Handwriting Style Mixture Adaptation

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

	Handwriting Style Mixture Adaptation
	Hong-Ming Yang; Xu-Yao Zhang; Fei Yin; Cheng-Lin Liu
	2017
会议名称	International Conference on Document Analysis and Recognition (ICDAR)
会议日期	2017-11
会议地点	Kyoto, Japan
摘要	In handwriting recognition, the test data usually come from multiple writers which are not shown in the training data. Therefore, adapting the base classifier towards the new style of each writer can significantly improve the generalization performance. Traditional writer adaptation methods usually assume that there is only one writer (one style) in the test data, and we call this situation as style-clear adaptation. However, a more common situation is that multiple handwriting styles exist in the test data, which is widely appeared in multi-font documents and handwriting data produced by the cooperation of multiple writers. We call the adaptation in this situation as style-mixture adaptation. To deal with this problem, in this paper, we propose a novel method called K-style mixture adaptation (K-SMA) with the assumption that there are totally K styles in the test data. Specifically, we first partition the test data into K groups (style clustering) according to their style consistency, which is measured by a newly designed style feature that can eliminate class (category) information and keep handwriting style information. After that, in each group, a style transfer mapping (STM) is used for writer adaptation. Since the initial style clustering may be not reliable, we repeat this process iteratively to improve the adaptation performance. The K-SMA model is fully unsupervised which do not require either the class label or the style index. Moreover, the K-SMA model can be effectively combined with the benchmark convolutional neural network (CNN) models. Experiments on the online Chinese handwriting database CASIAOLHWDB demonstrate that K-SMA is an efficient and effective solution for style-mixture adaptation.
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/19982
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. Handwriting Style Mixture Adaptation[C],2017.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
PID4958969.pdf（294KB）	会议论文		开放获取	CC BY-NC-SA	浏览