A Survey on the Classifiers in On-line Handwritten Uyghur Character Recognition System

Abstract

With the fast development of information technology made people eager to get access the convenient implementations of modern technology in every walk of life. Online handwritten recognition technology for Uyghur is also receiving great need, too. Precious work form researchers for this technology has been gifted many gains. This paper observe the classifiers used in previous work on this field in order to see their adaptabilities for Uyghur online handwritten recognition, and acquire clues for classifier implementation in future work. . Currently, he is a professor in the School of Software Engineering, Xinjiang University. He has published more than 150 technical papers on speech synthesis, natural language processing and image processing. He is a senior member of CCF and an affiliate member of IEEE.

Unconstrained online handwritten Uyghur word recognition based on recurrent neural networks and connectionist temporal classification

“…Studies on Uyghur handwriting recognition have also implemented the classic methods for character and word level recognitions task. HMM based and integrated segmentation-recognition approaches have been the most common word recognition systems (Simayi et al, 2016). For example, Chen (2013) reported 91.7% accuracy on 2,000 words using HMM; 93.71% recognition rate on 1058 word classes was achieved by Pi (2012).…”