Kelly, Daniel and McDonald, John and Markham, Charles (2011) Weakly Supervised Training of a Sign Language Recognition System Using Multiple Instance Learning Density Matrices. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 41 (2). pp. 526-541. ISSN 1083-4419

Preview

Download (990kB) | Preview

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.

Item Type:	Article
Keywords:	weakly supervised learning; HMM; multiple instance learning (MIL); sign language recognition; size function; support vector machine (SVM);
Academic Unit:	Faculty of Science and Engineering > Computer Science
Item ID:	8288
Identification Number:	https://doi.org/10.1109/TSMCB.2010.2065802
Depositing User:	John McDonald
Date Deposited:	08 Jun 2017 14:27
Journal or Publication Title:	IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
Publisher:	IEEE
Refereed:	Yes
URI:	http://ieeexplore.ieee.org
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads