FruitVeg-81 Dataset

This grocery food dataset has been collected within the project MANGO (Mobile Augmented Reality for Nutrition Guidance and Food Awareness). It contains 15737 images (longest side resized to 512px) with a total download size of 3.2GB.

The dataset consists of fruit and vegetable items with hierarchical labels. It is structured as follows:

  1. the first level depicts the general sort of food item (apples, bananas, ...)
  2. the second level collects food cultivars with similar visual appearance (red apples, green apples,...)
  3. the third level dstinguishes between different cultivars (Golden Delicious, Granny Smith, ...) or packaging types (boxed, tray, ...)
This results in a folder hierarchy with: 53 coarse classes (e.g. apple), 81 fine classes (e.g. green apples) and 125 cultivars (e.g. Golden Delicious). The folders within each cultivar folder correspond to specific recordings of the same fruit or vegetable, additionally a label is provided indicating the used smartphone (see Tab.3). Therefore the contained images within these folders (4-5 per recording) should be treated as one sample for training and testing.

If you use this dataset or results, please cite our paper:

Personalized Dietary Self-Management using Mobile Vision-based Assistance
Georg Waltner, Michael Schwarz , Stefan Ladstätter, Anna Weber, Patrick Luley, Meinrad Lindschinger, Irene Schmid, Walter Scheitz, Horst Bischof, and Lucas Paletta
In Proc. International Workshop on Multimedia Assisted Dietary Management (MADIMA, in conjunction with ICIAP), 2017

BibTeX reference for convenience:

  author={Georg Waltner and Michael Schwarz and Stefan Ladstätter and Anna Weber and Patrick Luley and Meinrad Lindschinger and Irene Schmid and Walter Scheitz and Horst Bischof and Lucas Paletta},
  title={{Personalized Dietary Self-Management using Mobile Vision-based Assistance}},
  booktitle={Proc. of ICIAP Workshop on Multimedia Assisted Dietary Management (MADIMA)},

DB Overview

The following table shows challenges of the FruitVeg-81 database:
number of objects
Golden Delicious
Granny Smith
fine-grained differences

Table 1: Challenges posed by the FruitVeg-81 dataset.

Recording Devices

The images were recorded in SPAR grocery stores using five mobile phones (Samsung Galaxy S3, Samsung Galaxy S3, Motorola Moto G, HTC One, HTC Three). Table 2 lists the models with abbreviation used within the dataset.

Model Abbreviation
Samsung Galaxy S3 gxs3
Samsung Galaxy S5 gxs5
HTC One htco
HTC Three htc3
Mototola Moto G motg

Table 2: Overview of the mobile phones used for recording the dataset.


By downloading the database you agree to the following restrictions:

  1. The FruitVeg-81 database is available for non-commercial research purposes only.
  2. The FruitVeg-81 database includes images obtained from Spar grocery stores which are not property of Graz University of Technology. Graz University of Technology is not responsible for the content nor the meaning of these images. Any use of the images must be negociated with the respective picture owners. In particular, you agree not to reproduce, duplicate, copy, sell, trade, resell or exploit for any commercial purposes, any portion of the images and any portion of derived data.
  3. You agree not to further copy, publish or distribute any portion of the FruitVeg-81 database. Except, for internal use at a single site within the same organization it is allowed to make copies of the database.
  4. All submitted papers or any publicly available text using the FruitVeg-81 database must cite the corresponding paper.
  5. The organization represented by you will be listed as users of the FruitVeg-81 database.

Download Instructions

If you agree with the terms of the license agreement contact Dušan Malić ( to obtain download instructions.
Please send the email from your official account so we can verify your affiliation and include your

  • Name
  • Position (job title)
  • Organization
  • and the intended use


This work was supported by the Austrian Research Promotion Agency (FFG) under the project Mobile Augmented Reality for Nutrition Guidance and Food Awareness (836488).