The combination of hyperspectral imaging with multivariate data analysis methods has recently been applied to develop a nondestructive technique, required to determine the seed viability of artificially aged vegetable and cereal seeds. In this study, the potential of shortwave infrared hyperspectral imaging to determine the viability of naturally aged seeds was investigated and thereafter a model for online seed sorting system was developed. The hyperspectral images of 400 Hinoki cypress tree seeds were acquired, and germination tests were conducted for viability confirmation, which indicated 31.5% of the viable seeds. Partial least square discriminant analysis models with 179 variables in the wavelength region of 1000–1800 nm were developed with a maximum model accuracy of 98.4% and 93.8% in both the calibration and validation sets, respectively. The partial least square discriminant analysis beta coefficient revealed the key wavelengths to differentiate viable from nonviable seeds, determined based on the differences in the chemical compositions of the seeds, including their lipid and fatty acid contents, which may control the germination ability of the seeds. The most effective wavelengths were selected using two model-based variable selection methods (i.e., the variable importance of projection (15 variables) and the successive projections algorithm (8 variables)) to develop the model. The successive projections algorithm wavelength selection method was considered to develop a viability model, and its application to the raw data resulted in a prediction accuracy of 94.7% in the calibration set and 92.2% in the validation set. These results demonstrate the potential of shortwave infrared hyperspectral imaging spectroscopy as a powerful nondestructive method to determine the viability of Hinoki cypress seeds. This method could be applied to develop an online seed sorting system for seed companies and nurseries.
HuangMTangJYangB, et al.
Classification of maize seeds of different years based on hyperspectral imaging and model updating. Comput Electron Agric2016;
122: 139–145.
2.
ZhangTWeiWZhaoB, et al.
A reliable methodology for determining seed viability by using hyperspectral data from two sides of wheat seeds. Sensors2018;
18: 813.
3.
DumontJHirvonenTHeikkinenV, et al.
Thermal and hyperspectral imaging for Norway spruce (Picea abies) seeds screening. Comput Electron Agric2015;
116: 118–124.
4.
WakholiCKandpalLMLeeH, et al.
Rapid assessment of corn seed viability using short wave infrared line-scan hyperspectral imaging and chemometrics. Sens Actuat B Chem2018;
255: 498–507.
5.
International Seed Testing Association.ISTA rules full issue.Int Rules Seed Test2015;
2015: 1–276.
6.
TigabuMOdenPERC.Simultaneous detection of filled, empty and insect-infested seeds of three Larix species with single seed near-infrared transmittance spectroscopy. New For2004;
27: 39–53.
7.
AhmedMRYasminJCollinsW, et al.
X-ray CT image analysis for morphology of muskmelon seed in relation to germination. Biosyst Eng2018;
175: 183–193.
8.
MohammedARYasminJCollinsW, et al.
Assessment of the morphological structure of watermelon and muskmelon seeds as related to viability. J Biosyst Eng2019;
44: 77–86.
9.
BrosnanTSunD-W.Inspection and grading of agricultural and food products by computer vision systems—a review.Comput Electron Agric2002;
36: 193–213.
10.
DuCJSunDW.Learning techniques used in computer vision for food quality evaluation: a review. J Food Eng2006;
72: 39–55.
11.
McCarthyWJKemenyGJ.Handbook of near-infrared analysis.
New York/Basel:
Marcel Dekker Inc., 2001, pp. 71–90.
12.
Esteve AgeletLHurburghCR.Limitations and current applications of near infrared spectroscopy for single seed analysis. Talanta2014;
121: 288–299.
13.
WorkmanLWeyerJ.Practical guide and spectral atlas for interpretive near-infrared spectroscopy. 2nd ed.Boca Raton, FL:
CRC Press, 2012.
14.
MoCLimJKwonSW, et al.
Hyperspectral imaging and partial least square discriminant analysis for geographical origin discrimination of white rice. J Biosyst Eng2017;
42: 293–300.
15.
WeinstockBAJanniJHagenL, et al.
Prediction of oil and oleic acid concentrations in individual corn (Zea mays L.) kernels using near-infrared reflectance hyperspectral imaging and multivariate analysis. Appl Spectrosc2006;
60: 9–16.
16.
QinJKimMSChaoK, et al.
Raman chemical imaging technology for food and agricultural applications. J Biosyst Eng2017;
42: 170–189.
LugueASalaGAlonsoA, et al.
Project of the “Ramon Areces” concentrated photovoltaic power station.Conf Rec IEEE Photovolt Spec Conf1978;
14: 1139–1114.
20.
WuDSunDW.Advanced applications of hyperspectral imaging technology for food quality and safety analysis and assessment: a review—part I: fundamentals.Innov Food Sci. Emerg Technol2013;
19: 1–14.
21.
MukasaPWakholiCMoC, et al.
Determination of viability of Retinispora (Hinoki cypress) seeds using FT-NIR spectroscopy.Infrared Phys Technol2019;
98: 62--68. DOI:10.1016/j.infrared.2019.02.008.
22.
HuangHLiuLNgadiMO, et al.
Rapid and non-invasive quantification of intramuscular fat content of intact pork cuts. Talanta2014;
119: 385–395.
23.
KandpalLMLeeHKimMS, et al.
Hyperspectral reflectance imaging technique for visualization of moisture distribution in cooked chicken breast. Sensors2013;
13: 13289–13300.
24.
LeeSHDoHSMinKJ.Effects of essential oil from Hinoki cypress, Chamaecyparis obtusa, on physiology and behavior of flies. PLoS One2015;
10: 1–14.
25.
LefcourtAMBeckEALoYM, et al.
Using hyperspectral fluorescence spectra of Deli commodities to select wavelengths for surveying Deli food contact surfaces. J Biosyst Eng2015;
40: 145–152.
26.
LohumiSLeeSLeeH, et al.
Application of hyperspectral imaging for characterization of intramuscular fat distribution in beef.Infrared Phys Technol2016;
74: 1–10.
27.
KandpalLMLohumiSKimMS, et al.
Near-infrared hyperspectral imaging system coupled with multivariate methods to predict viability and vigor in muskmelon seeds.Sens Actuat B Chem2016;
229: 534–544.
28.
SeoYLeeHBaeHJ, et al.
Optimized multivariate analysis for the discrimination of cucumber green mosaic mottle virus-infected watermelon seeds based on spectral imaging. J Biosyst Eng2019;
44: 95–102.
29.
KandpalLMLeeSKimMS, et al.
Short wave infrared (SWIR) hyperspectral imaging technique for examination of aflatoxin B1 (AFB1) on corn kernels. Food Control2014;
51: 171–176.
30.
MohammedARYasminJLeeWH, et al.
Imaging technologies for nondestructive measurement of internal properties of agricultural products: a review. J Biosyst Eng2017;
42: 199–216.
31.
LuZRiceAVasquezJ, et al. Target discrimination via optimal wavelength band selection with synthetic hyperspectral imagery. In: 2nd Work. Hyperspectral Image Signal Process Evol Remote Sensing, WHISPERS 2010—Work Progr IEEE, 2010, pp. 1–4. DOI: 10.1109/WHISPERS.2010.5594873.
32.
BajcsyPGrovesP.Methodology for hyperspectral band selection. Photogramm Eng Remote Sens2004;
70: 793–802.
33.
ElmasryGIqbalASunDW, et al.
Quality classification of cooked, sliced turkey hams using NIR hyperspectral imaging system. J Food Eng2011;
103: 333–344.
34.
WuDChenXShiP, et al.
Determination of α-linolenic acid and linoleic acid in edible oils using near-infrared spectroscopy improved by wavelet transform and uninformative variable elimination. Anal Chim Acta2009;
634: 166–171.
35.
MatsudaOHaraMTobitaH, et al.
Determination of seed soundness in conifers cryptomeria japonica and chamaecyparis obtusa using narrow-multiband spectral imaging in the short-wavelength infrared range. PLoS One2015;
10: 1–21.
ChenHSongQTangG, et al.
The combined optimization of Savitzky-Golay smoothing and multiplicative scatter correction for FT-NIR PLS models. ISRN Spectrosc2013;
2013: 1–9. DOI: 10.1155/2013/642190.
38.
BarnesRJDhanoaMSListerSJ.Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra. Appl Spectrosc1989;
43: 772–777.
39.
CandolfiADe MaesschalckRJouan-RimbaudD, et al.
The influence of data pre-processing in the pattern recognition of excipients near-infrared spectra. J Pharm Biomed Anal1999;
21: 115–132.
40.
OsborneBGFearnTHindlePT.Practical NIR spectroscopy with applications in food and beverage analysis.
Harlow, Essex, England:
Longman Scientific and Technical, 1993.
41.
LaschP.Spectral pre-processing for biomedical vibrational spectroscopy and microspectroscopic imaging.Chemom Intell Lab Syst2012;
117: 100–114.
42.
MalekiMRMouazenAMRamonH, et al.
Multiplicative scatter correction during on-line measurement with near infrared spectroscopy.Biosyst Eng2007;
96: 427–433.
43.
RinnanÅvan den BergFEngelsenSB.Review of the most common pre-processing techniques for near-infrared spectra.TrAC—Trends Anal Chem2009;
28: 1201–1222.
44.
VidalMAmigoJM.Pre-processing of hyperspectral images. Essential steps before image analysis.Chemom Intell Lab Syst2012;
117: 138–148.
45.
VarmuzaKFilzmoserP.Introduction to multivariate statistical analysis in chemometrics. CRC press, 2016. DOI: 10.1201/9781420059496.
46.
Galindo-PrietoBErikssonLTryggJ.Variable influence on projection (VIP) for OPLS models and its applicability in multivariate time series analysis.Chemom Intell Lab Syst2015;
146: 297–304.
47.
ShafferRE.Multi- and megavariate data analysis. Principles and applications, I. Eriksson, E. Johansson, N. Kettaneh-Wold and S. Wold, Umetrics Academy, Umeå, 2001, ISBN 91-973730-1-X, p. 533. J Chemom2002;
16(5): 261–262.
48.
WangLSunDWPuH, et al.
Application of hyperspectral imaging to discriminate the variety of maize seeds.Food Anal Methods2016;
9: 225–234.
49.
AraújoMCUSaldanhaTCBGalvãoRKH, et al.
The successive projections algorithm for variable selection in spectroscopic multicomponent analysis.Chemom Intell Lab Syst2001;
57: 65–73.
50.
FarhadiMTigabuMOdénPC.Near infrared spectroscopy as non-destructive method for sorting viable, petrified and empty seeds of Larix sibirica. Silva Fenn2015;
49: 1–12.
51.
Shenk JS, Workman JJ and Westerhaus MO. Application of NIR spectroscopy to agricultural products. Practical Spectroscopy Series 2001; 27: 419--474.
52.
WolffRLCompsBMarpeauAM, et al.
Taxonomy of Pinus species based on the seed oil fatty acid compositions.Trees—Struct Funct1997;
12: 113–118.
