Identification of muskmelon seed variety using hyperspectral imaging technology combined with machine learning

Kunlan Luo, Wenchao Ye, Yuhao Diao, Jing Zhao, Wanjun Chen, Houcheng Liu, Yongbing Long

Abstract


Abstract: Liquid crystal tunable filter (LCTF) based on hyperspectral imaging technology combined with machine learning is developed to identify muskmelon seed variety rapidly and non-destructively.  LCTF-based hyperspectral imaging system equipped with a cold ring LED source is constructed to acquire the reflectance spectra of the muskmelon seeds.  Discriminating models based on support vector machine (SVM), linear discriminant analysis (LDA), and convolutional neural network (CNN) are then established to identify the seed variety with reflectance spectra as input.  It is found that the LDA model achieved the highest classification accuracy of 100% for the test set while a relatively low value of 96% and 83% was obtained for the SVM and CNN model respectively.  To improve classification accuracy of the model, data preprocessing (Savitzky-Golay smoothing and multiple scattering correction) and spectral feature extraction algorithm (successive projections algorithm and principal component analysis) were employed to treat the reflectance data.  With these treatments, the classification accuracy of the test set was improved to the highest value of over 99% for the SVM model and 86% for the CNN model.  The results showed that the LCTF-based hyperspectral imaging technology combined with machine learning was feasible to identify the muskmelon seed variety.

Keywords: hyperspectral imaging; liquid crystal tunable filter; variety identification; muskmelon seed; support vector machine; linear discriminant analysis; convolution neural network

DOI: 10.33440/j.ijpaa.20200303.93

 

Citation: Luo K L, Ye W C, Diao Y H, Zhao J, Chen W J, Liu H C, Long Y B.  Identification of muskmelon seed variety using hyperspectral imaging technology combined with machine learning.  Int J Precis Agric Aviat, 2020; 3(3): 14–20.


Full Text:

PDF

References


Thakur H, Sharma S, Thakur M. Recent trends in muskmelon (Cucumis melo L.) research: an overview. Journal of Horticultural Science and Biotechnology, 2019; †94(4): 533–547. doi: 10.1080/ 14620316.2018.1561214.

Venora G, Grillo O, Shahin M A, et al. Identification of Sicilian landraces and Canadian cultivars of lentil using an image analysis system, Food Research International, 2007; 40(1): 161–166. doi: 10.1016/ j.foodres.2006.09.001.

Huebner F R, Hussain A, Lookhart G L, et al. Discrimination of sister-line IR rice varieties by polyacrylamide gel electrophoresis and reversed-phase high-performance liquid chromatography. Cereal Chemistry, 1991; 68(6): 583–588.

Wu J, Yu H C, Dai H F, et al. Metabolite profiles of rice cultivars containing bacterial blight-resistant genes are distinctive from susceptible rice. Acta Biochimica et Biophysica Sinica, 2012; 44(8), 650–659. doi: 10.1093/abbs/gms043.

Liu X, Wang Y, Su Q, Wang Z. Study On Identification System Of Maize Seeds varieties Based On Machine Vision, Computer and Computing Technologies in Agriculture, 2009; 3: 2207–2216. doi:10.1007/ 978-1-4419-0213-9_72

Deepak Kumar Jain, et al. An approach for hyperspectral image classification by optimizing SVM using self organizing map, Journal of Computational Science, 2018; 25: 252–259. doi: 10.1016/ j.jocs.2017.07.016.

Li C, Jiang K, Feng Q, Wang X, Meng Z, Wang S, Gao Y. Identification of melon seed varieties based on chlorophyll fluorescence and reflectance spectra. Spectroscopy and Spectral Analysis, 2018; 1: 151–156. doi: 10.3964/j.issn.1000-0593(2018)01-0151-06 (in Chinese)

Guo P T, Li M F, Luo W, et al. Estimation of foliar nitrogen of rubber trees using hyperspectral reflectance with feature bands. Infrared Physics & Technology, 2019; 102: 103021. doi: 10.1016/j.infrared.2019.103021.

Zhang X L, Liu F, Nie P C, et al. Rapid Detection of Nitrogen Content and Distribution in Oilseed Rape Leaves Based on Hyperspectral Imaging, Spectroscopy and Spectral Analysis, 2014; 34(9): 2513–2518. doi: 10.3964/j.issn.1000-0593(2014)09-2513-06. (in Chinese)

Barbedo J G A. Detection of nutrition deficiencies in plants using proximal images and machine learning: A review, Computers and Electronics in Agriculture, 2019; 162: 482–492. doi: 10.1016/ j.compag.2019.04.035.

Gutierrez S, Wendel A, Underwood J. Ground based hyperspectral imaging for extensive mango yield estimation, Computers and Electronics in Agriculture, 2019, 157: 126–135. doi: 10.1016/j.compag.2018.12.041.

Wendel A, Underwood J, Walsh K. Maturity estimation of mangoes using hyperspectral imaging from a ground based mobile platform, Computers and Electronics in Agriculture, 2018, 155: 298–313. doi: 10.1016/j.compag.2018.10.021.

Li H Y, Jia S Y, Le Z C. Quantitative Analysis of Soil Total Nitrogen Using Hyperspectral Imaging Technology with Extreme Learning Machine, Sensors; 2019, 19(20): 4355. doi: 10.3390/s19204355.

Feng C H, Makino Y, Oshita S, et al. Hyperspectral imaging and multispectral imaging as the novel techniques for detecting defects in raw and processed meat products: Current state-of-the-art research advances, Food Control, 2018; 84: 165–176. doi: 10.1016/j.foodcont.2017.07.013.

Ali M M, Bachik N A, Muhadi N A, et al. Non-destructive techniques of detecting plant diseases: A review, Physiological and Molecular Plant Pathology, 2019; 108: 101426. doi: 10.1016/j.pmpp.2019.101426.

Zhang J C, Huang Y B, Pu R L, et al. Monitoring plant diseases and pests through remote sensing technology: A review, Computers and Electronics in Agriculture, 2019; 165: 104943. doi: 10.1016/j.compag. 2019.104943.

Sun J, Cong S L, Mao H P, et al. Quantitative detection of mixed pesticide residue of lettuce leaves based on hyperspectral technique, Journal of Food Process Engineering, 2018; 41: e12654. doi: 10.1111/ jfpe.12654.

He X T, Feng X P, Sun D W, et al. Rapid and Nondestructive Measurement of Rice Seed Vitality of Different Years Using Near-Infrared Hyperspectral Imaging, Molecules, 2019; 24(12): 2227. doi: 10.3390/ molecules24122227.

Zhu Hongyun, Wang Changlong, Wang Jianbin, Ma Xiaolin. Signal denoising method based on singular value decomposition and Savitzky-Golay filter. Computer Applications, 2015, 35(10): 3004–3007, 3012. doi: 10.11772/j.issn.1001-9081.2015.10.3004(in Chinese)

Nie P C, Zhang J N, Feng X P, et al. Classification of hybrid seeds using near-infrared hyperspectral imaging technology combined with deep learning, Sensors and Actuators B: Chemical, 2019, 296: 126630. doi: 10.1016/j.snb.2019.126630.

Feng L, Zhu S S, Zhang C, et al. Identification of Maize Kernel Vigor under Different Accelerated Aging Times Using Hyperspectral Imaging, Molecules, 2018; 23(12): 3078. doi: 10.3390/molecules23123078.

Zhang J, Dai L M, Cheng F. Classification of Frozen Corn Seeds Using Hyperspectral VIS/NIR Reflectance Imaging, Molecules, 2019; 24(1): 149. doi: 10.3390/ molecules24010149.

Qiu Z J, Chen J, Zhao Y Y, et al. Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network, Applied sciences-Basel, 2018, 8(2): 212. doi: 10.3390/ app8020212.

Baek I, Kim M S, Cho B K, et al. Selection of Optimal Hyperspectral Wavebands for Detection of Discolored, Diseased Rice Seeds, Applied Sciences-Basel, 2019; 9(5): 1027. doi: 10.3390/app9051027.

Zhao Y Y, Zhu S S, Zhang C, et al. Application of hyperspectral imaging and chemometrics for variety classification of maize seeds, RSC Advances, 2018; 8(3): 1337–1345. doi: 10.1039/c7ra05954j.

Yang Q S, Marchant J A. Accurate blemish detection with active contour models, Computers and Electronics in Agriculture, 1996; 14(1): 77–89. doi: 10.1016/0168-1699(95)00038-0.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.