A deep learning framework for handwritten Ol Chiki character recognition

Autor: Debaditya Barman, Tuheli Bhattacharya, Nirmalya Chowdhury
Rok vydání: 2022
Zdroj: Journal of Scientific Research. 66:206-213
ISSN: 0447-9483
DOI: 10.37398/jsr.2022.660227
Popis: Ol Chiki is an Austroasiatic-Santali language used by the Santhal tribe of India. Despite being one of the official languages of India, Ol Chiki language still remains marginalized. Although there exist significant amount of work on recognizing handwritten characters of several other mainstream Indian languages (e.g. Hindi, Bengali etc.), very less number of work have been carried out for this language. In this work, a robust Handwritten Ol Chiki Character Recognition (HOCCR) system based on Deep learning has been proposed. Efficacy of the Histogram of Oriented Gradient (HOG) feature descriptor for recognizing Ol Chiki characters has been shown. A detailed comparative study has been carried out using several proposed prediction models.
Databáze: OpenAIRE