Plant Hyperspectral Imaging

Abstract

Hyperspectral imaging can generate spatial chemical information in plants. The imaging acquisition system is basically composed of a radiation source, sample stage, objective lens, spectrograph, CCD camera and a computer to store and process derived data. Most hyperspectral imaging acquisition approaches are nondestructive in nature and require minimum sample preparation, thus producing chemically rich information without modifying a sample's features. Data processing is mainly performed via multivariate image analysis (MIA), where computedā€based methods are employed for preprocessing, feature extraction and multivariate analysis towards classification. Applications vary according to the desired information of interest, but they mainly include textural analysis, chemical and biochemical analysis and plant disease identification. Successful studies in these areas reinforce the sensitivity and versatility of hyperspectral imaging in plants.

Key Concepts

  • Hyperspectral imaging is a powerful tool for analysing plants.
  • Both spatial and spectral information are acquired via hyperspectral imaging, generating chemically rich information with spatial distribution.
  • Most hyperspectral imaging techniques are nondestructive in nature and require minimal sample preparation.
  • Data are processed by computationalā€based methods, in particular, by using multivariate image analysis (MIA) techniques for feature extraction and classification.
  • Hyperspectral imaging is a versatile analytical technique with many applications in plant studies, such as textural analysis, chemical and biochemical analysis and disease identification.

Keywords: plant analysis; hyperspectral imaging; multispectral imaging; multivariate image analysis (MIA); feature extraction; classification; spectroscopy; spatial chemical information

Figure 1. Illustration of hyperspectral image.
Figure 2. (a) Illustration of a hyperspectral imaging system; (b) imaging acquisition unit.
Figure 3. Illustration of processing steps for analysing a hyperspectral image.
Figure 4. (a) Image of a kiwi fruit acquired via hyperspectral NIR analysis (Zhu et al., ); (b) surface deformation for a round‐shaped object affecting the light scattering (Pu et al., ).
Figure 5. Commelina communis (C. communis) cells exposed to 0, 100 and 200 ppm of calcium, accompanied by hyperspectral pseudo‐colour images acquired in different wavenumber ranges of the fingerprint region (900–1800 cm−1).
close

References

AlSuwaidi A , Veyes C , Hussey M , et al. (2016) Hyperspectral Selection Based Algorithm for Plant Classification. 2016 IEEE International Conference on Imaging Systems and Techniques (IST), Chania, Greece, pp 395–400.

AlSuwaidi A , Grieve B and Yin H (2018) Combining spectral and texture features in hyperspectral image analysis for plant monitoring. Measurement Science and Technology 29 (10): 104001.

Ariana DP , Lu R and Guyer DE (2006) Near‐infrared hyperspectral reflectance imaging for detection of bruises on pickling cucumbers. Computers and Electronics in Agriculture 53 (1): 60–70.

Azaria I , Goldschleger N and Ben‐Dor E (2012) Identification of Cannabis plantations using hyperspectral technology. Israel Journal of Plant Sciences 60 (1–2): 77–83.

Baranowski P , Mazurek W and Pastuszka‐Woźniak J (2013) Supervised classification of bruised apples with respect to the time after bruising on the basis of hyperspectral imaging data. Postharvest Biology and Technology 86: 249–258.

Barron C , Parker ML , Mills ENC , Rouau X and Wilson RH (2005) FTIR imaging of wheat endosperm cell walls in situ reveals compositional and architectural heterogeneity related to grain hardness. Planta 220 (5): 667–677.

Bauriegel E and Herppich WB (2014) Hyperspectral and chlorophyll fluorescence imaging for early detection of plant diseases, with special reference to Fusarium spec. infections on wheat. Agriculture 4 (1): 32–57.

Bodner G , Nakhforoosh A , Arnold T , et al. (2018) Hyperspectral imaging: a novel approach for plant root phenotyping. Plant Methods 14: 84.

Chen J , Sun S and Zhou Q (2016) Chemical morphology of Areca nut characterized directly by Fourier transform near‐infrared and mid‐infrared microspectroscopic imaging in reflection modes. Food Chemistry 212: 469–475.

Cozzolino D and Roberts J (2016) Applications and developments on the use of vibrational spectroscopy imaging for the analysis, monitoring and characterisation of crops and plants. Molecules 21: 755.

Dixon SJ and Brereton RG (2009) Comparison of performance of five common classifiers represented as boundary methods: Euclidean distance to centroids, linear discriminant analysis, quadratic discriminant analysis, learning vector quantization and support vector machines, as dependent on data structure. Chemometrics and Intelligent Laboratory Systems 95 (1): 1–17. DOI: 10.1016/j.chemolab.2008.07.010.

Duchesne C , Liu JJ and MacGregor JF (2012) Multivariate image analysis in the process industries: a review. Chemometrics and Intelligent Laboratory Systems 117: 116–128.

Feng YZ and Sun DW (2012) Application of hyperspectral imaging in food safety inspection and control: a review. Critical Reviews in Food Science and Nutrition 52 (11): 1039–1058.

Gierlinger N , Keplinger T and Harrington M (2012) Imaging of plant cell walls by confocal Raman microscopy. Nature Protocols 7: 1694–1708.

Gilchrist JR and Hyvärinen T (2018) Hyperspectral Imaging Spectroscopy: A Look at Real‐Life Applications. Photonics Media. https://www.photonics.com/Articles/Hyperspectral_Imaging_Spectroscopy_A_Look_at/a25139.

Golhani K , Balasundram SK , Vadamalai G and Pradhan B (2018) A review of neural networks in plant disease detection using hyperspectral data. Information Processing in Agriculture 5: 354–371.

Gómez‐Sanchis J , Moltó E , Camps‐Valls G , et al. (2008) Automatic correction of the effects of the light source on spherical objects. An application to the analysis of hyperspectral images of citrus fruits. Journal of Food Engineering 85 (2): 191–200.

Haas J and Mizaikoff B (2016) Advances in mid‐infrared spectroscopy for chemical analysis. Annual Review of Analytical Chemistry 9: 45–68. DOI: 10.1146/annurev-anchem-071015-041507.

Hendra PJ and Stratton PM (1969) Laser‐Raman spectroscopy. Chemical Reviews 69 (3): 325–344. DOI: 10.1021/cr60259a003.

Heraud P , Cowan MF , Marzec KM , et al. (2018) Label‐free Raman hyperspectral imaging analysis localizes the cyanogenic glucoside dhurrin to the cytoplasm in sorghum cells. Scientific Reports 8: 2691.

Hillnhütter C , Mahlein AK , Sikora RA and Oerke EC (2011) Remote sensing to detect plant stress induced by Heterodera schachtii and Rhizoctonia solani in sugar beet fields. Field Crops Research 122 (1): 70–77.

Huang W , Lamb DW , Niu Z , et al. (2007) Identification of yellow rust in wheat using in‐situ spectral reflectance measurements and airborne hyperspectral imaging. Precision Agriculture 8 (4–5): 187–197.

Huang M , Wang Q , Zhang M , et al. (2014) Prediction of color and moisture content for vegetable soybean during drying using hyperspectral imaging technology. Journal of Food Engineering 128: 24–30.

Jiang Y and Li C (2015) Detection and discrimination of cotton foreign matter using push‐broom based hyperspectral imaging: system design and capability. PLoS One 10: e0121969.

Kalivas JH (2005) Multivariate calibration, an overview. Analytical Letters 38 (14): 2259–2279. DOI: 10.1080/00032710500315904.

Kersting K , Xu Z , Wahabzada M , et al. (2012) Pre‐Symptomatic Prediction of Plant Drought Stress Using Dirichlet‐Aggregation Regression on Hyperspectral Images. Proceedings of the Twenty‐Sixth AAAI Conference on Artificial Intelligence, AAAI Publications, pp 302–308.

Kim Y , Glenn DM , Park J , Ngugi HK and Lehman BL (2011) Hyperspectral image analysis for water stress detection of apple trees. Computers and Electronics in Agriculture 77: 155–160.

Kumar G and Bhatia PK (2014) A Detailed Review of Feature Extraction in Image Processing Systems. 2014 Fourth International Conference on Advanced Computing & Communication Technologies, Rohtak, 2014, pp 5–12. DOI: 10.1109/ACCT.2014.74.

Kumar A , Lee WS , Ehsani RJ , et al. (2012) Citrus greening disease detection using aerial hyperspectral and multispectral imaging techniques. Journal of Applied Remote Sensing 6 (1): 063542.

Kuska M , Wahabzada M , Leucker M , et al. (2015) Hyperspectral phenotyping on the microscopic scale: towards automated characterization of plant‐pathogen interactions. Plant Methods 11: 28.

Lee H , Kim MS , Song YR , et al. (2016) Non‐destructive evaluation of bacteria‐infected watermelon seeds using visible/near‐infrared hyperspectral imaging. Journal of the Science of Food and Agriculture 97 (4): 1084–1092.

Lee H , Kim MS , Qin J , et al. (2017) Raman hyperspectral imaging for detection of watermelon seeds infected with Acidovorax citrulli . Sensors 17 (10): 2188.

Li X and He Y (2006) Non‐destructive measurement of acidity of Chinese bayberry using Vis/NIRS techniques. European Food Research and Technology 223 (6): 731–736.

Lowe A , Harrison N and French AP (2017) Hyperspectral image analysis techniques for the detection and classification of the early onset of plant disease and stress. Plant Methods 13: 80.

Lu J , Ehsani R , Shi Y , de Castro AI and Wang S (2018) Detection of multi‐tomato leaf diseases (late blight, target and bacterial spots) in different stages by using a spectral‐based sensor. Scientific Reports 8: 2793.

Mahlein AM (2016) Plant disease detection by imaging sensors – parallels and specific demands for precision agriculture and plant phenotyping. Plant Disease 100 (2): 241–251.

Mahlein AK , Kuska MT , Thomas S , et al. (2017) Plant disease detection by hyperspectral imaging: from the lab to the field. Advances in Animal Biosciences 8 (2): 238–243.

Manley M , Williams P , Nilsson D and Geladi P (2009) Near infrared hyperspectral imaging for the evaluation of endosperm texture in whole yellow maize (Zea maize L.) kernels. Journal of Agricultural and Food Chemistry 57 (19): 8761–8769.

Mee CY , Balasundram SK and Hanif AHM (2017) Detecting and monitoring plant nutrient stress using remote sensing approaches: a review. Asian Journal of Plant Sciences 16: 1–8.

Mobaraki N and Amigo JM (2018) HYPER‐tools. A graphical user‐friendly interface for hyperspectral image analysis. Chemometrics and Intelligent Laboratory Systems 172: 174–187.

Moghadam P , Ward D , Goan E , et al. (2017) Plant Disease Detection Using Hyperspectral Imaging. 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Sydney, NSW, Australia, IEEE, pp 1–8.

Nagasubramanian K , Jones S , Sarkar S , et al. (2018) Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in soybean stems. Plant Methods 14: 86.

Pasquini C (2018) Near infrared spectroscopy: a mature analytical technique with new perspectives – a review. Analytica Chimica Acta 1026: 8–36. DOI: 10.1016/j.aca.2018.04.004.

Pérez‐Bueno ML , Pineda M , Cabeza FM and Barón M (2016) Multicolor Fluorescence imaging as a candidate for disease detection in plant phenotyping. Frontiers in Plant Science 7: 1790.

Pineda M , Pérez‐Bueno ML and Barón M (2018) Detection of bacterial infection in melon plants by classification methods based on imaging data. Frontiers in Plant Science 9: 164.

Polder G , van der Heijden GWAM , van Doorn J and Baltissen TAHMC (2014) Automatic detection of tulip breaking virus (TBV) in tulip fields using machine vision. Biosystems Engineering 117: 35–42.

Prats‐Mateu B , Felhofer M , de Juan A and Gierlinger N (2018) Multivariate unmixing approaches on Raman images of plant cell walls: new insights or overinterpretation of results? Plant Methods 14: 52.

Prats‐Montalbán JM , de Juan A and Ferrer A (2011) Multivariate image analysis: a review with applications. Chemometrics and Intelligent Laboratory Systems 107 (1): 1–23.

Pu YY , Feng YZ and Sun DW (2015) Recent progress of hyperspectral imaging on quality and safety inspection of fruits and vegetables: a review. Comprehensive Reviews in Food Science and Food Safety 14 (2): 176–188.

Ribeiro LP , Klock ALS , Wordell Filho JA , et al. (2018) Hyperspectral imaging to characterize plant–plant communication in response to insect herbivory. Plant Methods 14: 54.

Rinnan Å (2014) Pre‐processing in vibrational spectroscopy – when, why and how. Analytical Methods 6: 7124–7129. DOI: 10.1039/C3AY42270D.

Santos MCD , Morais CLM , Nascimento YM , et al. (2017) Spectroscopy with computational analysis in virological studies: a decade (2006–2016). Trends in Analytical Chemistry 97: 244–256.

Singh A , Ganapathysubramanian B , Singh AK and Sarkar S (2016) Machine learning for high‐throughput stress phenotyping in plants. Trends in Plant Science 21 (2): 110–124.

Soper SA , McGown LB and Warner IM (1994) Molecular fluorescence, phosphorescence, and chemiluminescence spectrometry. Analytical Chemistry 66 (12): 428–444. DOI: 10.1021/ac00084a016.

Su WH and Sun DW (2018) Multispectral imaging for plant food quality analysis and visualization. Comprehensive Reviews in Food Science and Food Safety 17 (1): 220–239.

Suárez L , Zarco‐Tejada PJ , Sepulcre‐Cantó G , et al. (2008) Assessing canopy PRI for water stress detection with diurnal airborne imagery. Remote Sensing of Environment 112 (2): 560–575.

Tissue BM (2012) Ultraviolet and Visible Absorption Spectroscopy. John Wiley & Sons. DOI: 10.1002/0471266965.com059.pub2.

Wahabzaba M , Mahlein AK , Bauckhage C , et al. (2015) Metro maps of plant disease dynamics – automated mining of differences using hyperspectral images. PLoS One 10 (1): e0116902.

Wang H , Qian X , Zhang L , et al. (2018) A method of high throughput monitoring crop physiology using chlorophyll fluorescence and multispectral imaging. Frontiers in Plant Science 9: 407.

Warren FJ , Perston BB , Galindez‐Najera SP , et al. (2015) Infrared microspectroscopic imaging of plant tissues: spectral visualization of Triticum aestivum kernel and Arabidopsis leaf microstructure. The Plant Journal 84: 634–646.

Yu KQ , Zhao YR , Li XL , et al. (2014) Hyperspectral imaging for mapping of total nitrogen spatial distribution in pepper plant. PLoS One 9 (12): e116205.

Zarco‐Tejada PJ , Miller JR , Morales A , Berjón A and Agüera J (2004) Hyperspectral indices and model simulation for chlorophyll estimation in open‐canopy tree crops. Remote Sensing of Environment 90 (4): 463–476.

Zhao YR , Li X , Yu KQ , Cheng F and He Y (2016) Hyperspectral imaging for determining pigment contents in cucumber leaves in response to angular leaf spot disease. Scientific Reports 6: 27790.

Zhu H , Chu B , Fan Y , et al. (2017a) Hyperspectral imaging for predicting the internal quality of kiwi fruits based on variable selection algorithms and chemometric models. Scientific Reports 7: 7845.

Zhu H , Chu B , Zhang C , et al. (2017b) Hyperspectral imaging for presymptomatic detection of tobacco disease with successive projections algorithm and machine‐learning classifiers. Scientific Reports 7: 4125.

Further Reading

Camargo A and Smith JS (2009) Image pattern classification for the identification of disease causing agents in plants. Computers and Electronics in Agriculture 66 (2): 121–125.

Chang CI (2003) Hyperspectral Imaging: Techniques for Spectral Detection and Classification. New York: Springer US.

Grahn HF and Geladi P (2007) Techniques and Applications of Hyperspectral Image Analysis. Chichester: John Wiley & Sons, Ltd.

Gupta SD and Ibaraki Y (2014) Plant Image Analysis: Fundamentals and Applications. New York: CRC Press.

Su DW (2010) Hyperspectral Imaging for Food Quality Analysis and Control. Cambridge, UK: Academic Press.

Wang L and Zhao C (2016) Hyperspectral Image Processing. New York: Springer‐Verlag Berlin Heidelberg.

Contact Editor close
Submit a note to the editor about this article by filling in the form below.

* Required Field

How to Cite close
Morais, Camilo LM, Butler, Holly J, McAinsh, Martin R, and Martin, Francis L(Mar 2019) Plant Hyperspectral Imaging. In: eLS. John Wiley & Sons Ltd, Chichester. http://www.els.net [doi: 10.1002/9780470015902.a0028367]