Handwriting Recognition Based on Temporal Order Restored by the End-to-End System

Abstract

In this paper, we present an original framework for offline handwriting recognition. Our developed recognition system is based on Sequence to Sequence model employing the encoder decoder LSTM, for recovering temporal order from offline handwriting. Handwriting temporal recovery consists of two parts which are respectively extracting features using a Convolution Neural Network (CNN) followed by an LSTM layer and decoding the encoded vectors to generate temporal information using BLSTM. To produce a human-like velocity, we make a Sampling operation by the consideration of trajectory curvatures. Our work is validated by the LSTM recognition system based on Beta Elliptic model that is applied on Arabic and Latin On/Off dual handwriting character database.