Comparison of portable spectral imaging (443–726 nm) and RGB imaging for predicting poultry product “use-by” status through packaging film
The objective of this study is to compare portable visible spectral imaging (443–726 nm) and conventional RGB imaging for detecting products stored beyond the recommended “use-by” date and predicting the number of days poultry products have been stored. Packages of chicken thighs with skin on were s...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IM Publications Open
2021-10-01
|
| Series: | Journal of Spectral Imaging |
| Subjects: | |
| Online Access: | https://www.impopen.com/jsi-abstract/I10_a6 |
| _version_ | 1818723206805061632 |
|---|---|
| author | Anastasia Swanson Ana Herrero-Langreo Aoife Gowen |
| author_facet | Anastasia Swanson Ana Herrero-Langreo Aoife Gowen |
| author_sort | Anastasia Swanson |
| collection | DOAJ |
| description | The objective of this study is to compare portable visible spectral imaging (443–726 nm) and conventional RGB imaging for detecting products stored beyond the recommended “use-by” date and predicting the number of days poultry products have been stored. Packages of chicken thighs with skin on were stored at 4 °C and imaged daily in pack through plastic lidding film using spectral and RGB imaging over 10 days. K-nearest neighbour (KNN) models were built to detect poultry stored beyond its recommended “use-by” date and partial least squares regression (PLSR) models were built to predict the storage day of samples. Model overfitting in the spectral PLSR model was prevented using a geostatistical approach to estimate the number of latent variables (LV). All models were built at the object level by using mean spectra and colour values per image. The KNN model built using spectral images (acc. = 93 %, sen. = 75 %, spec. = 100 %) was more suitable than the model built using RGB images (acc. = 80 %, sen. = 42 %, spec. = 96 %) for detecting poultry stored beyond its “use-by” date. The PLSR model built using spectral images (R2 = 0.78 RMSEC = 0.92, RMSEV = 1.11, RMSEP = 1.34 day) was more suitable than the model built using RGB images (R2 = 0.60, RMSEC = 1.66, RMSEV = 1.67, RMSEP = 1.92 day) for predicting storage day of poultry products. |
| first_indexed | 2024-12-17T21:06:50Z |
| format | Article |
| id | doaj.art-fe0df5cad55144ba952129eb212357b1 |
| institution | Directory Open Access Journal |
| issn | 2040-4565 |
| language | English |
| last_indexed | 2024-12-17T21:06:50Z |
| publishDate | 2021-10-01 |
| publisher | IM Publications Open |
| record_format | Article |
| series | Journal of Spectral Imaging |
| spelling | doaj.art-fe0df5cad55144ba952129eb212357b12022-12-21T21:32:34ZengIM Publications OpenJournal of Spectral Imaging2040-45652021-10-0110a610.1255/jsi.2021.a6Comparison of portable spectral imaging (443–726 nm) and RGB imaging for predicting poultry product “use-by” status through packaging filmAnastasia Swanson0https://orcid.org/0000-0002-3642-1793Ana Herrero-Langreo1https://orcid.org/0000-0003-3258-6248Aoife Gowen2https://orcid.org/0000-0002-9494-2204UCD School of Biosystems and Food Engineering, University College Dublin, Belfield, Dublin 4, IrelandUCD School of Biosystems and Food Engineering, University College Dublin, Belfield, Dublin 4, IrelandUCD School of Biosystems and Food Engineering, University College Dublin, Belfield, Dublin 4, IrelandThe objective of this study is to compare portable visible spectral imaging (443–726 nm) and conventional RGB imaging for detecting products stored beyond the recommended “use-by” date and predicting the number of days poultry products have been stored. Packages of chicken thighs with skin on were stored at 4 °C and imaged daily in pack through plastic lidding film using spectral and RGB imaging over 10 days. K-nearest neighbour (KNN) models were built to detect poultry stored beyond its recommended “use-by” date and partial least squares regression (PLSR) models were built to predict the storage day of samples. Model overfitting in the spectral PLSR model was prevented using a geostatistical approach to estimate the number of latent variables (LV). All models were built at the object level by using mean spectra and colour values per image. The KNN model built using spectral images (acc. = 93 %, sen. = 75 %, spec. = 100 %) was more suitable than the model built using RGB images (acc. = 80 %, sen. = 42 %, spec. = 96 %) for detecting poultry stored beyond its “use-by” date. The PLSR model built using spectral images (R2 = 0.78 RMSEC = 0.92, RMSEV = 1.11, RMSEP = 1.34 day) was more suitable than the model built using RGB images (R2 = 0.60, RMSEC = 1.66, RMSEV = 1.67, RMSEP = 1.92 day) for predicting storage day of poultry products.https://www.impopen.com/jsi-abstract/I10_a6portable spectral imagingk-nearest neighbour (knn)partial least squares regression (plsr)poultry“use-by”plastic lidding film |
| spellingShingle | Anastasia Swanson Ana Herrero-Langreo Aoife Gowen Comparison of portable spectral imaging (443–726 nm) and RGB imaging for predicting poultry product “use-by” status through packaging film Journal of Spectral Imaging portable spectral imaging k-nearest neighbour (knn) partial least squares regression (plsr) poultry “use-by” plastic lidding film |
| title | Comparison of portable spectral imaging (443–726 nm) and RGB imaging for predicting poultry product “use-by” status through packaging film |
| title_full | Comparison of portable spectral imaging (443–726 nm) and RGB imaging for predicting poultry product “use-by” status through packaging film |
| title_fullStr | Comparison of portable spectral imaging (443–726 nm) and RGB imaging for predicting poultry product “use-by” status through packaging film |
| title_full_unstemmed | Comparison of portable spectral imaging (443–726 nm) and RGB imaging for predicting poultry product “use-by” status through packaging film |
| title_short | Comparison of portable spectral imaging (443–726 nm) and RGB imaging for predicting poultry product “use-by” status through packaging film |
| title_sort | comparison of portable spectral imaging 443 726 nm and rgb imaging for predicting poultry product use by status through packaging film |
| topic | portable spectral imaging k-nearest neighbour (knn) partial least squares regression (plsr) poultry “use-by” plastic lidding film |
| url | https://www.impopen.com/jsi-abstract/I10_a6 |
| work_keys_str_mv | AT anastasiaswanson comparisonofportablespectralimaging443726nmandrgbimagingforpredictingpoultryproductusebystatusthroughpackagingfilm AT anaherrerolangreo comparisonofportablespectralimaging443726nmandrgbimagingforpredictingpoultryproductusebystatusthroughpackagingfilm AT aoifegowen comparisonofportablespectralimaging443726nmandrgbimagingforpredictingpoultryproductusebystatusthroughpackagingfilm |