L’analisi dell’immagine come metodologia per migliorare la fase di selezione dei prodotti alimentari

With increased expectations for high quality and safety foodstuffs, the need for an accurate, fast and objective quality determination of these characteristics in food products continues to grow. Computer vision provides one alternative for an automated, non-destructive and cost-effective technique to accomplish these requirements. This inspection approach based on image analysis and processing has found a variety of different applications in the food industry. Considerable research has highlighted its potential for the inspection and grading of fruits and vegetables and It has been successfully adopted for the quality analysis of meat and fish, cheese, bread, etc. The final purpose of this work is the implementation of artificial vision systems able to: detect defects related to dirt on the eggshell standard conditions; identify and separate aflatoxin contaminated pistachios and cashews; classify peaches (var. Rich Lady) into different postharvest maturity classes. In this work we present the results of the application of the proposed visual processes on a wide sample of both clean-dirt eggs, contaminated-uncontaminated nuts and on peach at different ripening states. Particular attention It was been payed to adaptability of the systems to on-line grading existing machines to detect and sort out dirt, contaminated and over-ripened samples. In this way, the food producers, processors and traders will be able to control every sample of the lot quickly and accurately, separating dirt, contaminated and over-ripened samples from the process streams, increasing the general food quality and safety.