Presentation
MTG dataset (for Multi-Touch Gestures)
MTGSetA contains 18 multi-touch gestures.
MTGSetB consists of 31 classes, with 27 multi-touch gestures and 4 multi-stroke mono-touch gesture
| MTGSetA – 18 classes
MTGSetB – 46 classes, regrouped into 31 rotation-independant classes
|
| Gestures available in MTG |
Specifications
The MTG dataset is divided into two parts :
MTGSetA :
- 18 classes
- 10 persons
- 1,800 multi-touch gestures
MTGSetB :
- 31 classes
- 33 persons
- 7658 multi-touch gestures
Download
The database can be downloaded here (10Mo)
Contact
For any question, please contact Eric Anquetil.
References
This database can be used freely for research purpose. However, for any published work utilizing this database, please mention a reference to the following paper.
MTGSetA :
Zhaoxin Chen, Eric Anquetil, Harold Mouchère, Christian Viard-Gaudin. A graph modeling strategy for multi-touch gesture recognition. 14th International Conference on Frontiers in Handwriting Recognition (ICFHR-2014), Sep 2014, Crete island, Greece
MTGSetB :
Zhaoxin Chen, Eric Anquetil, Harold Mouchère, Christian Viard-Gaudin. Recognize multi-touch gestures by graph modeling and matching. 17th Biennial Conference of the International Graphonomics Society, International Graphonomics Society (IGS); Université des Antilles (UA), Jun 2015, Pointe-à-Pitre, Guadeloupe.
