Poornimathi-k/Tamil-Inscription: Robust Recognition of Tamil Inscription Letters Using a Hybrid Model Combining Recurrent Neural Networks, Graph Neural Networks, and Attention Mechanisms
Abstract
This release contains the implementation of the hybrid deep learning model proposed for recognizing ancient Tamil inscription letters and mapping them to modern Tamil characters.The framework combines Convolutional Neural Networks (CNN), Graph Neural Networks (GNN), Recurrent Neural Networks (RNN), and Attention mechanisms to improve recognition accuracy for degraded inscription images.The repository includes the code for preprocessing, segmentation, feature extraction, and character recognition used in the research study titled:"Robust Recognition of Tamil Inscription Letters Using a Hybrid Model Combining Recurrent Neural Networks, Graph Neural Networks, and Attention Mechanisms."This release corresponds to version v1.0 of the implementation used in the study.
Fields of Study & Subjects
Handwritten Text Recognition Techniques
Vehicle License Plate Recognition
Advanced Neural Network Applications
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 6 March 2026
- Language
- EN