End-to-end Handwritten Chinese Paragraph Text Recognition Using Residual Attention Networks

Abstract

Handwritten Chinese recognition which involves variant writing style, thousands of character categories and monotonous data mark process is a longterm focus in the field of pattern recognition research. The existing methods are facing huge challenges including the complex structure of character/line-touching, the discriminate ability of similar characters and the labeling of training datasets. To deal with these challenges, an end-to-end residual attention handwritten Chinese paragraph text recognition method is proposed, which uses fully convolutional neural networks as the main structure of feature extraction and employs connectionist temporal classification as a loss function. The novel residual attention gate block is more helpful in extracting essential features and making the training of deep convolutional neural networks more effective. In addition, we introduce the operations of batch bilinear interpolation which implement the mapping of two dimension text representation to one dimension text line representation without any position information of characters or text lines, and greatly reduce the labeling workload in preparing training datasets. In experimental, the proposed method is verified with two widely adopted handwritten Chinese text datasets, and achieves competitive results to the current state-of-the-art methods. Without using any position information of characters and text line, an accuracy rate of 90.53% is obtained in CASIA-HWDB test set.

An Efficient Hybrid Model for Arabic Text Recognition

“…This work presents a hybrid deep learning model that uses a convolutional neural network (CNN) and a bidirectional short-term memory network (BLSTM) and it operates without requiring segmentation. Primarily, CNN and RNN algorithms have been widely used for text recognition [4]. Several studies have shown that convolutional neural networks and recurrent neural networks (RNNs) are superior to Hidden Markov Models (HMMs) for sequence labeling tasks such as handwriting and speech recognition [5] in addition, RNN long-term short-term memory (LSTM) architecture allows it to capture longer contexts, which are important for the recognition of offline text tasks.…”