Title extraction and generation from OCR'd documents

被引：0
|
作者：
Taghva, Kazem [1 ]
Condit, Allen [1 ]
Lumos, Steve [1 ]
Borsack, Julie [1 ]
Nartker, Thomas [1 ]
机构：
[1] Univ Nevada, Informat Sci Res Inst, Las Vegas, NV 89154 USA
来源：
DOCUMENT RECOGNITION AND RETRIEVAL XIV | 2007年 / 6500卷
关键词：
information extraction; OCR; summarization; meta-data;
D O I：
10.1117/12.712264
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
引用
收藏
页数：6
相关论文
共 50 条
  • [1] Automatic Knowledge Extraction from OCR Documents Using Hierarchical Document Analysis
    Mohammad, Masum
    Kosaraju, Sai
    Bayramoglu, Tanju
    Modgil, Girish
    Kang, Mingon
    PROCEEDINGS OF THE 2018 CONFERENCE ON RESEARCH IN ADAPTIVE AND CONVERGENT SYSTEMS (RACS 2018), 2018, : 189 - 194
  • [2] Fast title extraction method for business documents
    Katsuyama, Y
    Naoi, S
    DOCUMENT RECOGNITION IV, 1997, 3027 : 192 - 201
  • [3] Toward generic title generation for clustered documents
    Tseng, Yuen-Hsien
    Lin, Chi-Jen
    Chen, Hsiu-Han
    Lin, Yu-I
    INFORMATION RETRIEVAL TECHNOLOGY, PROCEEDINGS, 2006, 4182 : 145 - 157
  • [4] Documents of Title
    Schutz, Anthony B.
    BUSINESS LAWYER, 2009, 64 (04): : 1229 - 1236
  • [5] Documents of Title
    Schutz, Anthony B.
    BUSINESS LAWYER, 2011, 66 (04): : 1147 - 1152
  • [6] Documents of Title
    Schutz, Anthony B.
    BUSINESS LAWYER, 2012, 67 (04): : 1293 - 1298
  • [7] Challenges in OCR of Devanagari documents
    Kompalli, S
    Nayak, S
    Setlur, S
    Govindaraju, V
    EIGHTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS 1 AND 2, PROCEEDINGS, 2005, : 327 - 331
  • [8] An approach of information extraction from web documents for automatic ontology generation
    Yeom, KW
    Park, JH
    COMPUTATIONAL INTELLIGENCE AND SECURITY, PT 1, PROCEEDINGS, 2005, 3801 : 450 - 457
  • [9] DOMITIAN TITLE GERMANICUS AND GREEK DOCUMENTS FROM EGYPT
    MARTIN, A
    HISTORIA-ZEITSCHRIFT FUR ALTE GESCHICHTE, 1987, 36 (01): : 73 - 82
  • [10] Summarization of imaged documents without OCR
    Xerox Palo Alto Research Cent, Palo Alto, United States
    Comput Vision Image Undersanding, 3 (307-320):
12345