Abstract
The importance of online handwriting recognition technology has steadily increased in recent years. This importance stems from the rapid increase in the number of handheld devices with digital pens and styluses. In addition, a large number of currently available communication software have been designed to support handwriting boards. During the past decade, most innovation in online handwriting recognition technology was geared towards supporting languages using the Latin alphabet. There has been a lack of sufficient development of Arabic online handwriting recognition (AOHR) systems, especially ones that perform recognition at the sentence level. In this paper, we present DeepOnKHATT, an end-to-end AOHR based on bidirectional long short-term memory and the connectionist temporal classification (BLSTM-CTC). DeepOnKHATT is capable of performing recognition at the sentence level in real-time. We evaluated our system utilizing two open access databases: CHAW and Online-KHATT. Our model achieved a 4.08% character error rate (CER) and a 14.65% word error rate (WER) against the CHAW dataset and a 12.24% CER and a 28.35% WER against the Online-KHATT dataset. A Comparison of the functionality of our proposed model to that of other existing systems showed that DeepOnKHATT had outperformed these systems.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Pattern Recognition and Artificial Intelligence
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
