• Dhanush Shetty
• Karthik K
• Prajwal
• Shishir
• Daya Naik

This model presents an innovative deep learning-based AI model designed for the real-time recognition of handwritten sentences, sing advanced neural models like convolutional neural networks (CNNs) and recurrent neural networks (RNNs), enhanced with attention mechanisms. The proposed model incorporates an end-to-end pipeline that processes variable-length input sequences, converts raw handwriting to a digital text-based format and this model is going to be extremely useful in doing basic tasks like data entry, keeping receipts, maintaining medical records. The model is trained on a diverse dataset of handwritten text and employs transfer learning to adapt to user-specific handwriting styles. We deployed the model which produce a result for the raw handwritten text image input into a digitally converted text. The deployment of this model in real-world scenarios, such as smart note-taking applications, etc. Future work focuses on expanding the models adaptability to multilingual handwriting and continuous learning capabilities.

Handwriting Recognition, Deep Learning, CNN, RNN, CTC, Natural Language Processing, Real-Time Processing, Optical Character Recognition, Sentence Interpretation, Multilingual Support

"Real Time Handwritten Sentence Interpretation System Using Deep Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.645-648, July-2025, Available :http://www.jetir.org/papers/JETIRGX06123.pdf

"Real Time Handwritten Sentence Interpretation System Using Deep Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp645-648, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06123.pdf