Download available

Authors:

Anne-Marie Burns and Marcelo M. Wanderley

Publication or Conference Title:

Proceedings of the 2006 Sound and Music Computing Conference (SMC2006)

Abstract:

This article presents a method to visually detect and recognize fingering gestures of the left hand of a guitarist. This method has been developed following preliminary manual and automated analysis of video recording of a guitarist. These analysis permitted to determine some important characteristics of a vision system for guitarist fingering, namely the focus on the effective gesture, the consideration of the action of each individual finger, and the definition of a recognition system not relying on comparison against a knowledge base of previously learned fingering positions. Motivated by these results, studies on three important aspects of a complete fingering system were conducted. One study was on finger tracking, another on strings and frets detection, and the last one on movement segmentation. Finally, a prototype that integrated the above three aspects in a system for guitarist left hand fingering detection has been developed.

Publication Details:

Type:	Conference Paper
Date:	06/01/2006
Location:	Marseille, France