Handwritten Urdu Character Recognition using 1-Dimensional BLSTM Classifier
This work addresses the lack of a comprehensive public dataset for Urdu handwritten character recognition, which is an incremental advancement for researchers in optical character recognition.
The paper tackles the problem of recognizing handwritten Urdu characters, a cursive script with no standard dataset, by introducing the Urdu-Nastaliq Handwritten Dataset (UNHD) and achieves significant accuracy using recurrent neural networks.
The recognition of cursive script is regarded as a subtle task in optical character recognition due to its varied representation. Every cursive script has different nature and associated challenges. As Urdu is one of cursive language that is derived from Arabic script, thats why it nearly shares the same challenges and difficulties even more harder. We can categorized Urdu and Arabic language on basis of its script they use. Urdu is mostly written in Nastaliq style whereas, Arabic follows Naskh style of writing. This paper presents new and comprehensive Urdu handwritten offline database name Urdu-Nastaliq Handwritten Dataset (UNHD). Currently, there is no standard and comprehensive Urdu handwritten dataset available publicly for researchers. The acquired dataset covers commonly used ligatures that were written by 500 writers with their natural handwriting on A4 size paper. We performed experiments using recurrent neural networks and reported a significant accuracy for handwritten Urdu character recognition.