Food 524 Database

Food524DB is the largest publicly available food dataset with 524 food classes and 247,636 images by merging food classes from existing datasets in the state of the art.

This database can be used for food recognition. The database is composed of 247,636 images belonging to 524 food categories. The database has been constructed by merging four benchmark datasets:  VIREO, Food-101, Food50, and a modified version of UECFOOD256.

Download Food524DB
  • To download the database information, follow this link:

      FOOD524DB.zip (1.5 MiB, 1,257 hits)

  • To download the modified UECFOOD256 dataset, follow this link: GDRIVE

If you use this database, please cite the following paper:

@inproceedings{ciocca2017Learning-CNN,
author = {Ciocca, Gianluigi and Napoletano, Paolo and 
Schettini, Raimondo},
editor="Battiato, Sebastiano and Farinella, Giovanni Maria and Leo, 
Marco and Gallo, Giovanni",
title="Learning CNN-based Features for Retrieval of Food Images",
bookTitle="New Trends in Image Analysis and Processing -- ICIAP 2017: 
ICIAP International Workshops, WBICV, SSPandBE, 3AS, RGBD, NIVAR, 
IWBAAS, and MADiMa 2017, Catania, Italy, September 11-15, 2017,
Revised Selected Papers",
year="2017",
publisher="Springer International Publishing",
pages="426--434",
isbn="978-3-319-70742-6",
doi="10.1007/978-3-319-70742-6_41"}

Publications

1.

CNN-based Features for Retrieval and Classification of Food Images
(Gianluigi Ciocca, Paolo Napoletano, Raimondo Schettini) In Computer Vision and Image Understanding, volume 176--177, pp. 70-77, Elsevier, 2018.

@article{ciocca2018cnn-based,
 author = {Ciocca, Gianluigi and Napoletano, Paolo and Schettini, Raimondo},
 year = {2018},
 pages = {70-77},
 title = {CNN-based Features for Retrieval and Classification of Food Images},
 volume = {176--177},
 publisher = {Elsevier},
 journal = {Computer Vision and Image Understanding},
 pdf = {/download/CVIU-food.pdf},
 doi = {10.1016/j.cviu.2018.09.001},
 projectref = {http://www.ivl.disco.unimib.it/activities/food475db/}}
2.

Learning CNN-based Features for Retrieval of Food Images
(Gianluigi Ciocca, Paolo Napoletano, Raimondo Schettini) In New Trends in Image Analysis and Processing -- ICIAP 2017: ICIAP International Workshops, WBICV, SSPandBE, 3AS, RGBD, NIVAR, IWBAAS, and MADiMa 2017, Catania, Italy, September 11-15, 2017, Revised Selected Papers, Cham, pp. 426-434, Springer International Publishing, 2017.

@inproceedings{ciocca2017Learning-CNN,
 author = {Ciocca, Gianluigi and Napoletano, Paolo and Schettini, Raimondo},
 editor = {Battiato, Sebastiano and Farinella, Giovanni Maria and Leo, Marco and Gallo, Giovanni},
 year = {2017},
 pages = {426-434},
 title = {Learning CNN-based Features for Retrieval of Food Images},
 publisher = {Springer International Publishing},
 address = {Cham},
 isbn = {978-3-319-70742-6},
 booktitle = {New Trends in Image Analysis and Processing -- ICIAP 2017: ICIAP International Workshops, WBICV, SSPandBE, 3AS, RGBD, NIVAR, IWBAAS, and MADiMa 2017, Catania, Italy, September 11-15, 2017, Revised Selected Papers},
 pdf = {/download/Ciocca2017learning-cnn.pdf},
 doi = {10.1007/978-3-319-70742-6_41},
 projectref = {http://www.ivl.disco.unimib.it/activities/food524db/}}