Keyword spotting in handwritten chinese documents using semi-markov conditional random fields
Zhang, Heng1; Zhou, Xiang-Dong2; Liu, Cheng-Lin3
2017-02-01
发表期刊ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
卷号58页码:49-61
文章类型Article
摘要This paper proposes a document indexing method for keyword spotting based on semi-Markov conditional random fields (semi-CRFs), which provide a theoretical framework for fusing the information of different contexts. The candidate segmentation-recognition lattice is first augmented based on the linguistic context to improve recognition results. For fast retrieval and to save storage space, the lattice is then purged by a forward backward pruning procedure. In the reduced lattice, we estimate character similarity scores based on the semi-CRF model. The parameters of semi-CRF model are estimated using a binary classification objective, i.e., the cross-entropy (CE) to discriminate candidate characters in the lattice. To locate mis-recognized character instances in the lattice, we use confusing similar characters as proxies and search for proxy-characters in the index file. The proxy-character driven search can significantly improve the performance compared with our previous character-synchronous dynamic search (CSDS) method. Experimental results on the online handwriting database CASIA-OLHWDB justify the effectiveness of the proposed method.
关键词Online Handwritten Chinese Documents Semi-markov Conditional Random Fields Keyword Spotting Proxy-character Driven Search
WOS标题词Science & Technology ; Technology
DOI10.1016/j.engappai.2016.11.006
关键词[WOS]CONTINUOUS SPEECH RECOGNITION ; CHARACTER-RECOGNITION ; TEXT RECOGNITION ; ONLINE ; MODEL ; SEGMENTATION ; RETRIEVAL
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China (NSFC)(61403385 ; 61273269)
WOS研究方向Automation & Control Systems ; Computer Science ; Engineering
WOS类目Automation & Control Systems ; Computer Science, Artificial Intelligence ; Engineering, Multidisciplinary ; Engineering, Electrical & Electronic
WOS记录号WOS:000392684200004
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/14365
专题模式识别国家重点实验室_模式分析与学习
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Intelligent Media Tech Res Ctr, Chongqing 400714, Peoples R China
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Zhang, Heng,Zhou, Xiang-Dong,Liu, Cheng-Lin. Keyword spotting in handwritten chinese documents using semi-markov conditional random fields[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,2017,58:49-61.
APA Zhang, Heng,Zhou, Xiang-Dong,&Liu, Cheng-Lin.(2017).Keyword spotting in handwritten chinese documents using semi-markov conditional random fields.ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,58,49-61.
MLA Zhang, Heng,et al."Keyword spotting in handwritten chinese documents using semi-markov conditional random fields".ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 58(2017):49-61.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang, Heng]的文章
[Zhou, Xiang-Dong]的文章
[Liu, Cheng-Lin]的文章
百度学术
百度学术中相似的文章
[Zhang, Heng]的文章
[Zhou, Xiang-Dong]的文章
[Liu, Cheng-Lin]的文章
必应学术
必应学术中相似的文章
[Zhang, Heng]的文章
[Zhou, Xiang-Dong]的文章
[Liu, Cheng-Lin]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。