A Food Photography App with Image Recognition for Thai Food

Abstract

In this paper, we present a food photography application for smart phones, which can recognise 13 types of Thai food from photos. With this feature, the application can easily help users calculate their calories and make some suggestion, just by keep taking a photo of food they are eating. Our application uses React Native for the front-end, and Python-Flask for the back-end. For image recognition, we design a deep convolutional neural network to learn from our dataset. Moreover, we compare the result of our model with another model adapted from the famous one of Karen Simonyan andAndrew Zisserman called VGG19. We use transfer learning from the pre-trained VGG19, implementing with Keras and Tensorflow. Our result shows that the transfer learning model is better. It give us approximately 82% test accuracy or 18% top-1 error rate. Using top-3 and top-5 scores, The model reports 2.6% top-3 error rate and 1.3% top-5 error rate, which works well in our application.

Tasks

Reproductions