T F, Kim M S, Chao K, Ritenour M A. 2008.Detecting citrus canker by hyperspectral reflectanceimaging and PCA-based image classification method.Proceedings of International Society for OpticalEngineering, 6983, 1-11

Rajkumanr P, Wang N, Elmasry G, Raghavan G S V, GariepyY. 2012. Studies on banana fruit quality and maturity stagesusing hyperspectral imaging. Journal of Food Engineering,108, 194-200

Vargas A M, Moon S K, Yang T, Alan M, Lefcourt Y, ChenR, Luo Y G, Song Y S, Buchanan R. 2005. Defection offecal contamination on cantaloupes using hyperspectralfluorescence imagery. Journal of Food Science, 70, 471-476

Vovk U, Pernus F, Likar B. 2007. A review of methods forcorrection of intensity inhomogeneity in MRI. IEEETransations on Medical Imaging, 26, 405-421

Wu D, Sun D W. 2013. Advanced applications of hyperspectralimaging technology for food quality and safety analysis andassessment: A review - Part II: Applications. InnovativeFood Science and Emerging Technologies, doi: 10.1016/j.ifset.2013.04.016

Xing J, Bravo C, Jancsók P T, Ramon H, De B J. 2005.Detecting bruises on ‘Golden Delicious’ apples usinghyperspectral imaging with multiple wavebands.Biosystems Engineering, 90, 27-36

Xue L, Li J, Liu M H. 2008. Detecting pesticide residue onnavel orange surface by using hyperspectral imaging. ActaOptica Sinica, 28, 2277-2280

(in Chinese)Zhao Q S, Liu J W, Chen J H, Saritpom V. 2008. Detectingsubtle bruises on fruits with hyperspectral imaging.Transactions of the Chinese Society for AgriculturalMachinery, 39, 106-109 (in Chinese)

Detection of Thrips Defect on Green-Peel Citrus Using Hyperspectral Imaging Technology Combining PCA and B-Spline Lighting Correction Method

Detection of Thrips Defect on Green-Peel Citrus Using Hyperspectral Imaging Technology Combining PCA and B-Spline Lighting Correction Method

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics