An in-situ trainable gesture classifier

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

57 Downloads (Pure)


Gesture recognition, i.e., the recognition of pre-defined gestures by arm or hand movements, enables a natural extension of the way we currently interact with devices (Horsley, 2016). Commercially available gesture recognition systems are usually pre-trained: the developers specify a set of gestures, and the user is provided with an algorithm that can recognize just these gestures. To improve the user experience, it is often desirable to allow users to define their own gestures. In that case, the user needs to train the recognition system herself by a set of example gestures. Crucially, this scenario requires learning gestures from just a few training examples in order to avoid overburdening the user. We present a new in-situ trainable gesture classifier based on a hierarchical probabilistic modeling approach. Casting both learning and recognition as probabilistic inference tasks yields a principled way to design and evaluate algorithm candidates. Moreover, the Bayesian approach facilitates learning of prior knowledge about gestures, which leads to fewer needed examples for training new gestures.
Originele taal-2Engels
TitelBenelearn 2017: Proceedings of the Twenty-Sixth Benelux Conference on Machine Learning, Technische Universiteit Eindhoven, 9-10 June 2017
RedacteurenW. Duivesteijn, M. Pechenizkiy, G.H.L. Fletcher
StatusGepubliceerd - 10 jun 2017
EvenementAnnual machine learning conference of the Benelux (Benelearn 2017) - Eindhoven, Nederland
Duur: 9 jun 201710 jun 2017


CongresAnnual machine learning conference of the Benelux (Benelearn 2017)
Verkorte titelBenelearn 2017
Internet adres


Duik in de onderzoeksthema's van 'An in-situ trainable gesture classifier'. Samen vormen ze een unieke vingerafdruk.

Citeer dit