Fish fillet authentication by image analysis
The work aims at developing an image analysis procedure able to distinguish high value fillets of Atlantic cod (Gadus morhua) from those of haddock (Melanogrammus aeglefinus). The images of fresh G. morhua (n ¼ 90) and M. aeglefinus (n ¼ 91) fillets were collected by a flatbed scanner and processed...
Published in: | Journal of Food Engineering |
---|---|
Main Authors: | , , |
Other Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier
2018
|
Subjects: | |
Online Access: | http://hdl.handle.net/2434/573656 https://doi.org/10.1016/j.jfoodeng.2018.04.012 |
id |
ftunivmilanoair:oai:air.unimi.it:2434/573656 |
---|---|
record_format |
openpolar |
spelling |
ftunivmilanoair:oai:air.unimi.it:2434/573656 2024-02-11T10:01:58+01:00 Fish fillet authentication by image analysis Grassi, Silvia Casiraghi, Ernestina Alamprese, Cristina S. Grassi E. Casiraghi C. Alamprese 2018-10 http://hdl.handle.net/2434/573656 https://doi.org/10.1016/j.jfoodeng.2018.04.012 eng eng Elsevier info:eu-repo/semantics/altIdentifier/wos/WOS:000434887600002 volume:234 firstpage:16 lastpage:23 numberofpages:8 journal:JOURNAL OF FOOD ENGINEERING http://hdl.handle.net/2434/573656 doi:10.1016/j.jfoodeng.2018.04.012 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85047397950 info:eu-repo/semantics/openAccess authentication cod Haddock grey level co-occurrence matrix analysi linear discriminant analysis Settore AGR/15 - Scienze e Tecnologie Alimentari info:eu-repo/semantics/article 2018 ftunivmilanoair https://doi.org/10.1016/j.jfoodeng.2018.04.012 2024-01-23T23:33:58Z The work aims at developing an image analysis procedure able to distinguish high value fillets of Atlantic cod (Gadus morhua) from those of haddock (Melanogrammus aeglefinus). The images of fresh G. morhua (n ¼ 90) and M. aeglefinus (n ¼ 91) fillets were collected by a flatbed scanner and processed at different levels. Both untreated and edge-based segmented (Canny algorithm) regions of interest were submitted to surface texture evaluation by Grey Level Co-occurrence Matrix analysis. Twelve surface texture variables selected by Principal Component Analysis or by SELECT algorithm were then used to develop Linear Discriminant Analysis models. An average correct classification rate ranging from 86.05 to 92.31% was obtained in prediction, irrespective the use of raw or segmented images. These findings pave the way for a simple machine vision system to be implemented along fish market chain, in order to provide stakeholders with a simple, rapid and cost-effective system useful in fighting commercial frauds. Article in Journal/Newspaper atlantic cod Gadus morhua The University of Milan: Archivio Istituzionale della Ricerca (AIR) Journal of Food Engineering 234 16 23 |
institution |
Open Polar |
collection |
The University of Milan: Archivio Istituzionale della Ricerca (AIR) |
op_collection_id |
ftunivmilanoair |
language |
English |
topic |
authentication cod Haddock grey level co-occurrence matrix analysi linear discriminant analysis Settore AGR/15 - Scienze e Tecnologie Alimentari |
spellingShingle |
authentication cod Haddock grey level co-occurrence matrix analysi linear discriminant analysis Settore AGR/15 - Scienze e Tecnologie Alimentari Grassi, Silvia Casiraghi, Ernestina Alamprese, Cristina Fish fillet authentication by image analysis |
topic_facet |
authentication cod Haddock grey level co-occurrence matrix analysi linear discriminant analysis Settore AGR/15 - Scienze e Tecnologie Alimentari |
description |
The work aims at developing an image analysis procedure able to distinguish high value fillets of Atlantic cod (Gadus morhua) from those of haddock (Melanogrammus aeglefinus). The images of fresh G. morhua (n ¼ 90) and M. aeglefinus (n ¼ 91) fillets were collected by a flatbed scanner and processed at different levels. Both untreated and edge-based segmented (Canny algorithm) regions of interest were submitted to surface texture evaluation by Grey Level Co-occurrence Matrix analysis. Twelve surface texture variables selected by Principal Component Analysis or by SELECT algorithm were then used to develop Linear Discriminant Analysis models. An average correct classification rate ranging from 86.05 to 92.31% was obtained in prediction, irrespective the use of raw or segmented images. These findings pave the way for a simple machine vision system to be implemented along fish market chain, in order to provide stakeholders with a simple, rapid and cost-effective system useful in fighting commercial frauds. |
author2 |
S. Grassi E. Casiraghi C. Alamprese |
format |
Article in Journal/Newspaper |
author |
Grassi, Silvia Casiraghi, Ernestina Alamprese, Cristina |
author_facet |
Grassi, Silvia Casiraghi, Ernestina Alamprese, Cristina |
author_sort |
Grassi, Silvia |
title |
Fish fillet authentication by image analysis |
title_short |
Fish fillet authentication by image analysis |
title_full |
Fish fillet authentication by image analysis |
title_fullStr |
Fish fillet authentication by image analysis |
title_full_unstemmed |
Fish fillet authentication by image analysis |
title_sort |
fish fillet authentication by image analysis |
publisher |
Elsevier |
publishDate |
2018 |
url |
http://hdl.handle.net/2434/573656 https://doi.org/10.1016/j.jfoodeng.2018.04.012 |
genre |
atlantic cod Gadus morhua |
genre_facet |
atlantic cod Gadus morhua |
op_relation |
info:eu-repo/semantics/altIdentifier/wos/WOS:000434887600002 volume:234 firstpage:16 lastpage:23 numberofpages:8 journal:JOURNAL OF FOOD ENGINEERING http://hdl.handle.net/2434/573656 doi:10.1016/j.jfoodeng.2018.04.012 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85047397950 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.1016/j.jfoodeng.2018.04.012 |
container_title |
Journal of Food Engineering |
container_volume |
234 |
container_start_page |
16 |
op_container_end_page |
23 |
_version_ |
1790597860953161728 |