Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

An IoT based remote medical diagnosis system using one time pad cipher over MQTT protocol.

Scientific reports·2025
Same author

Bio-inspired feature selection for early diagnosis of Parkinson's disease through optimization of deep 3D nested learning.

Scientific reports·2024
Same author

Real-time visual intelligence for defect detection in pharmaceutical packaging.

Scientific reports·2024
Same author

Implementation of explainable artificial intelligence in commercial communication systems using micro systems.

Science progress·2023
Same author

An Energy-Efficient and Blockchain-Integrated Software Defined Network for the Industrial Internet of Things.

Sensors (Basel, Switzerland)·2022
Same author

Cybercrime: Identification and Prediction Using Machine Learning Techniques.

Computational intelligence and neuroscience·2022

Related Experiment Video

Updated: Sep 29, 2025

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
05:58

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Published on: March 11, 2021

4.7K

A Deep Learning Approach for Recognizing the Cursive Tamil Characters in Palm Leaf Manuscripts.

Gayathri Devi S1, Subramaniyaswamy Vairavasundaram1, Yuvaraja Teekaraman2

  • 1School of Computing, SASTRA Deemed University, Thanjavur 613401, India.

Computational Intelligence and Neuroscience
|March 21, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a novel Convolutional Neural Network (CNN) for recognizing Tamil characters in ancient palm leaf manuscripts. The developed CNN achieved 94% accuracy, outperforming existing methods for digital transcription.

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.8K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K

Related Experiment Videos

Last Updated: Sep 29, 2025

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
05:58

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Published on: March 11, 2021

4.7K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.8K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K

Area of Science:

  • Digital Humanities
  • Computer Vision
  • Natural Language Processing

Background:

  • Palm leaf manuscripts represent a vast, yet largely inaccessible, repository of ancient Tamil literature and knowledge.
  • The cursive nature of script in these manuscripts poses significant challenges for accurate digital transcription and preservation.
  • Digitalization efforts are crucial for safeguarding and studying this invaluable cultural heritage.

Purpose of the Study:

  • To develop and evaluate a robust method for automatically recognizing cursive Tamil characters from palm leaf manuscripts.
  • To improve the accuracy and efficiency of transcribing historical Tamil texts.
  • To leverage deep learning for the preservation and accessibility of ancient manuscripts.

Main Methods:

  • A unique Convolutional Neural Network (CNN) model was designed and trained on Tamil palm leaf characters.
  • Image preprocessing involved morphological operations for noise reduction.
  • Text Line Slicing segmentation was employed to isolate individual characters.
  • Feature extraction included analysis of text line spacing and character spacing (with and without obstacles).

Main Results:

  • The proposed CNN model achieved a classification accuracy of 94% on cursive Tamil palm leaf characters.
  • This performance surpasses existing deep learning techniques, such as ResNet, which achieved 88% accuracy.
  • The study demonstrates the effectiveness of the CNN in handling the complexities of manuscript character recognition.

Conclusions:

  • The developed CNN-based approach offers a significant advancement in the automated recognition of Tamil characters from palm leaf manuscripts.
  • This technology can greatly facilitate the digitalization and transcription of historical Tamil texts, enhancing accessibility for research and cultural preservation.
  • The findings highlight the potential of deep learning in addressing challenges within digital humanities and historical document analysis.