Journal Article


Charles Markham
John McDonald
Daniel Kelly


Computer Science

classification sign language training algorithm sign language recognition system supervised learning language learning density

Weakly Supervised Training of a Sign Language Recognition System Using Multiple Instance Learning Density Matrices (2011)

Abstract A system for automatically training and spotting signs from continuous sign language sentences is presented. We propose a novel multiple instance learning density matrix algorithm which automatically extracts isolated signs from full sentences using the weak and noisy supervision of text translations. The automatically extracted isolated samples are then utilized to train our spatiotemporal gesture and hand posture classifiers. The experiments were carried out to evaluate the performance of the automatic sign extraction, hand posture classification, and spatiotemporal gesture spotting systems. We then carry out a full evaluation of our overall sign spotting system which was automatically trained on 30 different signs.
Collections Ireland -> Maynooth University -> Type = Article
Ireland -> Maynooth University -> Academic Unit = Faculty of Science and Engineering
Ireland -> Maynooth University -> Status = Published
Ireland -> Maynooth University -> Open Access DRIVERset
Ireland -> Maynooth University -> Academic Unit = Faculty of Science and Engineering: Computer Science

Full list of authors on original publication

Charles Markham, John McDonald, Daniel Kelly

Experts in our system

Charles Markham
Maynooth University
Total Publications: 64
John McDonald
Maynooth University
Total Publications: 79
Daniel Kelly
University College Cork
Total Publications: 17