Minimal Training, Large Lexicon, Unconstrained Sign Language Recognition
Minimal Training, Large Lexicon, Unconstrained Sign Language Recognition
复制标题
DOI：
10.5244/c.18.96
复制
发表时间：
2004-09
期刊：
影响因子：
--
通讯作者：
T. Kadir;R. Bowden;Eng-Jon Ong;Andrew Zisserman
中科院分区：
文献类型：
--
作者：
T. Kadir;R. Bowden;Eng-Jon Ong;Andrew Zisserman
本文提出了一种灵活的单目系统，该系统能够识别数量远远大于以往方法的符号词汇。该系统的强大功能得益于四个关键要素：(i)基于增强的头部和手部检测，消除了对气质颜色分割的需要；以身体为中心的活动描述，克服相机放置、校准和用户的问题；两阶段分类，其中第一阶段产生对活动的高水平语言描述，自然概括，从而减少训练；不需要hmm的第二阶段分类器库，进一步减少了培训需要。其结果是一个能够实时运行的系统，并且在每个符号只有一个训练实例的情况下，对大型词汇产生极高的识别率。我们证明，对于164个单词的词典，分类率高达92%，训练要求极低，优于以前需要数千个训练样例的方法。
This paper presents a flexible monocular system capable of recognising sign lexicons far greater in number than previous approaches. The power of the system is due to four key elements: (i) Head and hand detection based upon boosting which removes the need for temperamental colour segmentation; (ii) A body centred description of activity which overcomes issues with camera placement, calibration and user; (iii) A two stage classification in which stage I generates a high level linguistic description of activity which naturally generalises and hence reduces training; (iv) A stage II classifier bank which does not require HMMs, further reducing training requirements. The outcome of which is a system capable of running in real-time, and generating extremely high recognition rates for large lexicons with as little as a single training instance per sign. We demonstrate classification rates as high as 92% for a lexicon of 164 words with extremely low training requirements outperforming previous approaches where thousands of training examples are required.