본문 바로가기
  • Home

Mobile Application based on Image Processing and a Proportion for Food Intake Measuring

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2017, 22(5), pp.57-63
  • DOI : 10.9708/jksci.2017.22.05.057
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : April 20, 2017
  • Accepted : May 12, 2017
  • Published : May 31, 2017

Kim, Do Hyeon 1 Kim, yoon 1 Han Yu Ri 1

1강원대학교

Accredited

ABSTRACT

In the paper, we propose a new reliable technique for measuring food intake based on image automatically without user intervention. First, food and bowl image before and after meal is obtained by user. The food and the bowl are divided into each region by the K-means clustering, Otsu algorithm, Morphology, etc. And the volume of food is measured by a proportional expression based on the information of the container such as it’s entrance diameter, depth, and bottom diameter. Finally, our method calculates the volume of the consumed food by the difference between before and after meal. The proposed technique has higher accuracy than existing method for measuring food intake automatically. The experiment result shows that the average error rate is up to 7% for three types of containers. Computer simulation results indicate that the proposed algorithm is a convenient and accurate method of measuring the food intake.

Citation status

* References for papers published after 2022 are currently being built.