Skip to Main content Skip to Navigation
Conference papers

Learning to Recognize Touch Gestures: Recurrent vs. Convolutional Features and Dynamic Sampling

Quentin Debard 1 Christian Wolf 1, 2, 3 Stephane Canu 4, 5 Julien Arné 6
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
3 CHROMA - Robots coopératifs et adaptés à la présence humaine en environnements dynamiques
Inria Grenoble - Rhône-Alpes, CITI - CITI Centre of Innovation in Telecommunications and Integration of services
5 DocApp - LITIS - Equipe Apprentissage
LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
Abstract : We propose a fully automatic method for learning gestures on big touch devices in a potentially multiuser context. The goal is to learn general models capable of adapting to different gestures, user styles and hardware variations (e.g. device sizes, sampling frequencies and regularities). Based on deep neural networks, our method features a novel dynamic sampling and temporal normalization component, transforming variable length gestures into fixed length representations while preserving finger/surface contact transitions, that is, the topology of the signal. This sequential representation is then processed with a convolutional model capable, unlike recurrent networks, of learning hierarchical representations with different levels of abstraction. To demonstrate the interest of the proposed method, we introduce a new touch gestures dataset with 6591 gestures performed by 27 people, which is, up to our knowledge, the first of its kind: a publicly available multi-touch gesture dataset for interaction. We also tested our method on a standard dataset of symbolic touch gesture recognition, the MMG dataset, outperforming the state of the art and reporting close to perfect performance.
Complete list of metadata

Cited literature [32 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02302545
Contributor : Quentin Debard <>
Submitted on : Tuesday, October 1, 2019 - 5:16:28 PM
Last modification on : Thursday, July 16, 2020 - 2:45:26 PM

File

FG2018_paper.pdf
Files produced by the author(s)

Identifiers

Citation

Quentin Debard, Christian Wolf, Stephane Canu, Julien Arné. Learning to Recognize Touch Gestures: Recurrent vs. Convolutional Features and Dynamic Sampling. FG'2018 - 13th IEEE International Conference on Automatic Face and Gesture Recognition, May 2018, Xi'An, China. pp.114-121, ⟨10.1109/FG.2018.00026⟩. ⟨hal-02302545⟩

Share

Metrics

Record views

129

Files downloads

148