Online and offline handwritten Chinese character recognition: Benchmarking on new databases

• Published in: Pattern recognition 2013-01, Vol.46 (1), p.155-162
• Main Authors: Liu, Cheng-Lin, Yin, Fei, Wang, Da-Han, Wang, Qiu-Feng
• Format: Article
• Language: English
• Subjects: Applied sciences; Automation; Benchmarking; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Feature extraction; Handwritten Chinese character recognition; Information, signal and communications theory; Offline; On-line systems; Online; Pattern recognition; Signal and communications theory; Signal processing; Signal representation. Spectral analysis; Signal, noise; Telecommunications and information theory; Training
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2012.06.021

Recently, the Institute of Automation of Chinese Academy of Sciences (CASIA) released the unconstrained online and offline Chinese handwriting databases CASIA-OLHWDB and CASIA-HWDB, which contain isolated character samples and handwritten texts produced by 1020 writers. This paper presents our benchmarking results using state-of-the-art methods on the isolated character datasets OLHWDB1.0 and HWDB1.0 (called DB1.0 in general), OLHWDB1.1 and HWDB1.1 (called DB1.1 in general). The DB1.1 covers 3755 Chinese character classes as in the level-1 set of GB2312-80. The evaluated methods include 1D and pseudo 2D normalization methods, gradient direction feature extraction from binary images and from gray-scale images, online stroke direction feature extraction from pen-down trajectory and from pen lifts, classification using the modified quadratic discriminant function (MQDF), discriminative feature extraction (DFE), and discriminative learning quadratic discriminant function (DLQDF). Our experiments reported the highest test accuracies 89.55% and 93.22% on the HWDB1.1 (offline) and OLHWDB1.1 (online), respectively, when using the MQDF classifier trained with DB1.1. When training with both the DB1.0 and DB1.1, the test accuracies on HWDB1.1 and OLHWDB are improved to 90.71% and 93.95%, respectively. Using DFE and DLQDF, the best results on HWDB1.1 and OLHWDB1.1 are 92.08% and 94.85%, respectively. Our results are comparable to the best results of the ICDAR2011 Chinese Handwriting Recognition Competition though we used less training samples. ► This paper presents an evaluation of state-of-the-art methods on unconstrained Chinese handwriting databases. ► The achieved results are comparable with the ICDAR2011 Competition results though we used less training samples. ► We also provide standard feature data for the evaluation of machine learning and classification algorithms.