DenseRAN for Offline Handwritten Chinese Character Recognition

Recently, great success has been achieved in offline handwritten Chinese character recognition by using deep learning methods. Chinese characters are mainly logographic and consist of basic radicals, however, previous research mostly treated each Chinese character as a whole without explicitly considering its internal two-dimensional structure and radicals. In this study, we propose a novel radical analysis network with densely connected architecture (DenseRAN) to analyze Chinese character radicals and its two-dimensional structures simultaneously. DenseRAN first encodes input image to high-level visual features by employing DenseNet as an encoder. Then a decoder based on recurrent neural networks is employed, aiming at generating captions of Chinese characters by detecting radicals and two-dimensional structures through attention mechanism. The manner of treating a Chinese character as a composition of two-dimensional structures and radicals can reduce the size of vocabulary and enable DenseRAN to possess the capability of recognizing unseen Chinese character classes, only if the corresponding radicals have been seen in training set. Evaluated on ICDAR-2013 competition database, the proposed approach significantly outperforms whole-character modeling approach with a relative character error rate (CER) reduction of 18.54%. Meanwhile, for the case of recognizing 3277 unseen Chinese characters in CASIA-HWDB1.2 database, DenseRAN can achieve a character accuracy of about 41% while the traditional whole-character method has no capability to handle them.

[1]  Fei Yin,et al.  CASIA Online and Offline Chinese Handwriting Databases , 2011, 2011 International Conference on Document Analysis and Recognition.

[2]  Fei Yin,et al.  Radical-Based Chinese Character Recognition via Multi-Labeled Learning of Deep Residual Networks , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[3]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[4]  Kyunghyun Cho,et al.  Natural Language Understanding with Distributed Representation , 2015, ArXiv.

[5]  Jun Du,et al.  Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[6]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[7]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[8]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[9]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[10]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[11]  Dai Ruwei,et al.  Chinese character recognition: history, status and prospects , 2007 .

[12]  Fumitaka Kimura,et al.  Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Dan Ciresan,et al.  Multi-Column Deep Neural Networks for offline handwritten Chinese character classification , 2013, 2015 International Joint Conference on Neural Networks (IJCNN).

[14]  Kuo-Chin Fan,et al.  Optical recognition of handwritten Chinese characters by hierarchical radical matching method , 2001, Pattern Recognit..

[15]  Fei Yin,et al.  Online and offline handwritten Chinese character recognition: Benchmarking on new databases , 2013, Pattern Recognit..

[16]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[17]  Satoshi Naoi,et al.  Beyond human recognition: A CNN-based framework for handwritten character recognition , 2015, 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR).

[18]  Shiliang Zhang,et al.  Watch, attend and parse: An end-to-end neural network based approach to handwritten mathematical expression recognition , 2017, Pattern Recognit..

[19]  Fei Yin,et al.  Handwritten Chinese character recognition with spatial transformer and deep residual networks , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[20]  Jun Du,et al.  Radical Analysis Network for Zero-Shot Learning in Printed Chinese Character Recognition , 2017, 2018 IEEE International Conference on Multimedia and Expo (ICME).

[21]  Lianwen Jin,et al.  High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[22]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[24]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[25]  Cheng-Lin Liu,et al.  A new radical-based approach to online handwritten Chinese character recognition , 2008, 2008 19th International Conference on Pattern Recognition.

[26]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.