A system to help amateurs take pictures of delicious looking food

Takao Kakimori, Makoto Okabe, Keiji Yanai, Rikio Onai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Recently, many people have begun to take pictures of meals and food either at home or in restaurants. These pictures are then uploaded to social networking services (SNS) where they are shared with friends. People want to take pictures of food that looks delicious, but they often find this difficult. This is because most people lack the knowledge required to take attractive pictures. There are many photography techniques in use, e.g., composition [1], lighting, color, focus, etc. The techniques used to take good pictures vary depending on the subject. Amateur photographers find it difficult to choose techniques and apply them appropriately. In this paper, we consider the composition of food photographs and develop a system to support amateurs taking pictures of meals and food to make the food look delicious. Our target users are food photography amateurs. Our target photographic subjects are food items on plates or dishes. Using our system, there are four steps to food photography: 1) the user provides information about the foods to be photographed, or our system automatically recognizes these food items, with the aid of a camera on a mobile phone, 2) our system suggests a composition and camera tilt that will result in a picture that makes the food look delicious, 3) the user arranges the food and dishes on the table, and sets the camera position and tilt, 4) finally, the user takes the picture. If the user is not satisfied with the suggestion, we allow the user to design a new composition quickly and easily using their mobile phone. We performed a usability study for our system followed by a subjective evaluation of the quality of the pictures taken using our system.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE 2nd International Conference on Multimedia Big Data, BigMM 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages456-461
Number of pages6
ISBN (Electronic)9781509021789
DOIs
Publication statusPublished - 2016 Aug 16
Externally publishedYes
Event2nd IEEE International Conference on Multimedia Big Data, BigMM 2016 - Taipei, Taiwan, Province of China
Duration: 2016 Apr 202016 Apr 22

Other

Other2nd IEEE International Conference on Multimedia Big Data, BigMM 2016
Country/TerritoryTaiwan, Province of China
CityTaipei
Period16/4/2016/4/22

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Media Technology

Fingerprint

Dive into the research topics of 'A system to help amateurs take pictures of delicious looking food'. Together they form a unique fingerprint.

Cite this