Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
Zecheng Xie, Zenghui Sun, Lianwen Jin et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2017
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 percent, respectively, which are significantly better than the best result reported thus far in the literature.
Cited by 127 works. doi:10.1109/tpami.2017.2732978 Open-access PDF
Authors
References
- Deep Residual Learning for Image Recognition
- Long Short-Term Memory
- Distinctive Image Features from Scale-Invariant Keypoints
- Going deeper with convolutions
- Fully convolutional networks for semantic segmentation
- Caffe
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Sequence to Sequence Learning with Neural Networks
- Neural Machine Translation by Jointly Learning to Align and Translate
- Identity Mappings in Deep Residual Networks