A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition

A technique is presented which combines rule-based and neural network pattern recognition methods in an integrated system in order to perform learning and recognition of hand-written characters and gestures in realtime. The GesRec system is introduced which provides a framework for data acquisiti...

Full description

Bibliographic Details
Main Authors: Craven, Michael P., Curtis, K. Mervyn, Hayes-Gill, Barrie H., Thursfield, C.D.
Format: Conference or Workshop Item
Published: 1997
Subjects:
Online Access:https://eprints.nottingham.ac.uk/1902/
_version_ 1848790682384203776
author Craven, Michael P.
Curtis, K. Mervyn
Hayes-Gill, Barrie H.
Thursfield, C.D.
author_facet Craven, Michael P.
Curtis, K. Mervyn
Hayes-Gill, Barrie H.
Thursfield, C.D.
author_sort Craven, Michael P.
building Nottingham Research Data Repository
collection Online Access
description A technique is presented which combines rule-based and neural network pattern recognition methods in an integrated system in order to perform learning and recognition of hand-written characters and gestures in realtime. The GesRec system is introduced which provides a framework for data acquisition, training, recognition, and gesture-to-speech transcription in a Windows environment. A recognition accuracy of 92.5% was obtained for the hybrid system, compared to 89.6% for the neural network only and 82.7% for rules only. Training and recognition times are given for an able-bodied and a disabled user.
first_indexed 2025-11-14T18:16:30Z
format Conference or Workshop Item
id nottingham-1902
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T18:16:30Z
publishDate 1997
recordtype eprints
repository_type Digital Repository
spelling nottingham-19022020-05-04T20:33:25Z https://eprints.nottingham.ac.uk/1902/ A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition Craven, Michael P. Curtis, K. Mervyn Hayes-Gill, Barrie H. Thursfield, C.D. A technique is presented which combines rule-based and neural network pattern recognition methods in an integrated system in order to perform learning and recognition of hand-written characters and gestures in realtime. The GesRec system is introduced which provides a framework for data acquisition, training, recognition, and gesture-to-speech transcription in a Windows environment. A recognition accuracy of 92.5% was obtained for the hybrid system, compared to 89.6% for the neural network only and 82.7% for rules only. Training and recognition times are given for an able-bodied and a disabled user. 1997 Conference or Workshop Item PeerReviewed Craven, Michael P., Curtis, K. Mervyn, Hayes-Gill, Barrie H. and Thursfield, C.D. (1997) A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition. In: Proceedings of the Fourth IEEE International Conference on Electronics, Circuits and Systems, 15-18 December 1997, Cairo, Egypt. gesture recognition dissimilarity similarity segmentation text-to-speech gesture-to-speech sign language 3D tracking Augmentative and Alternative Communication AAC human computer interaction HCI
spellingShingle gesture recognition
dissimilarity
similarity
segmentation
text-to-speech
gesture-to-speech
sign language
3D tracking
Augmentative and Alternative Communication
AAC
human computer interaction
HCI
Craven, Michael P.
Curtis, K. Mervyn
Hayes-Gill, Barrie H.
Thursfield, C.D.
A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition
title A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition
title_full A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition
title_fullStr A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition
title_full_unstemmed A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition
title_short A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition
title_sort hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition
topic gesture recognition
dissimilarity
similarity
segmentation
text-to-speech
gesture-to-speech
sign language
3D tracking
Augmentative and Alternative Communication
AAC
human computer interaction
HCI
url https://eprints.nottingham.ac.uk/1902/