Open access
Aug 2026
Improved Recognition of Telugu Handwritten Characters Through Synthetic Data Generation and Attention-Based Modelling
The proposed system outperforms several current CNN-, RNN-, and heuristic-based techniques, achieving character recognition accuracy of 97.89% and word recognition accuracy of 97.34%, and confirms the efficacy of integrating transformer-based learning with generative AI.
Padmavathi Pragada, D. Ch
· Engineering Research Express · 0 citations