Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition

Journal article

Online handwritten Chinese text recognition (OHCTR) is a challenging problem as it involves a large-scale character set, ambiguous segmentation, and variable-length input sequences. In this paper, we exploit the outstanding capability of path signature to translate online pen-tip trajectories into informative signature feature maps, successfully capturing the analytic and geometric properties of pen strokes with strong local invariance and robustness. A multi-spatial-context fully convolutional recurrent network (MC-FCRN) is proposed to exploit the multiple spatial contexts from the signature feature maps and generate a prediction sequence while completely avoiding the difficult segmentation problem. Furthermore, an implicit language model is developed to make predictions based on semantic context within a predicting feature sequence, providing a new perspective for incorporating lexicon constraints and prior knowledge about a certain language in the recognition procedure. Experiments on two standard benchmarks, Dataset-CASIA and Dataset-ICDAR, yielded outstanding results, with correct rates of 97.50% and 96.58%, respectively, which are significantly better than the best result reported thus far in the literature.

Authors: Xie, Z; Sun, Z; Jin, L; Ni, H; Lyons, T

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Institute of Electrical and Electronics Engineers
• Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence
• Publication date: 2017-07-28
• Acceptance date: 2017-01-01
• DOI: 10.1109/TPAMI.2017.2732978
• EISSN: 2160-9292
• ISSN: 0162-8828
• Keywords: Trajectory; multiple spatial contexts; Hidden Markov models; Context modeling; Semantics; Robustness; residual recurrent network; Text recognition; path signature; Feature extraction; implicit language model; Handwritten Chinese text recognition