激光与光电子学进展, 2020, 57 (8): 081002, 网络出版: 2020-04-03
基于注意力机制的手写体中文字符识别 下载: 1214次
Handwritten Chinese Character Recognition Based on Attention Mechanism
手写体中文 卷积神经网络(CNN) 注意力机制 注意力-CNN模型(AT-CNN模型) handwritten Chinese convolutional neural network(CNN) attention mechanism attention-CNN model (AT-CNN model)
摘要
手写体中文的自动识别在文档数字化、手写笔记转录等方面有广泛应用。针对其具有的书写随意、结构复杂、数目众多等特点,提出了一种基于注意力机制的手写体中文识别方法。在卷积神经网络(CNN)模型的基础上,搭建了一种AT(Attention)-CNN网络模型,利用注意力机制实现网络层之间的信息交互,减少了因池化操作导致的信息丢失。在经典手写体中文数据集HWDB上进行实验,结果表明,该方法的识别准确率可以达到95.05%,相比其他模型有显著提升。
Abstract
Automatic recognition of handwritten Chinese has a wide range of applications in document digitization and handwritten note transcription. A method based on attention mechanism is proposed to recognize the handwritten Chinese characterized by their random writing, complex structure, and large number of features. Based on the traditional convolutional neural network (CNN) model, an attention-CNN (AT-CNN) model is proposed. The information interaction between each layer in the network is realized using attention mechanism, thus the information loss caused by pooling operations reduces. Experiments on the classical handwritten Chinese data set HWDB show that the recognition accuracy of this method can reach 95.05%, which is significantly improved compared with that by other models.
黄婉蓉, 何凯, 刘坤, 高圣楠. 基于注意力机制的手写体中文字符识别[J]. 激光与光电子学进展, 2020, 57(8): 081002. Wanrong Huang, Kai He, Kun Liu, Shengnan Gao. Handwritten Chinese Character Recognition Based on Attention Mechanism[J]. Laser & Optoelectronics Progress, 2020, 57(8): 081002.