René Gislum

Viability Prediction of Ricinus cummunis L. Seeds Using Multispectral Imaging

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

Viability Prediction of Ricinus cummunis L. Seeds Using Multispectral Imaging. / Olesen, Merete Halkjær; Nikneshan, Pejman; Shrestha, Santosh; Tadayyon, Ali; Deleuran, Lise Christina; Boelt, Birte; Gislum, René.

In: Sensors, Vol. 15, No. 2, 2015, p. 4592-4604.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

Olesen, MH, Nikneshan, P, Shrestha, S, Tadayyon, A, Deleuran, LC, Boelt, B & Gislum, R 2015, 'Viability Prediction of Ricinus cummunis L. Seeds Using Multispectral Imaging' Sensors, vol. 15, no. 2, pp. 4592-4604. https://doi.org/10.3390/s150204592

APA

Olesen, M. H., Nikneshan, P., Shrestha, S., Tadayyon, A., Deleuran, L. C., Boelt, B., & Gislum, R. (2015). Viability Prediction of Ricinus cummunis L. Seeds Using Multispectral Imaging. Sensors, 15(2), 4592-4604. https://doi.org/10.3390/s150204592

CBE

Olesen MH, Nikneshan P, Shrestha S, Tadayyon A, Deleuran LC, Boelt B, Gislum R. 2015. Viability Prediction of Ricinus cummunis L. Seeds Using Multispectral Imaging. Sensors. 15(2):4592-4604. https://doi.org/10.3390/s150204592

MLA

Vancouver

Olesen MH, Nikneshan P, Shrestha S, Tadayyon A, Deleuran LC, Boelt B et al. Viability Prediction of Ricinus cummunis L. Seeds Using Multispectral Imaging. Sensors. 2015;15(2):4592-4604. https://doi.org/10.3390/s150204592

Author

Olesen, Merete Halkjær ; Nikneshan, Pejman ; Shrestha, Santosh ; Tadayyon, Ali ; Deleuran, Lise Christina ; Boelt, Birte ; Gislum, René. / Viability Prediction of Ricinus cummunis L. Seeds Using Multispectral Imaging. In: Sensors. 2015 ; Vol. 15, No. 2. pp. 4592-4604.

Bibtex

@article{611262aba4424c46aced70fe1e659e8c,
title = "Viability Prediction of Ricinus cummunis L. Seeds Using Multispectral Imaging",
abstract = "The purpose of this study was to highlight the use of multispectral imaging in seed quality testing of castor seeds. Visually, 120 seeds were divided into three classes: yellow, grey and black seeds. Thereafter, images at 19 different wavelengths ranging from 375–970 nm were captured of all the seeds. Mean intensity for each single seed was extracted from the images, and a significant difference between the three colour classes was observed, with the best separation in the near-infrared wavelengths. A specified feature (RegionMSI mean) based on normalized canonical discriminant analysis, were employed and viable seeds were distinguished from dead seeds with 92{\%} accuracy. The same model was tested on a validation set of seeds. These seeds were divided into two groups depending on germination ability, 241 were predicted as viable and expected to germinate and 59 were predicted as dead or non-germinated seeds. This validation of the model resulted in 96{\%} correct classification of the seeds. The results illustrate how multispectral imaging technology can be employed for prediction of viable castor seeds, based on seed coat colour.",
keywords = "multispectral imaging, castor seed, canonical discriminant analysis (CDA), viability, germination",
author = "Olesen, {Merete Halkj{\ae}r} and Pejman Nikneshan and Santosh Shrestha and Ali Tadayyon and Deleuran, {Lise Christina} and Birte Boelt and Ren{\'e} Gislum",
year = "2015",
doi = "10.3390/s150204592",
language = "English",
volume = "15",
pages = "4592--4604",
journal = "Sensors",
issn = "1424-8220",
publisher = "M D P I AG",
number = "2",

}

RIS

TY - JOUR

T1 - Viability Prediction of Ricinus cummunis L. Seeds Using Multispectral Imaging

AU - Olesen, Merete Halkjær

AU - Nikneshan, Pejman

AU - Shrestha, Santosh

AU - Tadayyon, Ali

AU - Deleuran, Lise Christina

AU - Boelt, Birte

AU - Gislum, René

PY - 2015

Y1 - 2015

N2 - The purpose of this study was to highlight the use of multispectral imaging in seed quality testing of castor seeds. Visually, 120 seeds were divided into three classes: yellow, grey and black seeds. Thereafter, images at 19 different wavelengths ranging from 375–970 nm were captured of all the seeds. Mean intensity for each single seed was extracted from the images, and a significant difference between the three colour classes was observed, with the best separation in the near-infrared wavelengths. A specified feature (RegionMSI mean) based on normalized canonical discriminant analysis, were employed and viable seeds were distinguished from dead seeds with 92% accuracy. The same model was tested on a validation set of seeds. These seeds were divided into two groups depending on germination ability, 241 were predicted as viable and expected to germinate and 59 were predicted as dead or non-germinated seeds. This validation of the model resulted in 96% correct classification of the seeds. The results illustrate how multispectral imaging technology can be employed for prediction of viable castor seeds, based on seed coat colour.

AB - The purpose of this study was to highlight the use of multispectral imaging in seed quality testing of castor seeds. Visually, 120 seeds were divided into three classes: yellow, grey and black seeds. Thereafter, images at 19 different wavelengths ranging from 375–970 nm were captured of all the seeds. Mean intensity for each single seed was extracted from the images, and a significant difference between the three colour classes was observed, with the best separation in the near-infrared wavelengths. A specified feature (RegionMSI mean) based on normalized canonical discriminant analysis, were employed and viable seeds were distinguished from dead seeds with 92% accuracy. The same model was tested on a validation set of seeds. These seeds were divided into two groups depending on germination ability, 241 were predicted as viable and expected to germinate and 59 were predicted as dead or non-germinated seeds. This validation of the model resulted in 96% correct classification of the seeds. The results illustrate how multispectral imaging technology can be employed for prediction of viable castor seeds, based on seed coat colour.

KW - multispectral imaging

KW - castor seed

KW - canonical discriminant analysis (CDA)

KW - viability

KW - germination

U2 - 10.3390/s150204592

DO - 10.3390/s150204592

M3 - Journal article

VL - 15

SP - 4592

EP - 4604

JO - Sensors

JF - Sensors

SN - 1424-8220

IS - 2

ER -