Computer Vision Methods for Guitarist Left-Hand Fingering Recognition

Participants: Anne-Marie Burns
Marcelo M. Wanderley (supervisor)
In collaboration with Barbara Mazzarino, Gualtiero Volpe, and Antonio Camurri, InfoMus Laboratory, Genoa, Italy.

Finger-tracking Algorithm.
Funding: Quebec government (Programme de bourses pour de courts séjours d'études universitaires à l'extérieur du Québec)
Italian Ministry of Foreign Affairs, EU 6th FP IST ENACTIVE Network of Excellence (1st internship at InfoMus, Genoa, 2004)
Cost287-ConGAS (2nd internship at InfoMus, Genoa, 2007)
NSERC Discovery Grant (M. Wanderley) (Research assistant)
McGill University Alma Mater Student Travel Grant 2005, 2006

Project Type: Master's thesis (M.A. in Music Technology)

Time Period: Sept. 2003 - Aug. 2006. Status: Completed.


Project Description:

This project is about the development of an automated method to visually detect and recognize fingering gestures of the left hand of a guitarist. The choice of computer vision to perform that task is motivated by the absence of a satisfying method for realtime guitarist fingering detection. The development of this computer vision method follows preliminary manual and automated analyses of video recordings of a guitarist. These first analyses led to some important findings about the design methodology of such a system, namely the focus on the effective gesture, the consideration of the action of each individual finger, and 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 realtime finger tracking, another on string and fret detection, and the last on movement segmentation. Finally, these concepts were integrated into a prototype and a system for left-hand fingering detection was developed. Such a data acquisition system for fingering retrieval has uses in music theory, music education, automatic music and accompaniment generation and physical modeling.

Finger-tracking Algorithm


Publications:

  • Burns, A.-M. (2006). Computer Vision Methods for Guitarist Left-Hand Fingering Recognition. M.A. thesis, McGill University, Montréal, Québec
  • Burns, A.-M., & Wanderley, M. M. (2006). Visual methods for the retrieval of guitarist fingering. In proceedings of the New Interfaces for Musical Expression 2006 (pp. 196-199). Paris, France
  • Burns, A.-M., & Wanderley, M. M. (2006). Computer vision method for guitarist fingering retrieval. In proceedings of the Sound and Music Computing 2006 (pp. 1-7). Marseille, France
  • Burns, A.-M., & Mazzarino, B. (2006). Finger tracking methods using EyesWeb. In S. Gibet, N. Courty, & J.-F. Kamp (Eds.), Gesture workshop 2005 proceedings (Vol. LNAI 3881, pp. 156-167). Springer Verlag

Presentations:

  • Burns, A.-M., & Wanderley, M. M. (2006). Visual methods for the retrieval of guitarist fingering. New Interfaces for Musical Expression 2006. June 4-8, Paris, France
  • Burns, A.-M., & Wanderley, M. M. (2006). Computer vision method for guitarist fingering retrieval. Sound and Music Computing 2006. May, Marseille, France
  • Burns, A.-M., & Mazzarino, B. (2005). Finger tracking methods using EyesWeb. Gesture workshop 2005. May, Île de Berder, France