Systems and methods for end-to-end handwritten text recognition using neural networks

Abstract

The present disclosure provides systems and methods for end-to-end handwritten text recognition using neural networks. Most existing hybrid architectures involve high memory consumption and large number of computations to convert an offline handwritten text into a machine readable text with respective variations in conversion accuracy. The method combine a deep convolutional neural network (CNN) with a RNN (Recurrent Neural Network) based encoder unit and decoder unit to map a handwritten text image to a sequence of characters corresponding to text present in the scanned handwritten text inputimage. The deep CNN is used to extract features from handwritten text image whereas the RNN based encoder unit and decoder unit is used to generate converted text as a set of characters. The disclosed method requires less memory consumption and less number of computations with better conversion accuracy over the existing hybrid architectures.

Description

[0001] priority claim [0002] This application claims priority from Indian Patent Application No. 201821026934 filed on July 19, 2018. The entire content of the above application is hereby incorporated by reference. technical field [0003] The disclosure herein relates generally to handwritten text recognition in an offline mode, and more particularly, to systems and methods for end-to-end handwritten text recognition using neural networks. Background technique [0004] Offline Handwritten Text Recognition (HTR) from scanned images of handwritten text is an important problem for enterprises trying to digitize large volumes of handwritten scanned documents or reports in the current digital world. Offline Handwritten Text Recognition (HTR) is more challenging than the online mode, which utilizes attributes such as stroke information and trajectories in addition to text images, while the offline mode only has documents available for feature extraction / reported text image. ...

AI Technical Summary

Problems solved by technology

However, the representation is computationally expensive compared to standard convolution operations that extract the same visual features

Images