Handwritten Chinese character recognition, including online (stroke trajectory-based) and offline (image-based) recognition, have received intensive attention. Despite the tremendous advances and successful applications, there still remain big challenges, particularly in unconstrained handwriting recognition. To promote the performance, research efforts are needed to design new methods, and databases of unconstrained handwriting are needed for benchmarking. In recent years, many competitions of handwriting recognition have been effective to attract research attention and promote the technology. Particularly, we see evident increase of performance of Chinese handwriting recognition over time from the Contest at 2010 Chinese Conference on Pattern Recognition (CCPR 2010)  and the Contest at ICDAR2011 .
To evaluate the state of the art of Chinese handwriting recognition, we propose to organize a new round of Chinese Handwriting Recognition Competition at the 12th International Conference on Document Analysis and Recognition (ICDAR 2013).
The Chinese Handwriting Recognition Competition 2013 has five tasks:
1. Classification on Extracted Feature Data (Task 1)
2. Offline Chinese Character Recognition (Task 2)
3. Online Chinese Character Recognition (Task 3)
4. Offline Handwritten Text Recognition (Task 4)
5. Online Handwritten Text Recognition (Task 5)
Participations in any one or multiple tasks are welcome. Performance evaluation and system ranking will be based on single task, i.e., each task will be evaluated and ranked separately.
For isolated character recognition (Task1, Task 2 and Task 3), the character set is confined as the set of 3,755 Chinese characters (level-1 set of GB2312-80), which is often tested in Chinese character recognition research. The participating systems will be ranked according to the character recognition accuracies:
Where NC is the number of correctly recognized samples, and NI is the total number of test samples. We report the top-rank correct rate as well as the cumulated correct rate of top 10 classes.
For handwritten text recognition (Task 4 and Task 5), we will provide text page images (in the case of online recognition, page ink data) with the text lines segmented, such that the participants do not have to deal with text line segmentation. The participating systems will be evaluated in respect of correct rate (CR) and accurate rate (AR) over all the text lines in the test dataset :
where Nt is the total number of characters in the ground-truth texts, the numbers of substitution errors( Se ), deletion errors( De )and insertion errors( Ie )are obtained by error-correcting string matching by dynamic programming (DP). The accurate rate AR takes into account the inserted characters, and can be negative if the text lines are seriously over-segmented.
For all tasks, additional statistics of program size (including the storage size of classifier parameters) and recognition speed on a standard computing platform will be reported as well.
Note: The Task 1 is new. It allows the participant to focus on classification and learning algorithm, without need to fine tune the preprocessing and feature extraction techniques. The evaluation of classification algorithms is meaningful for the document recognition field since the character classifier always plays a crucial role in Chinese handwriting recognition. We will provide extracted feature data using state-of-the-art feature extraction methods on both training and test samples. The feature data of some standard datasets is now available on our database webpage.
 Cheng-Lin Liu, Fei Yin, Da-Han Wang, Qiu-Feng Wang, Chinese Handwriting Recognition Contest 2010, Proc. 2010 Chinese Conf. Pattern Recognition (CCPR), Chongqing, 2010.
 Cheng-Lin Liu, Fei Yin, Qiu-Feng Wang, Da-Han Wang, ICDAR 2011 Chinese Handwriting Recognition Competition. Proc. 11th ICDAR, Beijing, China, 2011, pp. 1464-1469.
 T.-H. Su, T.-W. Zhang, D.-J. Guan, H.-J. Huang, "Off-Line Recognition of Realistic Chinese Handwriting Using Segmentation-Free Strategy, Pattern Recognition, vol.42, no.1, pp.167-182, 2008.
 A. Vinciarelli, S. Bengio, H. Bunke, "Offline Recognition of Unconstrained Handwritten Texts Using HMMs and Statistical Language Models," IEEE Trans. Pattern Anal. Mach. Intell., vol.26, no.6, pp.709-720, Jun, 2004.