Sign language recognition using 3-D Hopfield neural network
- 19 November 2002
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
[[abstract]]This paper presents a sign language recognition system which consists of three modules: model-based hand tracking, feature extraction, and gesture recognition using a 3-D Hopfield neural network. In the experiments, we illustrate that this system can recognize 15 different gestures accurately.[[fileno]]2030109030033[[department]]電機工程學This publication has 9 references indexed in Scilit:
- Visual gesture recognitionIEE Proceedings - Vision, Image, and Signal Processing, 1994
- Fourier descriptors and handwritten digit recognitionMachine Vision and Applications, 1993
- Image processing system for interpreting motion in American Sign LanguageJournal of Biomedical Engineering, 1992
- Recognition of sign language motion imagesPattern Recognition, 1988
- A region based approach for human body motion analysisPattern Recognition, 1987
- High accuracy character recognition algorithm using fourier and topological descriptorsPattern Recognition, 1984
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- The interpretation of biological motionBiological Cybernetics, 1982
- Fourier Descriptors for Plane Closed CurvesIEEE Transactions on Computers, 1972