Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

World Food Atlas Project

Ali Rostami, Z Xie, A Ishino, Y Yamakata, K Aizawa, Ramesh Jain

TL;DR

This paper addresses the challenge of building a global World Food Atlas that unifies food knowledge, nutrition data, and user dietary histories across cultures. It proposes a dual approach: a Food Knowledge Graph (FKG) that semantically links ingredients, recipes, and nutrition in a Neo4j-based graph, and two mobile apps, FoodLog Athl and RecipeLog, to collect home-food records and author recipes. The contributions include the design of the FKG backbone with Dooley ontology-backed ingredient hierarchies, integration of geographic and nutritional attributes, and the AI-assisted workflow for recording meals and recipes. Together, these efforts aim to enable personalized diet management, cultural-insight sharing, and scalable data-driven health guidance worldwide.

Abstract

A coronavirus pandemic is forcing people to be "at home" all over the world. In a life of hardly ever going out, we would have realized how the food we eat affects our bodies. What can we do to know our food more and control it better? To give us a clue, we are trying to build a World Food Atlas (WFA) that collects all the knowledge about food in the world. In this paper, we present two of our trials. The first is the Food Knowledge Graph (FKG), which is a graphical representation of knowledge about food and ingredient relationships derived from recipes and food nutrition data. The second is the FoodLog Athl and the RecipeLog that are applications for collecting people's detailed records about food habit. We also discuss several problems that we try to solve to build the WFA by integrating these two ideas.

World Food Atlas Project

TL;DR

This paper addresses the challenge of building a global World Food Atlas that unifies food knowledge, nutrition data, and user dietary histories across cultures. It proposes a dual approach: a Food Knowledge Graph (FKG) that semantically links ingredients, recipes, and nutrition in a Neo4j-based graph, and two mobile apps, FoodLog Athl and RecipeLog, to collect home-food records and author recipes. The contributions include the design of the FKG backbone with Dooley ontology-backed ingredient hierarchies, integration of geographic and nutritional attributes, and the AI-assisted workflow for recording meals and recipes. Together, these efforts aim to enable personalized diet management, cultural-insight sharing, and scalable data-driven health guidance worldwide.

Abstract

A coronavirus pandemic is forcing people to be "at home" all over the world. In a life of hardly ever going out, we would have realized how the food we eat affects our bodies. What can we do to know our food more and control it better? To give us a clue, we are trying to build a World Food Atlas (WFA) that collects all the knowledge about food in the world. In this paper, we present two of our trials. The first is the Food Knowledge Graph (FKG), which is a graphical representation of knowledge about food and ingredient relationships derived from recipes and food nutrition data. The second is the FoodLog Athl and the RecipeLog that are applications for collecting people's detailed records about food habit. We also discuss several problems that we try to solve to build the WFA by integrating these two ideas.

Paper Structure

This paper contains 8 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Food Knowledge Graph
  3. Detailed food record collection
  4. Food Logging App: FoodLog Athl
  5. Recipe Authoring App: RecipeLog
  6. discussion
  7. conclusion
  8. Acknowledgement

Figures (4)

  • Figure 1: Food Knowledge Graph aggregating and unifying food-related information from multiple offline and online sources.
  • Figure 2: Food Knowledge Graph representation in the Neo4j environment. B1136 is the general pork node and B1631 is the general pineapple node. This image shows the result of the query looking for food items which have both pork and pineapple as ingredients.
  • Figure 3: FoodLog Athl creates food records semi-automatically by recognizing images of food. It has the function of communicating with a nutritionist via chat.
  • Figure 4: The RecipeLog provides the function of authoring recipes. (a) Once the ingredients are entered, their nutritional value is visualized in a radar chart. (b) The ingredients are searched from the "standard tables of food composition" provided by the Ministry of Education, Culture, Sports, Science and Technology.