Multispectral imaging for presymptomatic analysis of light leaf spot in oilseed rapeCitation formats

  • External authors:
  • Charles Veys
  • Fokion Chatziavgerinos
  • Ali Rashed Saeed A Bin Ghaith Alsuwaidi
  • James Hibbert
  • Mark Hansen
  • Gytis Bernotas
  • Melvyn Smith
  • Stephen Rolfe

Standard

Multispectral imaging for presymptomatic analysis of light leaf spot in oilseed rape. / Veys, Charles; Chatziavgerinos, Fokion; Bin Ghaith Alsuwaidi, Ali Rashed Saeed A; Hibbert, James; Hansen, Mark; Bernotas, Gytis; Smith, Melvyn; Yin, Hujun; Rolfe, Stephen; Grieve, Bruce.

In: Plant Methods, Vol. 15, No. 40, 4, 2019, p. 1-12.

Research output: Contribution to journalArticlepeer-review

Harvard

Veys, C, Chatziavgerinos, F, Bin Ghaith Alsuwaidi, ARSA, Hibbert, J, Hansen, M, Bernotas, G, Smith, M, Yin, H, Rolfe, S & Grieve, B 2019, 'Multispectral imaging for presymptomatic analysis of light leaf spot in oilseed rape', Plant Methods, vol. 15, no. 40, 4, pp. 1-12. https://doi.org/10.1186/s13007-019-0389-9

APA

Veys, C., Chatziavgerinos, F., Bin Ghaith Alsuwaidi, A. R. S. A., Hibbert, J., Hansen, M., Bernotas, G., Smith, M., Yin, H., Rolfe, S., & Grieve, B. (2019). Multispectral imaging for presymptomatic analysis of light leaf spot in oilseed rape. Plant Methods, 15(40), 1-12. [4]. https://doi.org/10.1186/s13007-019-0389-9

Vancouver

Veys C, Chatziavgerinos F, Bin Ghaith Alsuwaidi ARSA, Hibbert J, Hansen M, Bernotas G et al. Multispectral imaging for presymptomatic analysis of light leaf spot in oilseed rape. Plant Methods. 2019;15(40):1-12. 4. https://doi.org/10.1186/s13007-019-0389-9

Author

Veys, Charles ; Chatziavgerinos, Fokion ; Bin Ghaith Alsuwaidi, Ali Rashed Saeed A ; Hibbert, James ; Hansen, Mark ; Bernotas, Gytis ; Smith, Melvyn ; Yin, Hujun ; Rolfe, Stephen ; Grieve, Bruce. / Multispectral imaging for presymptomatic analysis of light leaf spot in oilseed rape. In: Plant Methods. 2019 ; Vol. 15, No. 40. pp. 1-12.

Bibtex

@article{afcaf26f54f648a29fc74277b3dde3ba,
title = "Multispectral imaging for presymptomatic analysis of light leaf spot in oilseed rape",
abstract = "Background: The use of spectral imaging within the plant phenotyping and breeding community has been increasing due its utility as a non-invasive diagnostic tool. However, there is a lack of imaging systems targeted specifically at plant science duties, resulting in low precision for canopy-scale measurements. This study trials a prototype multispectral system designed specifically for plant studies and looks at its use as an early detection system for visually asymptomatic disease phases, in this case Pyrenopeziza brassicae in Brassica napus. The analysis takes advantage of machine learning in the form of feature selection and novelty detection to facilitate the classification. An initial study into recording the morphology of the samples is also included to allow for further improvement to the system performance.Results: The proposed method was able to detect light leaf spot infection with 92% accuracy when imaging entire oilseed rape plants from above, 12 days after inoculation and 13 days before the appearance of visible symptoms. False colour mapping of spectral vegetation indices was used to quantify disease severity and its distribution within the plant canopy. In addition, the structure of the plant was recorded using photometric stereo, with the output influencing regions used for diagnosis. The shape of the plants was also recorded using photometric stereo, which allowed for reconstruction of the leaf angle and surface texture, although further work is needed to improve the fidelity due to uneven lighting distributions, to allow for reflectance compensation.Conclusions: The ability of active multispectral imaging has been demonstrated along with the improvement in time taken to detect light leaf spot at a high accuracy. The importance of capturing structural information is outlined, with its effect on reflectance and thus classification illustrated. The system could be used in plant breeding toenhance the selection of resistant cultivars, with its early and quantitative capability.",
keywords = "Disease detection, Light leaf spot, Oilseed rape, Multispectral, Preprocessing, Machine learning, Support vector machine, Novelty detection, Orientation effects, Photometric stereo",
author = "Charles Veys and Fokion Chatziavgerinos and {Bin Ghaith Alsuwaidi}, {Ali Rashed Saeed A} and James Hibbert and Mark Hansen and Gytis Bernotas and Melvyn Smith and Hujun Yin and Stephen Rolfe and Bruce Grieve",
year = "2019",
doi = "10.1186/s13007-019-0389-9",
language = "English",
volume = "15",
pages = "1--12",
journal = "Plant Methods",
issn = "1746-4811",
publisher = "Springer Nature",
number = "40",

}

RIS

TY - JOUR

T1 - Multispectral imaging for presymptomatic analysis of light leaf spot in oilseed rape

AU - Veys, Charles

AU - Chatziavgerinos, Fokion

AU - Bin Ghaith Alsuwaidi, Ali Rashed Saeed A

AU - Hibbert, James

AU - Hansen, Mark

AU - Bernotas, Gytis

AU - Smith, Melvyn

AU - Yin, Hujun

AU - Rolfe, Stephen

AU - Grieve, Bruce

PY - 2019

Y1 - 2019

N2 - Background: The use of spectral imaging within the plant phenotyping and breeding community has been increasing due its utility as a non-invasive diagnostic tool. However, there is a lack of imaging systems targeted specifically at plant science duties, resulting in low precision for canopy-scale measurements. This study trials a prototype multispectral system designed specifically for plant studies and looks at its use as an early detection system for visually asymptomatic disease phases, in this case Pyrenopeziza brassicae in Brassica napus. The analysis takes advantage of machine learning in the form of feature selection and novelty detection to facilitate the classification. An initial study into recording the morphology of the samples is also included to allow for further improvement to the system performance.Results: The proposed method was able to detect light leaf spot infection with 92% accuracy when imaging entire oilseed rape plants from above, 12 days after inoculation and 13 days before the appearance of visible symptoms. False colour mapping of spectral vegetation indices was used to quantify disease severity and its distribution within the plant canopy. In addition, the structure of the plant was recorded using photometric stereo, with the output influencing regions used for diagnosis. The shape of the plants was also recorded using photometric stereo, which allowed for reconstruction of the leaf angle and surface texture, although further work is needed to improve the fidelity due to uneven lighting distributions, to allow for reflectance compensation.Conclusions: The ability of active multispectral imaging has been demonstrated along with the improvement in time taken to detect light leaf spot at a high accuracy. The importance of capturing structural information is outlined, with its effect on reflectance and thus classification illustrated. The system could be used in plant breeding toenhance the selection of resistant cultivars, with its early and quantitative capability.

AB - Background: The use of spectral imaging within the plant phenotyping and breeding community has been increasing due its utility as a non-invasive diagnostic tool. However, there is a lack of imaging systems targeted specifically at plant science duties, resulting in low precision for canopy-scale measurements. This study trials a prototype multispectral system designed specifically for plant studies and looks at its use as an early detection system for visually asymptomatic disease phases, in this case Pyrenopeziza brassicae in Brassica napus. The analysis takes advantage of machine learning in the form of feature selection and novelty detection to facilitate the classification. An initial study into recording the morphology of the samples is also included to allow for further improvement to the system performance.Results: The proposed method was able to detect light leaf spot infection with 92% accuracy when imaging entire oilseed rape plants from above, 12 days after inoculation and 13 days before the appearance of visible symptoms. False colour mapping of spectral vegetation indices was used to quantify disease severity and its distribution within the plant canopy. In addition, the structure of the plant was recorded using photometric stereo, with the output influencing regions used for diagnosis. The shape of the plants was also recorded using photometric stereo, which allowed for reconstruction of the leaf angle and surface texture, although further work is needed to improve the fidelity due to uneven lighting distributions, to allow for reflectance compensation.Conclusions: The ability of active multispectral imaging has been demonstrated along with the improvement in time taken to detect light leaf spot at a high accuracy. The importance of capturing structural information is outlined, with its effect on reflectance and thus classification illustrated. The system could be used in plant breeding toenhance the selection of resistant cultivars, with its early and quantitative capability.

KW - Disease detection

KW - Light leaf spot

KW - Oilseed rape

KW - Multispectral

KW - Preprocessing

KW - Machine learning

KW - Support vector machine

KW - Novelty detection

KW - Orientation effects

KW - Photometric stereo

UR - http://www.scopus.com/inward/record.url?scp=85060455297&partnerID=8YFLogxK

U2 - 10.1186/s13007-019-0389-9

DO - 10.1186/s13007-019-0389-9

M3 - Article

VL - 15

SP - 1

EP - 12

JO - Plant Methods

JF - Plant Methods

SN - 1746-4811

IS - 40

M1 - 4

ER -