4. Cycle-Generative Adversarial Network for Generating a Pseudo Realistic Food Dataset Using RGB and Depth Images

Obada Al aama1, Yuma Yoshimoto2, Hakaru Tamukoh2
1Department of Life Science and Systems Engineering, Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, 2-4 Hibikino, Wakamatsu-ku, Kitakyushu, 808-0196, Japan
2Department of Human Intelligence System, Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology,2-4 Hibikino, Wakamatsu-ku, Kitakyushu, 808-0196, Japan
pp. 128-133
ABSTRACT
Constructing a food dataset is time and effort consuming due to the requirement for covering the feature variations of food samples. Additionally, a large dataset is needed for training neural networks. Generative adversarial networks (GANs) are a recently developed technique to learn deep representations without extensively annotated training data. They can be used in several applications, including generating food datasets. This paper advocates the use of Cycle-GAN to generate a large pseudo-realistic food dataset based on a large number of simulated images and a small number of real images in comparison to traditional techniques. A single depth camera in three different angles and a turntable are arranged to capture real RGB-D images of food samples. 3D modeling software is used to generate simulated images using the same configuration of captured real images. Results showed that Cycle-GAN realistic style transfer on simulated food objects is achievable, and that it can be an efficient tool to minimize real image capturing efforts.

ARTICLE INFO
Article History
Received 25 November 2020
Accepted 25 February 2022

Keywords
Cycle-GAN
Food dataset
RGB-D images

JAALR2304

Download article(PDF)