Food Recognition using Transfer Learning

This paper proposes the application of Transfer Learning in classifying a food dish. Traditional methods involve using Artificial Neural Networks (ANN) and Convolutional Neural Networks (CNN), which are highly inefficient when the classes in a dataset increase. Therefore, more modern ways of classification become vital to adapt to evolving human tastes. Thus, we have achieved excellent results by leveraging Neural Networks in the form of ResNet, VGG19, EfficientNet, and DenseNet. Additionally, a web crawler has been integrated to provide the recipe for the same dish.