Deep LSTM Networks for Online Chinese Handwriting Recognition

Currently two heavy burdens are borne in online Chinese handwriting recognition: a large-scale training data needs to be annotated with the boundaries of each character and effective features should be handcrafted by domain experts. To relieve such issues, the paper presents a novel end-to-end recognition method based on recurrent neural networks. A mixture architecture of deep bidirectional Long Short-Term Memory (LSTM) layers and feed forward subsampling layers is used to encode the long contextual history trajectories. The Connectionist Temporal Classification (CTC) objective function makes it possible to train the model without providing alignment information between input trajectories and output strings. During decoding, a modified CTC beam search algorithm is devised to integrate the linguistic constraints wisely. Our method is evaluated both on test set and competition set of CASIA-OLHWDB 2. x. Comparing with state-of-the-art methods, over 30% relative error reductions are observed on test set in terms of both correct rate and accurate rate. Even to the more challenging competition set, better results can be achieved by our method if the out-of-vocabulary problem can be ignored.