Real-Time Guitar Chord Recognition System Using Stereo Cameras for Supporting Guitarists
Chutisant Kerdvibulvech, Hideo Saitô, Non-members · 2007
This paper proposes a novel approach for recognizing chords played on a guitar by using stereo cameras. This process is done in real time by recognizing the patterns of flngers’ pushing positions detected from input images. The program detects the position of a player’s flngers by using on-line adaptation of color probabilities and a Bayesian classifler. Therefore the system is able to cope easily with considerable illumination changes and a dynamic background. ARTag is utilized to calculate the extrinsic parameters as an online process, so that the system can recognize the correct chord, even if the guitar is moving. By utilizing a triangulation method on stereo cameras, the 3D positions of flngers are recognized when a guitar string is pressed. It used the advantages found in PCA (Principal Component Analysis) to e‐ciently deal with complex chord classiflcation. The experimental results have revealed that the proposed system is efiective in real time also.