• Mr. P. Karthikeyan
• Moulishwar VS
• Mahendra Kumar V
• Srihariharan A

This survey paper navigates the realm of handwritten character recognition, converging pattern recognition and computer vision. Current RNN-CNN hybrid methods achieve a commendable 91.5% accuracy in predicting characters but exhibit limitations in recognizing entire lines of text. Our innovative system introduces a paradigm shift by adopting a line-by-line recognition approach, enhancing context awareness through integrating the GRU algorithm. A strategic collaboration with the IAM dataset facilitates robust training and enables error detection and correction, elevating the accuracy and reliability of handwritten text recognition. This holistic approach signifies a commitment to advancing recognition systems beyond isolated characters, ushering in a new era of context-aware text recognition.

Handwriting Recognition, Recurrent Neural Network, Gated Recurrent Unit, IAM Dataset.

"SURVEY ON HANDWRITTEN CHARACTER RECOGNITION USING RNN-GRU ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 1, page no.a464-a471, January-2024, Available :http://www.jetir.org/papers/JETIR2401055.pdf

"SURVEY ON HANDWRITTEN CHARACTER RECOGNITION USING RNN-GRU ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 1, page no. ppa464-a471, January-2024, Available at : http://www.jetir.org/papers/JETIR2401055.pdf