Olive Fruits Recognition Using Neural Networks

Abstract

A new method for olive fruit recognition is presented. Olive fruits size and weight are used for estimating the best harvesting moment of olive trees. Olive fruit recognition is performed by analyzing RGB images taken from olive trees. The harvesting decision comprehends two stages, the first stage focused on deciding whether or not the candidate identified in the picture corresponds to an olive fruit, and the second stage focused on olives overlapping in the pictures. The analyses required in these two stages are performed by implementing a neural networks solution approach.