Parametrized SOMs for hand posture reconstruction
- 1 January 2000
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (10987576) , 139-144 vol.4
- https://doi.org/10.1109/ijcnn.2000.860763
Abstract
This paper describes the use of neural network for gesture recognition based on finger tips, a system that recognizes continuous hand postures from video images. Our approach yields a full identification of all finger joint angles. This allows a full reconstruction of the 3D hand shape, using an artificial hand model with 16 segments and 20 joint angles. The focus of the present paper is how to employ a parametrised SOM neural network for the inverse kinematics task to compute the angles of a hand model out of 3D positions of the fingertips. We show that this type of neural net does not only achieve excellent results from very few training examples, but also can be applied to uncommon data structures.Keywords
This publication has 7 references indexed in Scilit:
- Vision based hand modeling and tracking for virtual teleconferencing and telecollaborationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Rapid learning with parametrized self-organizing mapsNeurocomputing, 1996
- Model-based analysis of hand postureIEEE Computer Graphics and Applications, 1995
- Towards an American Sign Language interfaceArtificial Intelligence Review, 1994
- Visual tracking of high DOF articulated structures: An application to human hand trackingPublished by Springer Nature ,1994
- Parametrized Self-Organizing MapsPublished by Springer Nature ,1993
- The self-organizing mapProceedings of the IEEE, 1990