Fruit Maturity Recognition from Agricultural, Market and Automation Perspectives

원문 초록

Motivated by the potential reduction in the required manual efforts in the fruit industry, this paper attempts to automate fruit maturity recognition. We study the problem from the agricultural, market, and automation perspectives, often taken at different points in the supply chain. Since different maturity states have different visual characteristics, an image classification technology can certainly help here. To develop fruit image classifiers, we need a feature extraction method and a learning algorithm. We use different pre-trained neural networks for effective feature extraction and employ different machine learning algorithms while carrying out bias/variance analysis of the learned models. The analysis helps us select the best ones for each perspective under consideration. We achieve 96%, 94%, and 86% accuracies on our novel dataset named RipeRaw from the agricultural, market, and automation perspectives, respectively.