The increasingly normative severity and market competitiveness have led the agriculture sector and the food industry to constantly look for logic improvements that can be applied in processes monitoring systems. In a context where fast, non-destructive and reliable techniques are required, image analysis-based methods have gained interest, thanks to their ability to spatially characterize heterogeneous samples. In such a scenario, HyperSpectral Imaging (HSI) is an emerging technique that provides not only spatial information of imaging systems, but even spectral information of spectroscopy. The utilization of the HSI approach opens new interesting scenario to quality control logics in agricultural and food processing/manufacturing sectors. Three different case studies are presented in this paper. In particular, the utilization of an HSI system, working in SWIR range, was applied for: i) detecting contaminants in dried fruits to be packaged, ii) identifying olive fruits attacked by olive fruit flies and iii) recognizing flour type. In particular, the proposed approach is based on the application of Partial Least Squares – Discriminant Analysis (PLS-DA) classification method to HyperSpectral images in Short Wave InfraRed (SWIR) range (1000-2500 nm). The proposed case studies demonstrate that this logic can be successfully utilized as a quality control system on agri-food products coming from different manufacturing stages, but it can even be seen as an analytical core for sorting engines.
Hyperspectral imaging logics. Efficient strategies for agri-food products quality control / Bonifazi, Giuseppe; Gasbarrone, Riccardo; Serranti, Silvia. - (2019). (Intervento presentato al convegno 2019 UBT International conference tenutosi a Pristina, Kosovo) [10.33107/ubt-ic.2019.392].
Hyperspectral imaging logics. Efficient strategies for agri-food products quality control
Bonifazi, Giuseppe
;Gasbarrone, Riccardo;Serranti, Silvia
2019
Abstract
The increasingly normative severity and market competitiveness have led the agriculture sector and the food industry to constantly look for logic improvements that can be applied in processes monitoring systems. In a context where fast, non-destructive and reliable techniques are required, image analysis-based methods have gained interest, thanks to their ability to spatially characterize heterogeneous samples. In such a scenario, HyperSpectral Imaging (HSI) is an emerging technique that provides not only spatial information of imaging systems, but even spectral information of spectroscopy. The utilization of the HSI approach opens new interesting scenario to quality control logics in agricultural and food processing/manufacturing sectors. Three different case studies are presented in this paper. In particular, the utilization of an HSI system, working in SWIR range, was applied for: i) detecting contaminants in dried fruits to be packaged, ii) identifying olive fruits attacked by olive fruit flies and iii) recognizing flour type. In particular, the proposed approach is based on the application of Partial Least Squares – Discriminant Analysis (PLS-DA) classification method to HyperSpectral images in Short Wave InfraRed (SWIR) range (1000-2500 nm). The proposed case studies demonstrate that this logic can be successfully utilized as a quality control system on agri-food products coming from different manufacturing stages, but it can even be seen as an analytical core for sorting engines.File | Dimensione | Formato | |
---|---|---|---|
Bonifazi_Hyperspectral-imaging-logics_postprint_2019.pdf
solo gestori archivio
Note: Articolo accettato per la pubblicazione
Tipologia:
Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.22 MB
Formato
Adobe PDF
|
1.22 MB | Adobe PDF | Contatta l'autore |
Bonifazi_Hyperspectral-imaging-logics_2019.pdf
solo gestori archivio
Note: link: https://knowledgecenter.ubt-uni.net/conference/2019/events/392
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
557.42 kB
Formato
Adobe PDF
|
557.42 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.