An Assessment of Arabic Handwriting Recognition Technology
An Assessment of Arabic Handwriting Recognition Technology
复制标题
阿拉伯语手写识别技术评估
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
G. R. Ball
中科院分区：
文献类型：
--
作者：
S. Srihari;G. R. Ball
阿拉伯文字的自动识别方法与拉丁文和中文文字的识别方法相比还处于早期阶段。阿拉伯手写识别技术的评估是基于已发表的文献。介绍了阿拉伯语脚本，然后描述了所涉及的过程的算法：分割，特征提取，分类和搜索。现有的阿拉伯语语料库的描述与语料库收集的设计。本文最后确定了技术差距，并提供了一个书目的阿拉伯语识别的最新文献。
Automated methods for the recognition of Arabic script are at an early stage compared to their counterparts for the recognition of Latin and Chinese scripts. An assessment of the technology for Arabic handwriting recognition is provided based on the published literature. An introduction to the Arabic script is given followed by a description of algorithms for the processes involved: segmentation, feature extraction, classification, and search. Existing corpora for Arabic are described together with a design for corpus collection. The paper is concluded by identifying technology gaps and providing a bibliography of the recent literature on Arabic recognition.