บทคัดย่องานวิจัย

Predicting the maturity of oranges with non destructive sensors.

Steinmetz, V.; Biavati, E.; Molto, E.; Pons, R.; Fornes, I.;

Acta Horticulturae Year: 1998 Issue: No. 421 Pages: 271-278 Ref: 7 ref.

1998

บทคัดย่อ

Predicting the maturity of oranges with non destructive sensors.

Various sensors were tested to predict the maturity of oranges for postharvest sorting. Nondestructive sensors, such as a vision system, firmness sensor, and near-infrared sensor, were used and reference measurements were made for sugar content, acidity, size and weight. A panel of 3 experts provided 3 classifications for fruits depending on their aspect. A total of 320 oranges (cv. Salustiana) were tested with the sensors. Neural network techniques provided better results than multiple linear regression for predicting maturity. The vision system was very useful for detecting defects and for colour evaluation. Combining the various sensors for the prediction of maturity index remains a difficult task. One major constraint is the acidity level which cannot be predicted using low-cost nondestructive sensors.