At the University of Campinas' School of Food Engineering (FEA-UNICAMP) in Brazil, researchers are investigating how papayas could be harvested mechanically using algorithms and computer vision.
The researchers employed a portable sensor to light and analyze fruit on the tree, and by emitting a bright signal that was reflected by the fruit and captured for spectral analysis. Golden papayas were measured and weighed, and peel color determined via a colorimeter.
The team also analyzed physical and chemical characteristics of the fruit, and classified the samples into maturity stages based on pulp firmness.
FEA-UNICAMP's Douglas Fernandes Barbin says descriptive features of the fruit were fed into a random-forest decision tree algorithm to simulate the fruit ripeness classification system, and computational processing followed by statistical analysis of properties and features yielded indicators of pulp firmness for each fruit.
The non-invasive system had an accuracy rate of up to 94.7%, according to Barbin.
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found