Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 40, Issue 8, Pages 1903-1917Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2017.2732978
Keywords
Handwritten Chinese text recognition; path signature; residual recurrent network; multiple spatial contexts; implicit language model
Funding
- NSFC [61472144, 61673182]
- National Key Research & Development Plan of China [2016YFB1001405]
- GDSTP [2015B010101004, 2015B010130003]
- GZSTP [201607010227]
- Alan Turing Institute under the EPSRC [EP/N510129/1]
- ERC advanced grant ESig [291244]
- Alan Turing Institute [TU/B/000039, TU/B/000085] Funding Source: researchfish
- Engineering and Physical Sciences Research Council [EP/N510129/1] Funding Source: researchfish
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available