Food Image Generation Using a Large Amount of Food Images with Conditional GAN: ramenGAN and recipeGAN
Abstract
Recently, image generation by Deep Convolutional Neural Network has been studied widely by many researchers. In this paper, we describe CNN-based image generation on food images. Especially, we focus on image generation using conditional Generative Adversarial Network (cGAN) with a large-scale dataset. In the experiments, we trained cGAN with a "ramen" image dataset and a recipe image dataset. For "ramen"GAN, we added a dish plate discriminator to make the shape of dishes rounder in generated images. For "recipe"GAN, we generated dish images from cooking ingredients, and tried image-based recipe search with generated images for the recipe database.
Cite
Text
Ito et al. "Food Image Generation Using a Large Amount of Food Images with Conditional GAN: ramenGAN and recipeGAN." International Joint Conference on Artificial Intelligence, 2018. doi:10.1145/3230519.3230598Markdown
[Ito et al. "Food Image Generation Using a Large Amount of Food Images with Conditional GAN: ramenGAN and recipeGAN." International Joint Conference on Artificial Intelligence, 2018.](https://mlanthology.org/ijcai/2018/ito2018ijcai-food/) doi:10.1145/3230519.3230598BibTeX
@inproceedings{ito2018ijcai-food,
title = {{Food Image Generation Using a Large Amount of Food Images with Conditional GAN: ramenGAN and recipeGAN}},
author = {Ito, Yoshifumi and Shimoda, Wataru and Yanai, Keiji},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2018},
pages = {71-74},
doi = {10.1145/3230519.3230598},
url = {https://mlanthology.org/ijcai/2018/ito2018ijcai-food/}
}