MANGO-I Dataset*

Georg Waltner1, Michael Schwarz2, Stefan Ladstätter2, Anna Weber2, Patrick Luley2, Meinrad Lindschinger3, Irene Schmid3, Horst Bischof1, and Lucas Paletta2.
1Institute for Computer Graphics and Vision, Graz University of Technology, Austria.
2JOANNEUM RESEARCH Forschungsgesellschaft mbH, Graz, Austria.
3Institute for Nutritional and Metabolic Diseases, Schwarzl Outpatient Clinic, Lassnitzhöhe, Austria.

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


This page briefly describes the MANGO-I dataset.

You can find:


2016-03-31 First release of the MANGO-I dataset.


This grocery food dataset has been collected within the project MANGO (Mobile Augmented Reality for Nutrition Guidance and Food Awareness). It contains 1719 videos comprising 23 classes, which are subdivided into 98 subclasses. Details about classes and used mobile phones can be found below in Tables 1-3.

Due to the nature of the database and the comprehensive annotation we think it is well suited to train and test algorithms for

Class Overview

1cherries 2apricots 3strawberries 4blackberries 5blueberries 6currants
7chanterelles 8champignons & mushrooms 9apples 10tomatoes 11salad 12pears
13broccoli 14cauliflower 15cabbage 16peppers 17grapes 18bananas
19herbs 20horseradish 21plums 22damsons 23raspberries   

Table 1: Overview of the 23 main classes as defined in MANGO-I.

The 23 classes have been further split into 35 visually distinct classes, e.g. sorts like "peppers" have been split into four classes (yellow, green, red and mixed). See Table 2 for a list of classes.

1 cherries 2 apricots 3 strawberries 4 blackberries 5 blueberries 6 chanterelles 7 champignons
8 tomatoes on the wine 9 green salad 10 pears 11 broccoli 12 cauliflower 13 cabbage 14 grapes
15 bananas 16 herbs 17 horseradish 18 plums 19 damsons 20 raspberries 21 red currants
22 black currants 23 white currants 24 brown mushrooms 25 red apples 26 green apples 27 mixed tomatoes 28 beef tomatoes
29 Kumato tomatoes 30 iceberg salad 31 Lollo Rosso salad 32 yellow peppers 33 green peppers 34 red peppers 35 mixed peppers

Table 2: Overview of the 35 visually distinct classes as defined in MANGO-I.

Mobile phones

The videos were recorded in two SPAR grocery stores in HD (1920x1080 and 1280x720) using five mobile phones (Samsung Galaxy S2, Samsung Galaxy S3, Motorola Moto G, HTC One, LG Nexus 4). Table 3 lists the models with resolution and abbreviation used within the dataset.
Model Resolution Abbreviation
Samsung Galaxy S2 1920x1080 gxs2
Samsung Galaxy S3 1920x1080 gxs3
LG Nexus 4 1920x1080 nex4
HTC One 1280x720 htco
Mototola Moto G 1280x720 motg

Table 3: Overview of the mobile phones used for recording the dataset.

File naming convention

The videos were named following a simple convention. When the name is split using "-" as delimiter, the first number is the main class of the above listed 23 food classes. The second number is the subcategory (one of total 98) and the third is a sequential number of recordings with the same mobile phone and of the same food item. These three numbers are followed by the abbreviation of the mobile phone as listed in Table 3. For some videos there is another tag "i1" or "i2" as abbreviation for an intuitive recording, where the subjects were not instructed beforehand.
The second number is intended to be used for hierarchical computer vision methods, where a class is further split into subclasses.
Example: 2-7-2-htco-i1.mp4 denotes the 7th subclass of apricots and the 2nd recording of this class with the mobile phone HTC One.

License agreement

By downloading the database you agree to the following restrictions:

  1. The MANGO-I database is available for non-commercial research purposes only.
  2. The MANGO-I 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 MANGO-I 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 MANGO-I database must cite the following paper:

    MANGO - Mobile Augmented Reality with Functional Eating Guidance and Food Awareness(pdf, bibtex)
    Georg Waltner, Michael Schwarz, Stefan Ladst├Ątter, Anna Weber, Patrick Luley, Horst Bischof, Meinrad Lindschinger, Irene Schmid, and Lucas Paletta
    In Proc. International Workshop on Multimedia Assisted Dietary Management (MADIMA, in conjunction with ICIAP), 2015

  5. The organization represented by you will be listed as users of the MANGO-I database.

Download instructions

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

If you already received your login credentials you can proceed to the download section.


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

Copyright 2010 ICG

Valid XHTML 1.1 Valid CSS