A Novel Artificial Intelligence Approach to Optical Character Recognition of Conjunct Gujarati Script

Dhananjay Patel, Himanshu Maniar and Jagin Patel

International Journal of Scientific Research in Science and Technology, 2025, vol. 12, issue 5, 35-41

Abstract: This paper surveys recent advances in optical char- acter recognition (OCR) for the Gujarati script, with a focus on complex conjunct characters. Gujarati is an Indo-Aryan script spoken by ∼62 million people [1], [2], yet its OCR remains challenging due to intricate glyph shapes and extensive consonant clusters [3], [4]. We review how machine learning (ML), deep learning (DL), and NLP techniques have been applied to segment and recognize Gujarati text, especially conjunct lig- atures. Notable studies from 2012–2025 are examined, including ANN and CNN-based classifiers that achieve high accuracy on isolated conjuncts [3], [5]. Finally, ongoing challenges (data scarcity, variability of handwriting and fonts) and outline future directions such as transformer models and language-model integration for Gujarati OCR.

Keywords: Gujarati OCR; conjunct characters; machine learning; deep learning; natural language processing; Indic script recognition (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrst.com/home/article/view/IJSRST2513114 Abstract page (text/html)
https://ijsrst.com/home/article/download/IJSRST2513114/IJSRST2513114 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:etm:ijsrst:v12:y2025:i5:id:1141

DOI: 10.32628/IJSRST2513114

Access Statistics for this article

More articles in International Journal of Scientific Research in Science and Technology from Technoscience Academy
Bibliographic data for series maintained by Pankaj Sharma ().