Leveraging Context to Support Automated Food Recognition in Restaurants

TL;DR

This paper presents a method that combines restaurant context and computer vision to improve automated food recognition from photos taken in real-world restaurant settings.

Contribution

It introduces a novel approach that leverages online restaurant data and visual recognition to accurately identify foods in unconstrained environments.

Findings

High accuracy in recognizing foods across diverse restaurant types

Effective use of online menu data to enhance recognition

Robust performance in real-world, unconstrained settings

Abstract

The pervasiveness of mobile cameras has resulted in a dramatic increase in food photos, which are pictures reflecting what people eat. In this paper, we study how taking pictures of what we eat in restaurants can be used for the purpose of automating food journaling. We propose to leverage the context of where the picture was taken, with additional information about the restaurant, available online, coupled with state-of-the-art computer vision techniques to recognize the food being consumed. To this end, we demonstrate image-based recognition of foods eaten in restaurants by training a classifier with images from restaurant's online menu databases. We evaluate the performance of our system in unconstrained, real-world settings with food images taken in 10 restaurants across 5 different types of food (American, Indian, Italian, Mexican and Thai).