Towards automated sorting of Atlantic cod (Gadus morhua) roe, milt, and liver - Spectral characterization and classification using visible and near-infrared hyperspectral imaging
Technological solutions regarding automated sorting of food according to their quality parameters are of great interest to food industry. In this regard, automated sorting of fish rest raw materials remains as one of the key challenges for the whitefish industry. Currently, the sorting of roe, milt,...
Published in: | Food Control |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2016
|
Subjects: | |
Online Access: | http://hdl.handle.net/11250/2469160 https://doi.org/10.1016/j.foodcont.2015.11.004 |
id |
ftsintef:oai:sintef.brage.unit.no:11250/2469160 |
---|---|
record_format |
openpolar |
spelling |
ftsintef:oai:sintef.brage.unit.no:11250/2469160 2023-05-15T15:27:20+02:00 Towards automated sorting of Atlantic cod (Gadus morhua) roe, milt, and liver - Spectral characterization and classification using visible and near-infrared hyperspectral imaging Paluchowski, Lukasz A. Misimi, Ekrem Grimsmo, Leif Randeberg, Lise Lyngsnes 2016 application/pdf http://hdl.handle.net/11250/2469160 https://doi.org/10.1016/j.foodcont.2015.11.004 eng eng Norges forskningsråd: 225349 Food Control. 2016, 62 337-345. urn:issn:0956-7135 http://hdl.handle.net/11250/2469160 https://doi.org/10.1016/j.foodcont.2015.11.004 cristin:1324923 Navngivelse-Ikkekommersiell-DelPåSammeVilkår 4.0 Internasjonal http://creativecommons.org/licenses/by-nc-sa/4.0/deed.no the authors CC-BY-NC-SA 337-345 62 Food Control Journal article Peer reviewed 2016 ftsintef https://doi.org/10.1016/j.foodcont.2015.11.004 2021-08-04T11:59:53Z Technological solutions regarding automated sorting of food according to their quality parameters are of great interest to food industry. In this regard, automated sorting of fish rest raw materials remains as one of the key challenges for the whitefish industry. Currently, the sorting of roe, milt, and liver in whitefish fisheries is done manually. Automated sorting could enable higher profitability, flexibility in production and increase the potential for high value products from roe, milt and liver that can be used for human consumption. In this study, we investigate and present a solution for classification of Atlantic cod (Gadus morhua) roe, milt and liver using visible and near-infrared hyperspectral imaging. Recognition and classification of roe, milt and liver from fractions is a prerequisite to enabling automated sorting. Hyperspectral images of cod roe, milt and liver samples were acquired in the 400–2500 nm range and specific absorption peaks were characterized. Inter- and intra-variation of the materials were calculated using spectral similarity measure. Classification models operating on one and two optimal spectral bands were developed and compared to the classification model operating on the full VIS/NIR (400–1000 nm) range. Classification sensitivity of 70% and specificity of 94% for one-band model, and 96% and 98% for two-band model (sensitivity and specificity respectively) were achieved. Generated classification maps showed that sufficient discrimination between cod liver, roe and milt can be achieved using two optimal wavelengths. Classification between roe, milt and liver is the first step towards automated sorting. acceptedVersion Article in Journal/Newspaper atlantic cod Gadus morhua SINTEF Open (Brage) Food Control 62 337 345 |
institution |
Open Polar |
collection |
SINTEF Open (Brage) |
op_collection_id |
ftsintef |
language |
English |
description |
Technological solutions regarding automated sorting of food according to their quality parameters are of great interest to food industry. In this regard, automated sorting of fish rest raw materials remains as one of the key challenges for the whitefish industry. Currently, the sorting of roe, milt, and liver in whitefish fisheries is done manually. Automated sorting could enable higher profitability, flexibility in production and increase the potential for high value products from roe, milt and liver that can be used for human consumption. In this study, we investigate and present a solution for classification of Atlantic cod (Gadus morhua) roe, milt and liver using visible and near-infrared hyperspectral imaging. Recognition and classification of roe, milt and liver from fractions is a prerequisite to enabling automated sorting. Hyperspectral images of cod roe, milt and liver samples were acquired in the 400–2500 nm range and specific absorption peaks were characterized. Inter- and intra-variation of the materials were calculated using spectral similarity measure. Classification models operating on one and two optimal spectral bands were developed and compared to the classification model operating on the full VIS/NIR (400–1000 nm) range. Classification sensitivity of 70% and specificity of 94% for one-band model, and 96% and 98% for two-band model (sensitivity and specificity respectively) were achieved. Generated classification maps showed that sufficient discrimination between cod liver, roe and milt can be achieved using two optimal wavelengths. Classification between roe, milt and liver is the first step towards automated sorting. acceptedVersion |
format |
Article in Journal/Newspaper |
author |
Paluchowski, Lukasz A. Misimi, Ekrem Grimsmo, Leif Randeberg, Lise Lyngsnes |
spellingShingle |
Paluchowski, Lukasz A. Misimi, Ekrem Grimsmo, Leif Randeberg, Lise Lyngsnes Towards automated sorting of Atlantic cod (Gadus morhua) roe, milt, and liver - Spectral characterization and classification using visible and near-infrared hyperspectral imaging |
author_facet |
Paluchowski, Lukasz A. Misimi, Ekrem Grimsmo, Leif Randeberg, Lise Lyngsnes |
author_sort |
Paluchowski, Lukasz A. |
title |
Towards automated sorting of Atlantic cod (Gadus morhua) roe, milt, and liver - Spectral characterization and classification using visible and near-infrared hyperspectral imaging |
title_short |
Towards automated sorting of Atlantic cod (Gadus morhua) roe, milt, and liver - Spectral characterization and classification using visible and near-infrared hyperspectral imaging |
title_full |
Towards automated sorting of Atlantic cod (Gadus morhua) roe, milt, and liver - Spectral characterization and classification using visible and near-infrared hyperspectral imaging |
title_fullStr |
Towards automated sorting of Atlantic cod (Gadus morhua) roe, milt, and liver - Spectral characterization and classification using visible and near-infrared hyperspectral imaging |
title_full_unstemmed |
Towards automated sorting of Atlantic cod (Gadus morhua) roe, milt, and liver - Spectral characterization and classification using visible and near-infrared hyperspectral imaging |
title_sort |
towards automated sorting of atlantic cod (gadus morhua) roe, milt, and liver - spectral characterization and classification using visible and near-infrared hyperspectral imaging |
publishDate |
2016 |
url |
http://hdl.handle.net/11250/2469160 https://doi.org/10.1016/j.foodcont.2015.11.004 |
genre |
atlantic cod Gadus morhua |
genre_facet |
atlantic cod Gadus morhua |
op_source |
337-345 62 Food Control |
op_relation |
Norges forskningsråd: 225349 Food Control. 2016, 62 337-345. urn:issn:0956-7135 http://hdl.handle.net/11250/2469160 https://doi.org/10.1016/j.foodcont.2015.11.004 cristin:1324923 |
op_rights |
Navngivelse-Ikkekommersiell-DelPåSammeVilkår 4.0 Internasjonal http://creativecommons.org/licenses/by-nc-sa/4.0/deed.no the authors |
op_rightsnorm |
CC-BY-NC-SA |
op_doi |
https://doi.org/10.1016/j.foodcont.2015.11.004 |
container_title |
Food Control |
container_volume |
62 |
container_start_page |
337 |
op_container_end_page |
345 |
_version_ |
1766357777084579840 |