An Automatic Non-Destructive Method for the Classification of the Ripeness Stage of Red Delicious Apples in Orchards Using Aerial Video

摘要: The estimation of the ripening state in orchards helps improve post-harvest processes. Picking fruits based on their stage maturity can reduce cost storage and increase market outcomes. Moreover, aerial images estimated ripeness be used as indicators for detecting water stress determining applied during irrigation. Additionally, they also related to crop coefficient (Kc) seasonal needs. purpose this research is develop a new computer vision algorithm detect existing an apple cultivar (of Red Delicious variety) estimate among four possible classes: unripe, half-ripe, ripe, overripe. proposed method combination most effective color features classifier artificial neural networks optimized with genetic algorithms. obtained results indicate average classification accuracy 97.88%, over dataset 8390 27,687 apples, values area under ROC (receiver operating characteristic) curve near or above 0.99 all classes. We believe remarkable performance that allows proper non-intrusive will help harvesting strategies.