All Issue

2024 Vol.33, Issue 4 Preview Page

Original Articles

Model for Non-destructive Quality Prediction of ‘Mihong’ Peach using Hyperspectral Imaging

초분광 영상을 활용한 복숭아 ‘미홍’ 과실의 비파괴 품질 예측 모델

Han Ryul Seo1
,
Seung Hwan Oh2
,
Ji Woo Lee1
,
Jae Won Ryu1
,
Hae Chan Jeon1
,
Seul Ki Lee3
,
Jin Gook Kim45
,
Seung Wook Song6*
서 한률1
,
오 승환2
,
이 지우1
,
류 재원1
,
전 해찬1
,
이 슬기3
,
김 진국45
,
송 승욱6*
1Senior Manager, Podo Inc., Digital New Technology Business, Image Lab, Seongnam-si 13449, Korea
2Team Manager, Podo Inc., Digital New Technology Business, Image Lab, Seongnam-si 13449, Korea
3Researcher, Fruit Research Division, National Institute of Horticultural and Herbal Science, Wanju 55365, Korea
4Professor, Department of Horticulture, College of Agriculture and Life Science, Gyeongsang National University, Jinju 52828, Korea
5Principal Researcher, Institute of Agriculture and Life Sciences, Gyeongsang National University, Jinju 52828, Korea
6Senior Director, Podo Inc., Digital New Technology Business, Image Lab, Seongnam-si 13449, Korea
1㈜포도 디지털신기술사업단 대리
2㈜포도 디지털신기술사업단 팀장
3국립원예특작과학원 과수과 농업연구사
4경상국립대학교 원예과학부 교수
5경상국립대학교 농업생명과학연구원 책임연구원
6㈜포도 디지털신기술사업단 단장
*Corresponding Author
31 October 2024. pp. 340-351
PDF XML Citation
Abstract

This study aims to develop a non-destructive quality prediction model for ‘Mihong’ peach under open-field conditions using hyperspectral imaging. The primary objective is to identify wavelengths and vegetation indices that exhibit strong correlation with soluble solids content (SSC), titratable acidity (TA), and firmness in the image data captured by a hyperspectral camera. These indices were subsequently used to construct predictive models for SSC, TA, and firmness. Hyperspectral imaging data were collected from 120 ‘Mihong’ peach samples during the 2023 and 2024 growing seasons. The data preprocessing methods (IQR, SNV, SG) were applied to improve the accuracy of the models, and predictive models were developed using partial least squares regression (PLSR), random forest (RF), and extreme gradient boosting (XGB) algorithms. Model performance was assessed using the coefficient of determination (R2) and root mean square error (RMSE).

Keywords
harvester identification
machine learning
non-destructive investigation
spectral analysis
VNIR

본 연구는 복숭아 ‘미홍’의 비파괴 품질 예측 모델을 개발하기 위해 노지 현장에서의 초분광 영상을 활용하였다. 주요 목표는 초분광 카메라로 취득된 영상 데이터를 활용하여 가용성 고형물 함량(SSC), 산도(TA) 그리고 경도(Firmness)와 높은 상관관계를 보이는 파장대 및 식생 지수를 산출하는 것이다. 산출된 파장대 및 지수는 이후 가용성 고형물 함량, 산도 그리고 경도에 대한 예측 모델을 구축하기 위한 독립 변수로 활용되었다. 2023년과 2024년에 걸쳐 복숭아의 생육기간 동안 총 120개의 ‘미홍’ 복숭아의 초분광 영상데이터가 수집되었다. 모델의 정확도 향상을 위하여 데이터 전처리(IQR, SNV, SG 등)를 수행하였으며, 예측 모델은 부분 최소 제곱 회귀(Partial Least Squares Regression, PLSR), Random forest(RF), 그리고 Extreme Gradient Boosting(XGB) 알고리즘을 사용하여 구축하였다. 구축한 모델의 성능은 결정 계수(R2)와 평균 제곱근 오차(RMSE)를 사용하여 평가하였다.

키워드
근적외선
기계 학습
분광 분석
비파괴 조사
수확기 판별
References
1

Busemeyer L., D. Mentrup, K. Moller, E. Wunder, K. Alheit, and V. Hahn et al. 2013, Breedvision: A multi-sensor platform for non-destructive field-based phenotyping in plant breeding. Sensors 13:2830-2847. doi.org/10.3390/s130202830

10.3390/s13030283023447014PMC3658717
2

Costa C., F. Antonucci, and F. Pallottino et al. 2011, Hyperspectral imagery applications for precision agriculture - A systemic survey. Multimedia Tools Appl 4:673-692. doi:10.1007/s11947-011-0556-0

10.1007/s11947-011-0556-0
3

Dong J., and W. Guo 2015, Nondestructive determination of apple internal qualities using near-infrared hyperspectral reflectance imaging. Food Anal Methods 8:2635-2646. (in Korean) doi:10.1007/s12161-015-0169-8

10.1007/s12161-015-0169-8
4

Forkmann G., and S. Martens 2001, Metabolic engineering and applications of flavonoids. Curr Opin Biotechnol 12:155-160. doi.org/10.1016/S0958-1669(00)00197-4

10.1016/S0958-1669(00)00192-011287230
5

Giovos R., Tassopoulos D., Kalivas D., Lougkos N., and Priovolou A. 2021, Remote sensing vegetation indices in viticulture: A critical review. Agriculture 11:457. doi:10.3390/ agriculture11050457.

10.3390/agriculture11050457
6

Jacquemoud S., and F. Baret 1990, PROSPECT: A model of leaf optical properties spectra. Remote Sens Environ 34:75-91.

10.1016/0034-4257(90)90100-Z
7

Jang K.E., G. Kim, M.H. Shin, J.G. Cho, J.H. Jeong, S.K. Lee, D. Kang, and J.G. Kim 2022, Field application of a Vis/NIR hyperspectral imaging system for nondestructive evaluation of physicochemical properties in 'Madoka' peaches. Plants 11:2327. doi.org/10.3390/plants11172327

10.3390/plants1117232736079708PMC9460469
8

Jia W., M. Sun, J. Lian, and S. Hou 2022, Feature dimensionality reduction: a review. Complex Intell Syst 8:2663-2693. doi:10.1007/s40747-021-00637-x

10.1007/s40747-021-00637-x
9

Jin H., and L. Eklundh 2014, A physically based vegetation index for improved monitoring of plant phenology. Remote Sens Environ 152:512-525. doi.org/10.1016/j.rse.2014.06.004

10.1016/j.rse.2014.07.010
10

Kim J., H. Lee, M. Jeong, D. Kim, and S. Park 2019, Diagnosis of Nitrogen nutritional status in apple tree leaves using hyperspectral imaging. J Biosyst Eng 44:245-253. (in Korean) doi:10.5307/JBE.2019.44.4.245

10.1007/s42853-019-00035-9
11

Kim J.T., Y.H. Kim, J.S. Choi, and I.J. Lee 2014, Effect of sorbitol and salicylic acid on quality and functional food contents of tomato fruit (Solanum lycopersicum). Horti Sci Technol 32:771-780. (in Korean) doi:10.7235/hort.2014.13250

10.7235/hort.2014.14018
12

Kim M.J., W.H. Yu, D.J. Song, S.W. Chun, M.S. Kim, A. Lee, G. Kim, B.S. Shin, and C. Mo 2024, Prediction of soluble-solid content in citrus fruit using visible-near-infrared hyperspectral imaging based on effective-wavelength selection algorithm. Sensors 24:1512. (in Korean) doi:10.3390/s24051512

10.3390/s2405151238475048PMC10935418
13

Kim S.H., P. Tripathi, S. Yu, J.M. Park, J.D. Lee, Y.S. Chung, G. Chung, and Y. Kim 2021, Selection of tolerant and susceptible wild soybean (Glycine soja Siebold & Zucc.) accessions under waterlogging condition using vegetation indices. Pol J Environ Stud 30:3659-3675. (in Korean) doi:10.15244/pjoes/132257

10.15244/pjoes/130491
14

Li L., Q. Zhang, and D. Huang 2014, A review of imaging techniques for plant phenotyping. Sensors 14:20078-20111. doi:10.3390/s141120078

10.3390/s14112007825347588PMC4279472
15

Ministry of Agriculture, Food and Rural Affairs. 2023, Major Statistics 2023. Ministry of Agriculture, Food and Rural Affairs.

16

Mishra P., M.S. Mohd Asaari, A. Herrero-Langreo, S. Lohumi, B. Diezma, and P. Scheunders 2017, Close range hyperspectral imaging of plants: A review. Biosyst Eng 164:49-67. doi:10.1016/j.biosystemseng.2017.09.009

10.1016/j.biosystemseng.2017.09.009
17

Mo C., M. Kim, G. Kim, J. Lim, S. Delwiche, K. Chao, H. Lee, and B. Cho 2017, Spatial assessment of soluble solid contents on apple slices using hyperspectral imaging. Biosyst Eng 159:10-21. doi:10.1016/j.biosystemseng.2017.04.010

10.1016/j.biosystemseng.2017.04.010
18

Na S.I., C.W. Park, K.H. So, H.Y. Ahn, and K.D. Lee 2019, Photochemical reflectance index (PRI) mapping using drone-based hyperspectral image for evaluation of crop stress and its application to multispectral imagery. Korean J Remote Sens 35:637-647. (in Korean)

19

Ou C., Z. Jia, S. Sun, J. Liu, W. Ma, J. Wang, C. Mi, and P. Mao 2024, Using machine learning methods combined with vegetation indices and growth indicators to predict seed yield of bromus inermis. Plants 13:773; doi:10.3390/plants13060773.

10.3390/plants1306077338592838PMC10974845
20

Ryu J.H., D. Oh, S.W. Jang, H. Jeong, K.H. Moon, and J. Cho 2018, Assessment of photochemical reflectance index measured at different spatial scales utilizing leaf reflectometer, field hyper-spectrometer, and multi-spectral camera with UAV. Korean J Remote Sens 34:1055-1066. (in Korean)

21

Seo D., K.C. Kim, M. Lee, K.D. Kwon, and G. Kim 2021, Research on Tomato Flowers and Fruits Object Detection Model in Greenhouse Environment Using Deep Learning. J Kor Inst Commun Inform Sci 46:2072-2077. (in Korean) doi:10.7840/kics. 2021.46.11.2072

10.7840/kics.2021.46.11.2072
22

Shin M.H., K.E. Jang, S.K. Lee, J.G. Cho, S.J. Song, and J.G. Kim 2022, Grading of Harvested 'Mihwang' Peach Maturity with Convolutional Neural Network. J Bio-Env Con 31:270-278. (in Korean) doi:10.12791/KSBEC.2022.31.4.270

10.12791/KSBEC.2022.31.4.270
23

Shin Y.H., J.H. Park, and M.S. Park 2003, Spectral reflectance characteristics and vegetation indices of field crops. KCID Journal 10:43-54.

24

Song A., W. Jeon, and Y. Kim 2017, Study of Prediction Model Improvement for Apple Soluble Solids Content Using a Ground-based Hyperspectral Scanner. Korean J Remote Sens 33:559-570. (in Korean) doi:10.7780/kjrs.2017.33.5.1.9

25

Steele M.R., A.A. Gitelson, D.C. Rundquist, and M.N. Merzlyak 2009, Nondestructive estimation of anthocyanin content in grapevine leaves. Am J Enol Vitic 60:87-92. https://digitalcommons.unl.edu/natrespapers/283

10.5344/ajev.2009.60.1.87
26

Stellacci A., A. Castrignano, A. Troccoli, B. Basso, and G. Buttafuoco 2016, Selecting optimal hyperspectral bands to discriminate nitrogen status in durum wheat: A comparison of statistical approaches. Environ Monit Assess 188:199. doi.org/10.1007/s10661-016-5168-4

10.1007/s10661-016-5171-026922749
27

Wang F., C. Zhao, H. Yang, H. Jiang, L. Li, and G. Yang 2022, Non-destructive and in-site estimation of apple quality and maturity by hyperspectral imaging. Comput Electron Agric 195:106843. doi.org/10.1016/j.compag.2022.106843

10.1016/j.compag.2022.106843
28

Wendel A., and J. Underwood 2017, Illumination compensation in ground based hyperspectral imaging. ISPRS J Photogramm Remote Sens 129:162-178.

10.1016/j.isprsjprs.2017.04.010
29

Wendel A., J. Underwood, and K. Walsh 2018, Maturity estimation of mangoes using hyperspectral imaging from a ground-based mobile platform. Comput Electron Agric 155:298-313. doi:10.1016/j.compag.2018.10.021

10.1016/j.compag.2018.10.021
30

Yoon J.B., Y.N. Yoon, and Y.H. Kim 2021, Utilization of Vegetation Indices in the Agricultural Field. J Agric Life Sci 55:1-9. (in Korean) doi:10.14397/jals.2021.55.5.1

10.14397/jals.2021.55.5.1
Information
  • Publisher :The Korean Society for Bio-Environment Control
  • Publisher(Ko) :(사)한국생물환경조절학회
  • Journal Title :Journal of Bio-Environment Control
  • Journal Title(Ko) :생물환경조절학회지
  • Volume : 33
  • No :4
  • Pages :340-351
  • Received Date : 2024-07-17
  • Revised Date : 2024-10-18
  • Accepted Date : 2024-10-21
  • DOI :https://doi.org/10.12791/KSBEC.2024.33.4.340
Journal Informaiton Journal of Bio-Environment Control Journal of Bio-Environment Control
Online Submission
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crossref funder-registry
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close