Abstract

Non-destructive evaluation of vegetables by Computer Vision Systems (CVSs) makes possible to check their quality level in an objective and consistent way along the whole supply chain up to the final users. CVSs have been proven to be successful when applied to unpackaged products.The proposed approach aimed to enable this analysis on packaged fresh-cut lettuce with minimum constraints on the acquisition phase and without any care to flatten the surface of the bag facing the camera. A deep-learning architecture, based on Convolutional Neural Networks (CNNs), was used to identify regions of the image where the vegetable was visible with minimum colour distortions due to packaging. To meaningfully assess the performance of the system, each lettuce's sample was acquired both through packaging material and without packaging material. The image analysis was applied to both the resulting images to automatically grade their quality level. The results showed that the performance loss due to the presence of packaging is negligible (83% instead of 86%) and that the proposed system can be used to monitor the quality level of fresh-cut lettuce regardless of packaging at all the critical check points along the supply chain.

Autore Pugliese

• Logrieco Antonio Francesco , Pace Bernardo , Cefola Maria , Attolico Giovanni

Tutti gli autori

• Cavallo D.P.; Cefola M.; Pace B.; Logrieco A.F.; Attolico G.

Titolo volume/Rivista

Journal of food engineering

Anno di pubblicazione

2017

ISSN

0260-8774

ISBN

Non Disponibile

Numero di citazioni Wos

Nessuna citazione

Ultimo Aggiornamento Citazioni

Non Disponibile

Numero di citazioni Scopus

Non Disponibile

Ultimo Aggiornamento Citazioni

Non Disponibile

Settori ERC

Non Disponibile

Codici ASJC

Non Disponibile