Home // VISUAL 2022, The Seventh International Conference on Applications and Systems of Visual Paradigms // View article

Deep Learning-Based Food Identification and Calorie Estimation System

Authors:
Jung-Tang Huang
Chen-Hao Wang

Keywords: Image recognition; Volume estimate; Calorie estimates; Depth camera; Deep learning

Abstract:
This paper uses a depth camera for image recognition and calorie estimation of the food on the user's table, and uses more than 400 food photos as a database to train the yolov5 neural network to recognize the food on the table. Next, use the depth camera to estimate how many calories you have. For this experiment, more than 90% recognition rate can be obtained in most cases, while the heat estimation error is less than 10%.

Pages: 14 to 17

Copyright: Copyright (c) IARIA, 2022

Publication date: May 22, 2022

Published in: conference

ISSN: 2519-8645

ISBN: 978-1-61208-978-2

Location: Venice, Italy

Dates: from May 22, 2022 to May 26, 2022