Cognitive spectroscopy for the classification of rice varieties: A comparison of machine learning and deep learning approaches in analysing long-wave near-infrared hyperspectral images of brown and milled samples

被引:21
作者
Onmankhong, Jiraporn [1 ]
Ma, Te [2 ]
Inagaki, Tetsuya [2 ]
Sirisomboon, Panmanas [1 ]
Tsuchikawa, Satoru [2 ]
机构
[1] King Mongkuts Inst Technol Ladkrabang, Sch Engn, Dept Agr Engn, Bangkok 10520, Thailand
[2] Nagoya Univ, Grad Sch Bioagr Sci, Chikusa Ku, Furo Cho, Nagoya, Aichi 4648601, Japan
关键词
Thai jasmine rice; Nondestructive distinguishment; Near infrared hyperspectral imaging (NIR-HSI); Support vector machine (SVM); Convolutional neural network (CNN); AMYLOSE CONTENT; DIFFERENT CULTIVARS; JASMINE RICE; IDENTIFICATION; PROTEIN; BRAN;
D O I
10.1016/j.infrared.2022.104100
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
Rapid and non-destructive detection of genuine Thai Jasmine rice (Khao Dawk Mali 105 (KDML105)) from Pathum Thani1 (PTT1) and Phitsanulok2 (PSL2) under either milled or brown conditions is required to disrupt fraudulent. This study aimed to resolve this real issue using long-wave near infrared hyperspectral imaging (NIRHSI) coupled with machine learning and deep learning approaches. The best classification accuracy for the milled rice was achieved using the spectral imaging-based analysis on the NIR-HSI data with selected wavelength, approximately 95% for the test set either by convolutional neural network or support vector machine (SVM), whereas for the brown rice, the SVM model based on the averaged NIR spectra could achieve the best classification accuracy of 95.4%. It suggests the chemical component difference and its spatial distribution in the milled rice could contribute higher classification accuracy. Additionally, the surface bran effects of brown rice could be reduced by using averaged spectral data coupled with the SVM method.
引用
收藏
页数:11
相关论文
共 48 条
[31]  
Osborne B.G., 1993, LONGMAN SCI TECHNICA
[32]   Rapid Vitality Estimation and Prediction of Corn Seeds Based on Spectra and Images Using Deep Learning and Hyperspectral Imaging Techniques [J].
Pang, Lei ;
Men, Sen ;
Yan, Lei ;
Xiao, Jiang .
IEEE ACCESS, 2020, 8 :123026-123036
[33]   Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network [J].
Qiu, Zhengjun ;
Chen, Jian ;
Zhao, Yiying ;
Zhu, Susu ;
He, Yong ;
Zhang, Chu .
APPLIED SCIENCES-BASEL, 2018, 8 (02)
[34]   Optimization of rice amylose determination by NIR-spectroscopy using PLS chemometrics algorithms [J].
Sampaio, Pedro Sousa ;
Soares, Andreia ;
Castanho, Ana ;
Almeida, Ana Sofia ;
Oliveira, Jorge ;
Brites, Carla .
FOOD CHEMISTRY, 2018, 242 :196-204
[35]   Eating quality evaluation of Khao Dawk Mali 105 rice using near-infrared spectroscopy [J].
Siriphollakul, Pornarree ;
Nakano, Kazuhiro ;
Kanlayanarat, Sirichai ;
Ohashi, Shintaroh ;
Sakai, Ryosuke ;
Rittiron, Ronnarit ;
Maniwara, Phonkrit .
LWT-FOOD SCIENCE AND TECHNOLOGY, 2017, 79 :70-77
[36]   Identification of Lettuce Leaf Nitrogen Level Based on Adaboost and Hyperspectrum [J].
Sun Jun ;
Jin Xia-ming ;
Mao Han-ping ;
Wu Xiao-hong ;
Tang Kai ;
Zhang Xiao-dong .
SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33 (12) :3372-3376
[37]   Classification of rice amylose content by analysis of physicochemical properties [J].
Suwannaporn, Prisana ;
Pitiphunpong, Sawidtree ;
Champangern, Sirirat .
STARCH-STARKE, 2007, 59 (3-4) :171-177
[38]  
Suwansri S, 2004, J FOOD SCI, V69, pS30
[39]   Identification of adulteration in uncooked Jasmine rice by a portable low-cost artificial olfactory system [J].
Timsorn, Kriengkri ;
Lorjaroenphon, Yaowapa ;
Wongchoosuk, Chatchawal .
MEASUREMENT, 2017, 108 :67-76
[40]   Effect of amylose content on gelatinization, retrogradation and pasting properties of flours from different cultivars of Thai rice [J].
Varavinit, S ;
Shobsngob, S ;
Varanyanond, W ;
Chinachoti, P ;
Naivikul, O .
STARCH-STARKE, 2003, 55 (09) :410-415