Automatic Fruits Classification System Based on Deep Neural Network

Abstract

Fruit classification is playing a vital role in robot-based farming. The plucking of fruits and packing is done using robots nowadays. This could only be possible using efficiently trained robots base on machine learning. Different techniques have been developed for fruit classification, but still, there are many gaps, i.e., efficiency and accuracy. In this research work, we are targeting classification accuracy. This paper presented an Automatic Fruit Detection tool with good precision and recalled using deep learning neural networks. It will help in farming, cultivation, and produce sound effects in robotic farming. The aim is to build an accurate, fast and reliable fruit detection system, a vital element of an autonomous agricultural robotic platform; it is a crucial element for fruit yield estimation and automated harvesting. We used the ResNet-50 in the context of transfer learning. Different training choices were defined, i.e., 10% to 80%. Experimental results show that we compete for the prior approaches even on only 10% training. The proposed approach achieves state-of-the-art results compared to prior work with the F1 Score, which considers both precision and recall performances improving from 0.838 to 0.894 and 0.995 of accuracy. In addition to improved accuracy, this approach is also much quicker as compared to recent approaches.