Improved Deep Convolutional Neural Network For Online Handwritten Chinese Character Recognition using Domain-Specific Knowledge

Abstract

Deep convolutional neural networks (DCNNs) have achieved great success in various computer vision and pattern recognition applications, including those for handwritten Chinese character recognition (HCCR). However, most current DCNN-based HCCR approaches treat the handwritten sample simply as an image bitmap, ignoring some vital domain-specific information that may be useful but that cannot be learnt by traditional networks. In this paper, we propose an enhancement of the DCNN approach to online HCCR by incorporating a variety of domain-specific knowledge, including deformation, non-linear normalization, imaginary strokes, path signature, and 8-directional features. Our contribution is twofold. First, these domain-specific technologies are investigated and integrated with a DCNN to form a composite network to achieve improved performance. Second, the resulting DCNNs with diversity in their domain knowledge are combined using a hybrid serial-parallel (HSP) strategy. Consequently, we achieve a promising accuracy of 97.20% and 96.87% on CASIA-OLHWDB1.0 and CASIA-OLHWDB1.1, respectively, outperforming the best results previously reported in the literature.

5 pages, 4 figures, 3 tables. Accepted to appear at ICDAR 2015

References in corpus (2)

• Improving neural networks by preventing co-adaptation of feature detectors
• Sparse arrays of signatures for online character recognition

Cited by in corpus (3)

• Toward high-performance online HCCR: a CNN approach with DropDistortion, path signature and spatial stochastic max-pooling
• Skeleton-based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module
• A Generative Model for Multi-Dialect Representation