Convolutional neural network (CNN) has achieved tremendous success in handwritten Chinese character recognition (HCCR). However, most CNN-based HCCR research nowadays focus on complicated and deep CNN module, rarely analyzing the whole feature extraction process which has a crucial impact on the final recognition rate. In this paper, the following two questions are answered: (1). Information loss is inevitable on the training stage of complex learning problems, but at which layer does the information loss mainly occur; (2). Different layers have different effects on CNN, what is the best place for multistage feature extraction that influences CNN most. We make use of the proposed module in typical CNN and analyze classification results on CASIA-HWDB1.1. It is shown in this paper that, (1). Multi-stage feature extraction achieves better performance on HCCR than single stage feature extraction. (2). Multi-stage feature extraction should be designed at the convolution layer rather than the pooling layer. (3). Multi-stage feature extraction designed at shallow layers outperforms that designed at deeper layers. By analyzing the structure of multistage feature extraction, we propose an appropriate CNN approach to HCCR, which achieves a new state-of-the-art recognition accuracy of 91.89 %.
CITATION STYLE
Wu, X., Shu, C., & Zhou, N. (2016). Multi-stage feature extraction in offline handwritten Chinese character recognition. In Communications in Computer and Information Science (Vol. 663, pp. 474–485). Springer Verlag. https://doi.org/10.1007/978-981-10-3005-5_39
Mendeley helps you to discover research relevant for your work.