Published on Mon Apr 18 2016

Fully Convolutional Recurrent Network for Handwritten Chinese Text Recognition

Zecheng Xie, Zenghui Sun, Lianwen Jin, Ziyong Feng, Shuye Zhang

The FCRN is end-to-end trainable in contrast to conventional methods whose components are separately trained and tuned. We evaluate the performance of the proposed method on the test sets from the CASIA-OLHWDB and ICDAR 2013 Chinese handwriting recognition competition.

0
0
0
Abstract

This paper proposes an end-to-end framework, namely fully convolutional recurrent network (FCRN) for handwritten Chinese text recognition (HCTR). Unlike traditional methods that rely heavily on segmentation, our FCRN is trained with online text data directly and learns to associate the pen-tip trajectory with a sequence of characters. FCRN consists of four parts: a path-signature layer to extract signature features from the input pen-tip trajectory, a fully convolutional network to learn informative representation, a sequence modeling layer to make per-frame predictions on the input sequence and a transcription layer to translate the predictions into a label sequence. The FCRN is end-to-end trainable in contrast to conventional methods whose components are separately trained and tuned. We also present a refined beam search method that efficiently integrates the language model to decode the FCRN and significantly improve the recognition results. We evaluate the performance of the proposed method on the test sets from the databases CASIA-OLHWDB and ICDAR 2013 Chinese handwriting recognition competition, and both achieve state-of-the-art performance with correct rates of 96.40% and 95.00%, respectively.

Sun Oct 09 2016
Computer Vision
Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
Online handwritten Chinese text recognition (OHCTR) involves a large-scale character set, ambiguous segmentation, andvariable-length input sequences. We exploit the outstanding ability of path signature to translate online pen-tip trajectories intoformative signature feature maps. A multi-spatial-
0
0
0
Sun Jun 28 2020
Computer Vision
Offline Handwritten Chinese Text Recognition with Convolutional Neural Networks
The offline handwritten Chinese text recognition (HCTR) is one of the most challenging tasks because it involves thousands of characters, variant writing styles and complex data collection process. Deep learning based methods have been dominating the text recognition tasks in different and multilingual scenarios.
0
0
0
Fri Jul 20 2018
Machine Learning
An Efficient End-to-End Neural Model for Handwritten Text Recognition
Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents. In this paper we introduce a novel approach that combines a deep convolutional network with a recurrent Encoder-Decoder network.
0
0
0
Wed Jul 10 2019
Computer Vision
Fully Convolutional Networks for Handwriting Recognition
Handwritten text recognition is challenging because of the virtually infinite ways a human can write the same message. Our fully convolutional handwriting model takes in a handwriting sample of unknown length and outputs an arbitrary stream of symbols.
0
0
0
Wed Dec 09 2020
Computer Vision
Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?
Unconstrained handwritten text recognition remains an important challenge for deep neural networks. Recurrence-free architectures with gated mechanisms have been proposed as one possible alternative to CNN+BLSTM.
0
0
0
Mon Dec 31 2018
Computer Vision
Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks
Unconstrained text recognition is an important computer vision task. In our proposed architecture we strive for simplicity and efficiency without sacrificing recognition accuracy. Our proposed architecture is a fully convolutional network without any recurrent connections trained with the CTC loss function.
0
0
0