DocumentCode
2699084
Title
Postal Address Detection fromWeb Documents
Author
Can, Lin ; Qian, Zhang ; Xiaofeng, Meng ; Wenyin, Liu
Author_Institution
Sch. of Inf., Renmin Univ., Beijing
fYear
2005
fDate
8-9 April 2005
Firstpage
40
Lastpage
45
Abstract
An approach to postal address detection from Web pages is proposed. The Web pages are first segmented into text blocks based on their visual similarity. The text content in each block undergoes the recognition process, which employs a syntactic approach. The grammars of almost all possible patterns of postal addresses are built for this purpose. The results of our preliminary experiments on 44 Web pages with 56 true addresses show that our approach can detect the postal addresses with a high precision (89.3%) and a low false alarms rate (3.8%)
Keywords
Web sites; document image processing; grammars; image recognition; text analysis; Web documents; grammars; postal address detection; text blocks; text recognition; Application software; Computer applications; Computer science; Data mining; HTML; Information retrieval; Machine learning; Partial response channels; Statistical analysis; Text recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Web Information Retrieval and Integration, 2005. WIRI '05. Proceedings. International Workshop on Challenges in
Conference_Location
Tokyo
Print_ISBN
0-7695-2414-1
Type
conf
DOI
10.1109/WIRI.2005.28
Filename
1552994
Link To Document