IEEE Trans Pattern Anal Mach Intell. 2011 Oct;33(10):2066-80. doi: 10.1109/TPAMI.2011.22. Epub 2011 Feb 4.
This study aims at building an efficient word recognition system resulting from the combination of three handwriting recognizers. The main component of this combined system is an HMM-based recognizer which considers dynamic and contextual information for a better modeling of writing units. For modeling the contextual units, a state-tying process based on decision tree clustering is introduced. Decision trees are built according to a set of expert-based questions on how characters are written. Questions are divided into global questions, yielding larger clusters, and precise questions, yielding smaller ones. Such clustering enables us to reduce the total number of models and Gaussians densities by 10. We then apply this modeling to the recognition of handwritten words. Experiments are conducted on three publicly available databases based on Latin or Arabic languages: Rimes, IAM, and OpenHart. The results obtained show that contextual information embedded with dynamic modeling significantly improves recognition.
本研究旨在构建一个高效的单词识别系统，该系统结合了三个手写识别器。该组合系统的主要组成部分是基于 HMM 的识别器，它考虑了动态和上下文信息，以便更好地对书写单位进行建模。为了对上下文单元进行建模，引入了基于决策树聚类的状态绑定过程。决策树是根据一组关于字符如何书写的基于专家的问题构建的。问题分为全局问题和精确问题，全局问题生成较大的聚类，而精确问题生成较小的聚类。这种聚类方法使我们能够将模型和高斯密度的总数减少 10 倍。然后，我们将这种建模应用到手写单词的识别中。实验在三个基于拉丁语或阿拉伯语的公开可用数据库上进行：Rimes、IAM 和 OpenHart。所得到的结果表明，嵌入动态建模的上下文信息显著提高了识别性能。
