Unsupervised adaptation of neural networks for Chinese handwriting recognition

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Unsupervised adaptation of neural networks for Chinese handwriting recognition
	Hong-Ming Yang; Xu-Yao Zhang; Fei Yin; Zhenbo Luo; Cheng-Lin Liu
	2016
会议名称	International Conference on Frontiers in Handwriting Recognition (ICFHR)
会议录名称	International Conference on Frontiers in Handwriting Recognition (ICFHR)
会议日期	October 23-26
会议地点	Shenzhen, China
摘要	Writer adaptation is an important topic in handwriting recognition, which can further improve the performance of writer-independent recognizer. In this paper, we propose combining the neural network classifier with style transfer mapping (STM) for unsupervised writer adaptation, which only require writer-specific unlabeled data, and therefore is more common and efficient compared to supervised adaptation. We use some techniques like dropout, ReLU, momentum, and deeply supervised strategy to improve the performance of the neural network classifier. For a specific writer in the test data, an adaptation layer is added to the pre-trained neural network classifier. In adaptation process, only the parameters in adaptation layer are updated while other parameters of the neural network are kept unchanged. To train the adaptation layer, we use the same technology as STM learning but redefine the source point set, target point set and the corresponding confidence. Experiments on the online Chinese handwriting database CASIA-OLHWDB1.1 demonstrate that our method is very efficient and effective in improving classification accuracy. The experimental results also show that our proposed method outperforms the previous proposed learning vector quantization (LVQ) and modified quadratic discriminant function (MQDF) with STM methods for writer adaptation.
关键词	Adaptation
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12469
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	Cheng-Lin Liu
作者单位	中科院自动化所
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Hong-Ming Yang,Xu-Yao Zhang,Fei Yin,et al. Unsupervised adaptation of neural networks for Chinese handwriting recognition[C],2016.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
PID4396673.pdf（291KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载