Classification of Fruits using Image Processing and Deep Neural Networks

Fruits have shown a crucial role in our daily life. Fruits provide us rich resources for our food, pharmacy and industrial materials. The automatic classification of fruits using artificial intelligence and image processing has attracted a large number of researches. However, there exists a large number of species of fruits, the accurate classification of fruits is a challenging task. The paper presents a method for the classification of fruits using the Alexnet, Resnet-50 and MobileNetV3. We collect and normalize various fruit images for the training and testing the deep learning models. The accuracy of 90% and 92% the methods using Alexnet and Resnet-50 on various dataset has shown the potential application of the method in reality. Moreover, the application of the MobileNetV3 improves the execution time of the classification of fruit images.