International Journal For Multidisciplinary Research

E-ISSN: 2582-2160   •   Impact Factor: 9.24

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

Call for Paper Volume 8, Issue 5 (September-October 2026) Submit your research before last 3 days of October to publish your research paper in the issue of September-October.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 8 Issue 5
September-October 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

High-Resolution U-Net Restoration of Degraded Tamil Palm-Leaf Manuscripts

Author(s) Mr. Aravindhan Ravichandran, Dr. Durgadevi P
Country India
Abstract Palm-leaf manuscripts are a primary carrier of Indic literary and scientific heritage, yet ink erosion, worm holes, and missing character blocks make them difficult to digitise. This paper presents a restoration-centric pipeline for Tamil palm-leaf images. Clean scans of 262 leaves from the Naladiyar, Tholkappiyam, and Thirikadugam collections are paired with synthetically damaged counterparts generated by documented OpenCV operators. A 31.04-million-parameter U-Net is trained at a resolution of 384 by 1280 with a hybrid loss of L1 plus 0.5 times the mean squared error, for 30 epochs, on an AMD Instinct MI210 accelerator. The best checkpoint reaches a validation loss of 0.0314 in 28.04 minutes, with a peak allocation of 42.54 GB of graphics memory. Qualitative inference recovers stroke continuity and inverts simulated holes and missing blocks while preserving leaf geometry. A Tesseract Tamil baseline on the printed Mozhi corpus yields a mean character error rate of approximately 0.34 and is treated as a transcription control, not as a palm-leaf reading score. Translation via IndicTrans2 is specified as a planned, not-yet-trained module. The implemented contribution of this work is supervised high-resolution restoration under an explicit, reproducible protocol.
Keywords Palm-Leaf Manuscripts, Document Restoration, U-Net, Synthetic Degradation, Tamil Heritage, Computer Vision, Cultural Heritage Digitisation
Field Engineering
Published In Volume 8, Issue 5, September-October 2026
Published On 2026-10-03
DOI https://doi.org/10.36948/ijfmr.2026.v08i05.88963
View / Download PDF File

Share this



E-ISSN 2582-2160
CrossRef

CrossRef DOI prefix of IJFMR is 10.36948/ijfmr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJFMR
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 +91-9687-828-838 editor@ijfmr.com
Powered by Sky Research Publication and Journals