Currently, owing to the ubiquity of mobile devices, online handwritten Chinese character recognition (HCCR) has become one of the suitable choice for feeding input to cell phones and tablet devices. Over the past few years, larger and deeper convolutional neural networks (CNNs) have extensively been employed for improving character recognition performance. However, its substantial storage requirement is a significant obstacle in deploying such networks into portable electronic devices. To circumvent this problem, we propose a novel technique called DropWeight for pruning redundant connections in the CNN architecture. It is revealed that the proposed method not only treats streamlined architectures such as AlexNet and VGGNet well but also exhibits remarkable performance for deep residual network and inception network. We also demonstrate that global pooling is a better choice for building very compact online HCCR systems. Experiments were performed on the ICDAR-2013 online HCCR competition dataset using our proposed network, and it is found that the proposed approach requires only 0.57 MB for storage, whereas state-of-the-art CNN-based methods require up to 135 MB; meanwhile the performance is decreased only by 0.91%.

提出一种称为DropWeight的新技术，可以修剪卷积神经网络中的冗余连接，从而在ICDAR-2013在线手写字符识别竞争数据集上获得出色的性能，仅需0.57 MB的存储空间，并仅降低0.91％的性能，而全局池化是构建非常紧凑的在线HCCR系统的更好选择。

使用DropWeight与全局池化的在线手写汉字识别非常紧凑的CNN分类器设计