ICDAR 2011 Chinese Handwriting Recognition Competition
Authors:
- Cheng-Lin LiuCLCheng-Lin Liu
- Fei YinFYFei Yin
- Qiu-Feng WangQWQiu-Feng Wang
- Da-Han WangDWDa-Han Wang
- 1 September 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15205363,p. 1464-1469
Abstract
In the Chinese handwriting recognition competition organized with the ICDAR 2011, four tasks were evaluated: offline and online isolated character recognition, offline and online handwritten text recognition. To enable the training of recognition systems, we announced the large databases CASIA-HWDB/OLHWDB. The submitted systems were evaluated on un-open datasets to report character-level correct rates. In total, we received 25 systems submitted by eight groups. On the test datasets, the best results (correct rates) are 92.18% for offline character recognition, 95.77% for online character recognition, 77.26% for offline text recognition, and 94.33% for online text recognition, respectively. In addition to the evaluation results, we provide short descriptions of the recognition methods and have brief discussions.Keywords
This publication has 14 references indexed in Scilit:
- CASIA Online and Offline Chinese Handwriting Databases2011
- Deep, Big, Simple Neural Nets for Handwritten Digit RecognitionNeural Computation, 2010
- Recognition of Handwritten Chinese Characters by Combining Regularization, Fisher's Discriminant and Distorted Sample Generation2009
- Building compact MQDF classifier for large character set recognition by subspace distribution sharingPattern Recognition, 2008
- Gabor feature extraction for character recognition: comparison with gradient feature2005
- Offline recognition of unconstrained handwritten texts using HMMs and statistical language modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Handwritten digit recognition: investigation of normalization and feature extraction techniquesPattern Recognition, 2004
- Two-dimensional extension of nonlinear normalization method using line density for character recognition2002
- HANDWRITTEN CHINESE CHARACTER RECOGNITION WITH DIRECTIONAL DECOMPOSITION CELLULAR FEATURESJournal of Circuits, Systems and Computers, 1998
- Modified Quadratic Discriminant Functions and the Application to Chinese Character RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1987