Hyperspectral imaging coupled with multivariate analysis and artificial intelligence to the classification of maize kernels
More details
Hide details
Department of Biosystems Engineering, University of Mohaghegh Ardabili, Ardabil 56199-11367, Iran
Institute of Sciences and Technologies for Sustainable Energy and Mobility, National Research Council (STEMS-CNR), Via Canal Bianco 28, 44124 Ferrara, Italy
Faculty of Production and Power Engineering, University of Agriculture in Kraków, Balicka 116B, 30-149 Kraków, Poland
Institute of Agrophysics, Polish Academy of Sciences, Doświadczalna 4, 20-290 Lublin, Poland
Faculty of Agriculture, University of South Bohemia in České Budějovice, Studentská 1668, 370 05 České Budějovice, Czech Republic
Faculty of Engineering, Slovak University of Agriculture in Nitra, Hlinku 2, 949 76 Nitra, Slovakia
Final revision date: 2022-02-13
Acceptance date: 2022-03-08
Publication date: 2022-04-07
Corresponding author
Marek Gancarz
Int. Agrophys. 2022, 36(2): 83-91
  • Hyperspectral imaging system can quickly classify maize cultivars using LDA methods.
  • Length and width a single kernel did not affect the cultivars classification significantly.
  • Discrimination accuracy decreases with the lower number of predictor variables.
  • Non-destructive hyperspectral imaging can used with the weight and dimensions measurement.
Maize (Zea mays) is one of the key crops in the world, taking third place after wheat and rice in terms of cultivated area. This study aimed to demonstrate the potential of non-destructive hyperspectral imaging in the wavelength range of 400-1000 nm to discriminate between and classify maize kernels in three cultivars by using non-destructive hyperspectral imaging in the wavelength range of 400-1000 nm. Three cultivars of maize kernels were exposed to hyperspectral imaging with 20 replications. Predictor variables included 28 intensities of reflection wave for spectral imaging and 4 variables in terms of the weight, length, width, and thickness of a single kernel. The classification was successfully performed through Linear Discriminant Analysis and Artificial Neural Network methods, taking into account 32, 15, and 5 predictor variables. According to the results, Linear Discriminant Analysis with 32 predictor variables is characterized by a high degree of accuracy (95%). The most important predictor variables included the reflection wave intensity of the third peak, the wavelength intensity of 490 nm, the wavelength intensity of 580 nm, and the weight and thickness of a single kernel.
The authors declare that there is no conflict of interest regarding the publication of this paper.
Alsalem M., Salehi A., Zhao J., Rewald B., and Bodner G., 2021. Combining image analyses tools for comprehensive characterization of root systems from soil-filled rhizobox phenotyping platforms. Int. Agrophys., 35(3), 257-268,
Anjos O., Campos M.G., Ruiz P.C., and Antunes P., 2015. Application of FTIR-ATR spectroscopy to the quantification of sugar in honey. Food Chem., 169, 218-223,
Bajus P., Mraz M., Rigo I., Findura P., Fürstenzeller A., Kielbasa P., and Malaga-Tobola U., 2019. The influence of drying temperature and moisture of corn seeds planted on their damage. Agric. Engin., 23(1), 5-12,
Bauriegel E., Giebel A., and Herppich W.B., 2011. Hyperspectral and chlorophyll fluorescence imaging to analyse the impact of Fusarium culmorum on the photosynthetic integrity of infected wheat ears. Sensors, 11(4), 3765-3779,
Cheng J.-H. and Sun D.-W., 2015. Rapid quantification analysis and visualization of Escherichia coli loads in grass carp fish flesh by hyperspectral imaging method. Food Bioproc. Technol., 8(5), 951-959,
Cheng J.-H., Sun D.-W., Pu H., and Zeng X.-A., 2014. Comparison of visible and long-wave near-infrared hyperspectral imaging for colour measurement of grass carp (Ctenopharyngodon idella). Food Bioproc. Technol., 7(11), 3109-3120,
Combrzyński M., Oniszczuk T., Kupryaniuk K., Wójtowicz A., Mitrus M., Milanowski M., Soja J., Budziak-Wieczorek I., Karcz D., Kamiński D., Kulesza S., Wojtunik-Kulesza K., Kasprzak-Drozd K., Gancarz M., Kowalska I., Ślusarczyk L., and Matwijczuk A., 2021. Physical properties, spectroscopic, microscopic, x-ray, and chemometric analysis of starch films enriched with selected functional additives. Materials, 14, 2673,
Delwiche S.R., Souza E.J., and Kim M.S.,2013. Limitations of single kernel near-infrared hyperspectral imaging of soft wheat for milling quality. Bios. Engin., 115(3), 260-273,
de Araújo Gomes A., Schenone A.V., Goicoechea H.C., and de Araújo M.C.U., 2015. Unfolded partial least squares/residual bilinearization combined with the Successive Projections Algorithm for interval selection: enhanced excitation-emission fluorescence data modeling in the presence of the inner filter effect. Anal. Bioanal. Chem., 407(19), 5649-5659,
Dziki D., Tarasiuk W., Łysiak G., and Jochymek P., 2020. The study of particle size distribution of micronized oat bran layer. Agric. Engin., 24(2), 45-54,
ElMasry G., Iqbal A., Sun D.-W., Allen P., and Ward P., 2011. Quality classification of cooked, sliced turkey hams using NIR hyperspectral imaging system. J. Food Engin., 103(3), 333-344,
ElMasry G., Sun D.-W. and Allen P., 2012. Near-infrared hyperspectral imaging for predicting colour, pH and tenderness of fresh beef. J. Food Engin., 110(1), 127-140,
Gowen A.A., O'Donnell C.P., Cullen P.J., Downey G. and Frias J.M., 2007. Hyperspectral imaging - an emerging process analytical tool for food quality and safety control. Trends Food Sci. Technol., 18(12), 590-598,
Harris D., Rashid A., Miraj G., Arif M., and Shah H., 2007. 'On-farm' seed priming with zinc sulphate solution - A cost-effective way to increase the maize yields of resource-poor farmers. Field Crops Res., 102(2), 119-127,
Huang M., Zhao W., Wang Q., Min Z., and Zhu Q., 2015. Prediction of moisture content uniformity using hyperspectral imaging technology during the drying of maize kernel. Int. Agrophys., 29(1), 39-46,
Hu M.-H., Dong Q.-L., Liu B.-L., and Opara U.L., 2016. Prediction of mechanical properties of blueberry using hyperspectral interactance imaging. Postharvest Biol. Technol., 115, 122-131,
Jackman P., Sun D.-W., Du C.-J., Allen P., and Downey G., 2008. Prediction of beef eating quality from colour, marbling and wavelet texture features. Meat Sci., 80, 1273-81,
Kamruzzaman M., ElMasry G., Sun D.-W., and Allen P., 2011. Application of NIR hyperspectral imaging for discrimination of lamb muscles. J. Food Engin., 104(3), 332-340,
Kamruzzaman M., ElMasry G., Sun D.-W., and Allen P., 2012. Prediction of some quality attributes of lamb meat using near-infrared hyperspectral imaging and multivariate analysis. Anal. Chim. Acta, 714, 57-67,
Kapela K., Sikorska A., Niewęgłowski M., Krasnodębska E., Zarzecka K., and Gugała M., 2020. The impact of nitrogen fertilization and the use of biostimulants on the yield of two maize varieties (Zea mays L.) cultivated for grain. Agronomy, 10,(9), 1408,
Karami H., Rasekh M., and Mirzaee-Ghaleh E., 2020a. Comparison of chemometrics and AOCS official methods for predicting the shelf life of edible oil. Chemom. Intell. Lab. Syst., 206, 104165,
Karami H., Rasekh M., and Mirzaee-Ghaleh E., 2020b. Qualitative analysis of edible oil oxidation using an olfactory machine. J. Food Meas. Charact., 14(5), 2600-2610,
Karami H., Rasekh M., and Mirzaee-Ghaleh E., 2020c. Application of the E-nose machine system to detect adulterations in mixed edible oils using chemometrics methods. J. Food Meas. Charact., 44(9), e14696,
Karami H., Rasekh M., and Mirzaee-Ghaleh E., 2021. Identification of olfactory characteristics of edible oil during storage period using metal oxide semiconductor sensor signals and ANN methods. J. Food Proc, Preserv., 45(10), e15749,
Khorramifar A., Rasekh M., Karami H., Malaga-Toboła U., and Gancarz M., 2021. A machine learning method for classification and identification of potato cultivars based on the reaction of MOS type sensor-array. Sensors, 21(17), 5836,
Khorsand A., Rezaverdinejad V., Asgarzadeh H., Majnooni-Heris A., Rahimi A., and Besharat S., 2020. Response of maize and black gram yield and water productivity to variation in canopy temperature and crop water stress index. Int. Agrophys., 34(3), 381-390,
Lei Z., Zeng Y., Liu P., and Su X., 2021. Active deep learning for hyperspectral image classification with uncertainty learning. IEEE Geoscience and Remote Sensing Letters, 1-5,
Benthien J., Heldner S., Seppke B., and Hörbelt J., 2020. Comparison of two techniques of pattern recognition in the image analysis-based wheat stalk length characterization. Agric. Engin., 24(2), 1-8,
Liu W., Zeng S., Wu G., Li H., and Chen F., 2021. Rice seed purity identification technology using hyperspectral image with LASSO logistic regression model. Sensors, 21(13), 4384,
Pekel A.Y., Çalık A., Kuter E., Alataş M.S., Öklen S.B., Kızıl A., Bulat M., and Cengiz Ö., 2020. Impact of chemical and physical properties on flowability characteristics of corn distillers dried grains with solubles. Int. Agrophys., 34(2), 195-202,
Rasekh M. and Karami H., 2021a. E-nose coupled with an artificial neural network to detection of fraud in pure and industrial fruit juices. Int. J. Food Propert., 24(1), 592-602,
Rasekh M. and Karami H., 2021b. Application of electronic nose with chemometrics methods to the detection of juices fraud. J. Food Proc. Preserv., 45(2), e15432,
Rasekh M., Karami H., Wilson A.D., and Gancarz M., 2021a. Classification and identification of essential oils from herbs and fruits based on a mos electronic-nose technology. Chemosensors, 9(6), 142,
Rasekh M., Karami H., Wilson A.D., and Gancarz M., 2021b. Performance analysis of mau-9 electronic-nose mos sensor array components and ann classification methods for discrimination of herb and fruit essential oils. Chemosensors, 9(9), 243,
Sellami A. and Tabbone S., 2022. Deep neural networks-based relevant latent representation learning for hyperspectral image classification. Pattern Recognit., 121, 108224,
Sun J., Jiang S., Mao H., Wu X., and Li Q., 2016. Classification of black beans using visible and near infrared hyperspectral imaging. Int. J. Food Propert., 19(8), 1687-1695,
Tan D., Guo L., Liu J., Fan Y., and Li Q., 2020. Response of dry matter translocation and grain yield of summer maize to biodegradable film in the North China plain. Int. Agrophys., 34(1), 87-94,
Tatli S., Mirzaee-Ghaleh E., Rabbani H., Karami H., and Wilson A.D., 2020. Rapid detection of urea fertilizer effects on voc emissions from cucumber fruits using a MOS E-Nose Sensor Array. Agronomy, 12, 35,
Valous N.A., Mendoza F., Sun D.-W., and Allen P., 2009. Colour calibration of a laboratory computer vision system for quality evaluation of pre-sliced hams. Meat Sci., 81(1), 132-141,
Wang Q.G., Zhu Q.B., Qin J.W., and Huang G., 2015. Review of seed quality and safety tests using optical sensing technologies. Seed Sci. Technol., 43, 3, 337-366,
Williams P.J. and Kucheryavskiy S., 2016. Classification of maize kernels using NIR hyperspectral imaging. Food Chem., 209, 131-138,
Wu D., Sun D.-W., and He Y., 2012. Application of long-wave near infrared hyperspectral imaging for measurement of color distribution in salmon fillet. Innov. Food Sci. Emerg. Technol., 16, 361-372,
Yang X., Hong H., You Z., and Cheng F., 2015. Spectral and image integrated analysis of hyperspectral data for waxy corn seed variety classification. Sensors, 15(7), 15578-15594,
Yuan Y., Wang C., and Jiang Z., 2021. Proxy-based deep learning framework for spectral-spatial hyperspectral image classification: efficient and robust. IEEE Trans. Geosci. Remote Sens., 1-15,
Zhang X., Liu F., He Y., and Li X., 2012. Application of hyperspectral imaging and chemometric calibrations for variety discrimination of maize seeds. Sensors, 12(12), 17234-17246,
Journals System - logo
Scroll to top