Recognition of Off-line Arabic Handwriting using Hidden Markov Model Toolkit

摘要：

　　This paper presents an off-line Arabic handwriting recognition system using the Hidden Markov Model Toolkit(HTK).HTK is a portable toolkit for speech recognition system.The recognition system extracts a set of features on binary handwritten images using sliding widow,builds character HMM models and learns word HMM models using embedded training without character pre-segmentation.Moreover this paper studies the relationship between frame overlap and number of stats.Experiments that have been implemented on the benchmark IFN/ENIT database show the average recognition rate of this system is 85.43%.

关键词： optical character recognition Arabic handwriting recognition hidden markov model,sliding window

作者: Dong Xiang Hu Liu Xianqiao Chen Yanfen Cheng Hanbing Yao

作者单位: School of Computer Science and Technology,Wuhan University of Technology Wuhan 430063,PR China

会议类型: 国际会议

会议名称: The Eleventh International Symposium on Distributed Computing and Applications to Business,Engineering and Science(DCABES2012)(第十一届分布式计算及其应用国际学术研讨会)(原名:电子商务、工程及科学领域的分布式计算和应用国际学术研讨会)

会议地点: 桂林

会议语种:英文

页码: 409-412

在线出版日期: 2012-10-19（万方平台首次上网日期，不代表论文的发表时间）