Recognition of Indonesian Traditional Cakes using The MobileNet Algorithm

Abstract

Indonesia is a country with a variety of cultures, ranging from dance to cuisine and food variations. Cake is one of the unique variations of food include traditional cake. A variety of custom-made cakes will make the taste special, even though the name is the same. Traditional cakes are foods that are part of the ancestral culture that has been passed down from generation to generation explicitly in the region or Indonesian society. Machine learning methods are suitable for consistent and clear object recognition, this requires complex image pre-processing and feature extraction methods. The proposed model of our research is MobileNetv2 which was customized and then we did fine tuning then all of our training datasets do data-augmentation to create new datasets with various patterns so that the train dataset can be more numerous and avoid overfitting and the model can detect cake differences with an accuracy rate of 94% and loss 0.06.