中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 模式分析与学习团队
Unsupervised Structure-Texture Separation Network for Oracle Character Recognition

文献类型：期刊论文

作者Wang, Mei3; Deng, Weihong3; Liu, Cheng-Lin1,2
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2022
卷号31页码:3137-3150
关键词Character recognition Bones Adaptation models Training Feature extraction Writing Transforms Oracle character recognition unsupervised domain adaptation feature disentanglement generative adversarial network
ISSN号1057-7149
DOI10.1109/TIP.2022.3165989
通讯作者Deng, Weihong(whdeng@bupt.edu.cn)
英文摘要Oracle bone script is the earliest-known Chinese writing system of the Shang dynasty and is precious to archeology and philology. However, real-world scanned oracle data are rare and few experts are available for annotation which make the automatic recognition of scanned oracle characters become a challenging task. Therefore, we aim to explore unsupervised domain adaptation to transfer knowledge from handprinted oracle data, which are easy to acquire, to scanned domain. We propose a structure-texture separation network (STSN), which is an end-to-end learning framework for joint disentanglement, transformation, adaptation and recognition. First, STSN disentangles features into structure (glyph) and texture (noise) components by generative models, and then aligns handprinted and scanned data in structure feature space such that the negative influence caused by serious noises can be avoided when adapting. Second, transformation is achieved via swapping the learned textures across domains and a classifier for final classification is trained to predict the labels of the transformed scanned characters. This not only guarantees the absolute separation, but also enhances the discriminative ability of the learned features. Extensive experiments on Oracle-241 dataset show that STSN outperforms other adaptation methods and successfully improves recognition performance on scanned data even when they are contaminated by long burial and careless excavation.
WOS关键词BONE
资助项目National Natural Science Foundation of China[61871052] ; National Natural Science Foundation of China[62192784]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000784189200003
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/48319]  
专题自动化研究所_模式识别国家重点实验室_模式分析与学习团队
通讯作者Deng, Weihong
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
3.Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Pattern Recognit & Intelligent Syst Lab, Beijing 100876, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Mei,Deng, Weihong,Liu, Cheng-Lin. Unsupervised Structure-Texture Separation Network for Oracle Character Recognition[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:3137-3150.
APA Wang, Mei,Deng, Weihong,&Liu, Cheng-Lin.(2022).Unsupervised Structure-Texture Separation Network for Oracle Character Recognition.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,3137-3150.
MLA Wang, Mei,et al."Unsupervised Structure-Texture Separation Network for Oracle Character Recognition".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):3137-3150.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。