• K.Sandeep
• L.Govardhana Rao
• M.Kushma
• K.Himani
• Y.Dorayya Chowdary

Handwritten text Recognition (HTR) is an automatic way to convert text image into text form. There is a main approach for handwritten text Recognition (HTR) is Artificial Neural Networks (ANNs). ANN gets its inputs in the form of feature vectors. Every feature or property is separated and assigned a numerical value that can be used to identify a character called its vector. Vector database is usually utilized to train the network so that each character can be effectively getting recognized on the basis of its topological properties. Artificial neural network is a powerful data modeling tool that is able to capture and represent complex input/output relationships. ANN is high noise tolerant recognition system. It consists of Convolutional Neural Network (CNN) layers, Recurrent Neural Network (RNN) layers and a Connectionist temporal Classification (CTC).CNN layers to extract features from the input image, which applies a filter kernel of size 5x5 in the first two layers and 3x3 in the last three layers to the input. RNN layers to propagate information through the image. The RNN outputs a matrix which contains a probability distribution over the characters at each image position .Decoding this matrix yields the final text and is done by the connectionist temporal classification operation (CTC).

Handwritten Character Recognition,Artificial Neural Network, Back Propagation.

"Automated tool to convert handwritten text image into text", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.387-390, March-2019, Available :http://www.jetir.org/papers/JETIR1903C55.pdf

"Automated tool to convert handwritten text image into text", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp387-390, March-2019, Available at : http://www.jetir.org/papers/JETIR1903C55.pdf