An Ensemble of Geometric Stemming and Feed-Forward RNN to Translate Brahmi Script into Indian Regional Language

Smitha B.N; Divyashree K; Abhishek A Madagaounkar; Tarun A S; Vijay Belavigi; Tilak Somappa Bisanalli

An Ensemble of Geometric Stemming and Feed-Forward RNN to Translate Brahmi Script into Indian Regional Language

Author(s)	Prof. Smitha B.N, Prof. Divyashree K, Mr. Abhishek A Madagaounkar, Mr. Tarun A S, Mr. Vijay Belavigi, Mr. Tilak Somappa Bisanalli
Country	India
Abstract	The computational linguistics field is changing fast. Translating ancient Brahmi script is a new way of preserving history. It is different from standard Optical Character Recognition (OCR) methods. An ensemble of geometric streaming and feed-forward Recurrent Neural Networks (RNN) can help reduce processing time and map phonetics efficiently. This project compares conventional OCR with our ensemble neural method. We look at how accurate they are, how well they map characters, and how much computational power they cost. The main challenge is understanding how degraded ancient scripts work. They are not the same as modern digital text. We made special synthetic image datasets for training. We tested them to see how accurate they are. We also used computers to simulate how these ensemble algorithms behave on raw stone inscriptions. We found that the ensemble approach has some advantages. It can recognize complex shapes and can translate quickly. It needs to be done carefully to make sure the translation to regional languages is accurate. This project helps researchers understand how to use deep learning in epigraphic design.
Keywords	Brahmi Script Translation, Deep Learning, Pattern Recognition, Natural Language Processing (NLP), Image Processing, Character Segmentation.
Published In	Volume 7, Issue 4, July-August 2026
Published On	2026-08-12

View / Download PDF File

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

An Ensemble of Geometric Stemming and Feed-Forward RNN to Translate Brahmi Script into Indian Regional Language

Share this