Picture-to-Amount (PITA): Predicting Relative Ingredient Amounts from Food Images

Abstract

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.

References in corpus (8)

• Distributed Representations of Words and Phrases and their Compositionality
• In Defense of the Triplet Loss for Person Re-Identification
• Learning with a Wasserstein Loss
• ChineseFoodNet: A large-scale Image Dataset for Chinese Food Recognition
• Mining Discriminative Food Regions for Accurate Food Recognition
• Computer vision-based food calorie estimation: dataset, method, and experiment
• Deep Cooking: Predicting Relative Food Ingredient Amounts from Images
• The Art of Food: Meal Image Synthesis from Ingredients

Cited by in corpus (1)

• Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning