UEC-Ramen555 is a ramen image dataset that has 555 ramen images. Each image has segmentation mask of ramen attributes.
The semantic mask consists of 11 classes of pixel-level semantic labels that are manually annotated. And 5 additional soup category label annotations are included.
The ramen image semantic label contains semantic labels for the background, bowl, soup, spoon, chopsticks and toppings (e.g. half-cut egg, seaweed, sliced roast pork, etc.). Soup category labels include salt soup, soy sauce soup, miso soup, pork bone soup and spicy soup.
| Name | RGB | |
|---|---|---|
| 0 | 'background' | 0,0,0 |
| 1 | 'bowl' | 226,128,128 |
| 2 | 'soup' | 64,32,32 |
| 3 | 'spoon' | 255,0,0 |
| 4 | 'chopsticks' | 255,191,0 |
| 5 | 'cut_egg' | 127,255,0 |
| 6 | 'egg' | 0,255,63 |
| 7 | 'seaweed' | 0,255,255 |
| 8 | 'meat' | 0,63,255 |
| 9 | 'menma' | 127,0,255 |
| 10 | 'naruto' | 255,0,191 |
| Name | |
|---|---|
| 0 | 'salt' |
| 1 | 'soysauce' |
| 2 | 'miso' |
| 3 | 'porkbone' |
| 4 | 'spicy' |
UEC-Ramen555 dataset can be used only for non-commercial research purpose.
If you publish a paper using our dataset, we'd glad if you could refer to the following paper:
@inproceedings{ramenasyoulike2019,
title={Ramen as You Like: Sketch-based Food Image Generation and Editing},
author={Cho, Jaehyeong and Shimoda, Wataru and Yanai, Keiji},
booktitle={ACM International Conference on Multimedia},
year={2019}
}Please feel free to contact us with any comments and questions by email.
(Jaehyeong Cho, Prof. Keiji Yanai)
Department of Informatics,
The University of Electro-Communications,
Tokyo, Japan