Back to Search
Start Over
Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition.
- Source :
-
IEEE Transactions on Pattern Analysis & Machine Intelligence . Aug2018, Vol. 40 Issue 8, p1903-1917. 15p. - Publication Year :
- 2018
-
Abstract
- 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. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 01628828
- Volume :
- 40
- Issue :
- 8
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Pattern Analysis & Machine Intelligence
- Publication Type :
- Academic Journal
- Accession number :
- 130457384
- Full Text :
- https://doi.org/10.1109/TPAMI.2017.2732978