Kelly Daniel, Mc Donald John, Markham Charles
Computer Science Department, National University of Ireland Maynooth, Maynooth, Ireland.
IEEE Trans Syst Man Cybern B Cybern. 2011 Apr;41(2):526-41. doi: 10.1109/TSMCB.2010.2065802. Epub 2010 Sep 23.
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.
提出了一种用于从连续手语句子中自动训练和识别手语的系统。我们提出了一种新颖的多实例学习密度矩阵算法，该算法利用文本翻译的弱监督和噪声监督，从完整句子中自动提取孤立的手语。然后，利用自动提取的孤立样本训练我们的时空手势和手部姿势分类器。进行实验以评估自动手语提取、手部姿势分类和时空手势识别系统的性能。然后，我们对在30种不同手语上自动训练的整体手语识别系统进行了全面评估。
