Food Ingredients Recognition through Multi-label Learning
This work addresses the need for automated food diary construction to support healthy diets, but it is incremental as it adapts existing CNN methods to a specific domain.
The paper tackles the problem of food ingredients recognition from images as a multi-label learning task, proposing a method that adapts a state-of-the-art CNN to predict ingredient lists from pictures, even for unseen recipes, and demonstrates generalization with high variability training.
Automatically constructing a food diary that tracks the ingredients consumed can help people follow a healthy diet. We tackle the problem of food ingredients recognition as a multi-label learning problem. We propose a method for adapting a highly performing state of the art CNN in order to act as a multi-label predictor for learning recipes in terms of their list of ingredients. We prove that our model is able to, given a picture, predict its list of ingredients, even if the recipe corresponding to the picture has never been seen by the model. We make public two new datasets suitable for this purpose. Furthermore, we prove that a model trained with a high variability of recipes and ingredients is able to generalize better on new data, and visualize how it specializes each of its neurons to different ingredients.