A method with neural networks for the classification of fruits and vegetables

In this paper, a novel method for the classification of fruits and vegetables is introduced. This technique is divided into two parts, the electronic nose and classification method. First, an electronic nose is designed with an arduino microcontroller and with some electronic sensors to obtain real data of the smells of fruits or vegetables. Second, a classification method is introduced with a neural network to detect between three kinds of objects: fruits or vegetables. The introduced strategy is validated by three experiments with the adaline, multilayer, and radial basis function neural networks.