Deep Cooking: Predicting Relative Food Ingredient Amounts from Images
This addresses a novel task in computer vision for food analysis, but it appears incremental as it builds on existing ingredient prediction methods.
The paper tackles the problem of predicting both ingredients and their relative amounts from food images, proposing two deep learning models that achieve encouraging results on a dataset of internet recipes.
In this paper, we study the novel problem of not only predicting ingredients from a food image, but also predicting the relative amounts of the detected ingredients. We propose two prediction-based models using deep learning that output sparse and dense predictions, coupled with important semi-automatic multi-database integrative data pre-processing, to solve the problem. Experiments on a dataset of recipes collected from the Internet show the models generate encouraging experimental results.