Vision-based detection of guitar players' fingertips without markers

Chutisant Kerdvibulvech, Hideo Saito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Citations (Scopus)

Abstract

This paper proposes a vision-based method for detecting the positions of fingertips of a hand playing a guitar. We detect the skin color of a guitar player's hand by using on-line adaptation of color probabilities and a Bayesian classifier which can cope with considerable illumination changes and a dynamic background. The results of hand segmentation are used to train an artificial neural network. A set of Gabor filters is utilized to compute a lower-dimensional representation of the image. Then an LLM (Local-Linear- Mapping)-network is applied to map and estimate fingertip positions smoothly. The system enables us to visually detect the fingertips even when the fingertips are in front of skin-colored surfaces and/or when the fingers are not fully stretched out. Representative experimental results are also presented.

Original languageEnglish
Title of host publicationComputer Graphics, Imaging and Visualisation: New Advances, CGIV 2007
Pages419-424
Number of pages6
DOIs
Publication statusPublished - 2007
EventComputer Graphics, Imaging and Visualisation: New Advances, CGIV 2007 - Bangkok, Thailand
Duration: 2007 Aug 132007 Aug 16

Other

OtherComputer Graphics, Imaging and Visualisation: New Advances, CGIV 2007
CountryThailand
CityBangkok
Period07/8/1307/8/16

Fingerprint

Skin
Color
Gabor filters
Classifiers
Lighting
Neural networks

Keywords

  • Bayesian classifier
  • Fingertip detection of guitar player
  • Gabor filter
  • Local linear mapping network

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Kerdvibulvech, C., & Saito, H. (2007). Vision-based detection of guitar players' fingertips without markers. In Computer Graphics, Imaging and Visualisation: New Advances, CGIV 2007 (pp. 419-424). [4293708] https://doi.org/10.1109/CGIV.2007.88

Vision-based detection of guitar players' fingertips without markers. / Kerdvibulvech, Chutisant; Saito, Hideo.

Computer Graphics, Imaging and Visualisation: New Advances, CGIV 2007. 2007. p. 419-424 4293708.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kerdvibulvech, C & Saito, H 2007, Vision-based detection of guitar players' fingertips without markers. in Computer Graphics, Imaging and Visualisation: New Advances, CGIV 2007., 4293708, pp. 419-424, Computer Graphics, Imaging and Visualisation: New Advances, CGIV 2007, Bangkok, Thailand, 07/8/13. https://doi.org/10.1109/CGIV.2007.88
Kerdvibulvech C, Saito H. Vision-based detection of guitar players' fingertips without markers. In Computer Graphics, Imaging and Visualisation: New Advances, CGIV 2007. 2007. p. 419-424. 4293708 https://doi.org/10.1109/CGIV.2007.88
Kerdvibulvech, Chutisant ; Saito, Hideo. / Vision-based detection of guitar players' fingertips without markers. Computer Graphics, Imaging and Visualisation: New Advances, CGIV 2007. 2007. pp. 419-424
@inproceedings{7e585ce040954b37ac6e20f45676f1a3,
title = "Vision-based detection of guitar players' fingertips without markers",
abstract = "This paper proposes a vision-based method for detecting the positions of fingertips of a hand playing a guitar. We detect the skin color of a guitar player's hand by using on-line adaptation of color probabilities and a Bayesian classifier which can cope with considerable illumination changes and a dynamic background. The results of hand segmentation are used to train an artificial neural network. A set of Gabor filters is utilized to compute a lower-dimensional representation of the image. Then an LLM (Local-Linear- Mapping)-network is applied to map and estimate fingertip positions smoothly. The system enables us to visually detect the fingertips even when the fingertips are in front of skin-colored surfaces and/or when the fingers are not fully stretched out. Representative experimental results are also presented.",
keywords = "Bayesian classifier, Fingertip detection of guitar player, Gabor filter, Local linear mapping network",
author = "Chutisant Kerdvibulvech and Hideo Saito",
year = "2007",
doi = "10.1109/CGIV.2007.88",
language = "English",
isbn = "0769529283",
pages = "419--424",
booktitle = "Computer Graphics, Imaging and Visualisation: New Advances, CGIV 2007",

}

TY - GEN

T1 - Vision-based detection of guitar players' fingertips without markers

AU - Kerdvibulvech, Chutisant

AU - Saito, Hideo

PY - 2007

Y1 - 2007

N2 - This paper proposes a vision-based method for detecting the positions of fingertips of a hand playing a guitar. We detect the skin color of a guitar player's hand by using on-line adaptation of color probabilities and a Bayesian classifier which can cope with considerable illumination changes and a dynamic background. The results of hand segmentation are used to train an artificial neural network. A set of Gabor filters is utilized to compute a lower-dimensional representation of the image. Then an LLM (Local-Linear- Mapping)-network is applied to map and estimate fingertip positions smoothly. The system enables us to visually detect the fingertips even when the fingertips are in front of skin-colored surfaces and/or when the fingers are not fully stretched out. Representative experimental results are also presented.

AB - This paper proposes a vision-based method for detecting the positions of fingertips of a hand playing a guitar. We detect the skin color of a guitar player's hand by using on-line adaptation of color probabilities and a Bayesian classifier which can cope with considerable illumination changes and a dynamic background. The results of hand segmentation are used to train an artificial neural network. A set of Gabor filters is utilized to compute a lower-dimensional representation of the image. Then an LLM (Local-Linear- Mapping)-network is applied to map and estimate fingertip positions smoothly. The system enables us to visually detect the fingertips even when the fingertips are in front of skin-colored surfaces and/or when the fingers are not fully stretched out. Representative experimental results are also presented.

KW - Bayesian classifier

KW - Fingertip detection of guitar player

KW - Gabor filter

KW - Local linear mapping network

UR - http://www.scopus.com/inward/record.url?scp=46449100407&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46449100407&partnerID=8YFLogxK

U2 - 10.1109/CGIV.2007.88

DO - 10.1109/CGIV.2007.88

M3 - Conference contribution

AN - SCOPUS:46449100407

SN - 0769529283

SN - 9780769529288

SP - 419

EP - 424

BT - Computer Graphics, Imaging and Visualisation: New Advances, CGIV 2007

ER -