Picture-to-Amount (PITA): Predicting Relative Ingredient Amounts from Food Images
This addresses a novel and challenging problem in food analysis for health and lifestyle applications, though it appears incremental as it builds on existing cross-modal embedding methods.
The paper tackles the problem of predicting relative ingredient amounts from food images, which is crucial for accurate nutrition estimation, and proposes the PITA deep learning architecture that uses a domain-driven Wasserstein loss to improve baselines on this task.
Increased awareness of the impact of food consumption on health and lifestyle today has given rise to novel data-driven food analysis systems. Although these systems may recognize the ingredients, a detailed analysis of their amounts in the meal, which is paramount for estimating the correct nutrition, is usually ignored. In this paper, we study the novel and challenging problem of predicting the relative amount of each ingredient from a food image. We propose PITA, the Picture-to-Amount deep learning architecture to solve the problem. More specifically, we predict the ingredient amounts using a domain-driven Wasserstein loss from image-to-recipe cross-modal embeddings learned to align the two views of food data. Experiments on a dataset of recipes collected from the Internet show the model generates promising results and improves the baselines on this challenging task. A demo of our system and our data is availableat: foodai.cs.rutgers.edu.