Food Image Recognition by Deep Learning

Abstract/Technology Overview

The goal of this project is to recognize food photos automatically using machine learning techniques, with a focus of recognizing popular local food dishes in Singapore. Food image recognition can be very useful for addressing many real needs of a smart nation, particularly for wellness and healthcare applications. One example is to apply food image recognition technologies for smart food logging so as to recognize the nutrition of daily food intakes in order to promote a healthy lifestyle, which is crucial for our aging society.

Technology Features, Specifications and Advantages

The proposed Artificial Intelligence (AI) technology consists of a series of food image recognition solutions and API services, including but not limited to: 

1) Automated food image recognition for popular local foods in Singapore;

2) API services for applying food image recognition in web & mobile apps;

3) Automated calculation of nutrition (such as calories) based on food photos.

Potential Applications

This technology applies to the following industries:

Wellness & Healthcare

  • Smart food logging for healthy food consumption by tracking the nutrition of food consumed
  • Medical dieting control for patients with chronic conditions, such as diabetes, heart disease, and high cholesterol
  • Food recommendation services in F&B industry to encourage a healthy lifestyle

Technology Owner

Lydia Tan


Living Analytics Research Centre, Singapore Management University

Technology Category
  • Healthcare
  • Artificial Intelligence
  • Healthcare ICT
  • Smart Cities
  • Video/Image Analysis
Technology Status
  • Available for Licensing
Technology Readiness Level
  • TRL 8

food, image recognition, deep learning, nutrition tracking, Artificial Intelligence, AI