Abstract
Objectives The purpose of this study is to investigate how a deep learning-based optical character recognition (OCR) tool can improve students' handwriting. We aim to develop and validate the effectiveness of a handwriting checking tool to counteract the increase in bad handwriting due to the acceleration of digitalization.
 Methods This study began with the development of a notification letter checker tool using Jetson Nano and NAVER CLOVA OCR. The tool was then applied to 20 fifth-grade students for about two months, and pre- and post-training visuoperceptual development tests were conducted to measure changes before and after training.
 Results The results of the study demonstrated that the use of a deep learning-based optical character recognition tool had a positive impact on students' handwriting skills. Improvements in performance were observed in some of the visuoperceptual developmental test items, and substantial changes in handwriting confidence were also observed.
 Conclusions This study confirms the potential of deep learning-based OCR tools as an important tool for improv-ing students' handwriting skills. However, since the study was conducted on a limited sample group, further re-search is needed, and the accumulated Korean handwriting data from this study can be developed into a more ef-fective tool. The tools developed in this study are available on GitHub at https://github.com/jkf87/autostampper.
Sign-in/Register to access full text options 
Free) 
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 call
