System for Identifying Texts Written in Kazakh Language


Authors : Absenova B.M; Zhanibay S.B; Zheksebay D.M; Temesheva S.A; Turmaganbet U.K

Volume/Issue : Volume 7 - 2022, Issue 12 - December

Google Scholar : https://bit.ly/3IIfn9N

Scribd : https://bit.ly/3Yhk0jJ

DOI : https://doi.org/10.5281/zenodo.7620902

Abstract : Recently, image-based text extraction has becomea prominent and hard study subject in computer vision. In this article, the texts written in Kazakh are classified based on factors such as writing style and diversity of writing, and a text recognition system based on correctly defined terms is developed.Text matching is accomplished by using the EasyOCR library to the input picture to extract the areas containing the words. The words in the text are then determined using the locations acquired. To initialize the text and recognize the defined text, twodistinct functions are utilized. As a consequence, a method for recognizing Kazakh words as graphics is developed. The accuracy of proper text identification revealed a result of 91%

Keywords : Text, detection, optical character recognition, scene,detector

Recently, image-based text extraction has becomea prominent and hard study subject in computer vision. In this article, the texts written in Kazakh are classified based on factors such as writing style and diversity of writing, and a text recognition system based on correctly defined terms is developed.Text matching is accomplished by using the EasyOCR library to the input picture to extract the areas containing the words. The words in the text are then determined using the locations acquired. To initialize the text and recognize the defined text, twodistinct functions are utilized. As a consequence, a method for recognizing Kazakh words as graphics is developed. The accuracy of proper text identification revealed a result of 91%

Keywords : Text, detection, optical character recognition, scene,detector

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe