Abstract | ||
---|---|---|
This paper presents the implementation and evaluation of a Hidden Markov Model to extract addresses from OCR text. Although Hidden Markov Models discover addresses with high precision and recall, this type of Information Extraction task seems to be affected negatively by the presence of OCR text. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1117/12.587799 | Document Recognition and Retrieval XII |
Keywords | Field | DocType |
information extraction, Hidden Markov Models, OCR | Maximum-entropy Markov model,Pattern recognition,Computer science,Precision and recall,Optical character recognition,Speech recognition,Information extraction,Artificial intelligence,Hidden Markov model | Conference |
Volume | ISSN | Citations |
5676 | 0277-786X | 13 |
PageRank | References | Authors |
3.03 | 4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
kazem taghva | 1 | 20 | 4.28 |
jeffrey coombs | 2 | 89 | 7.73 |
ray pereda | 3 | 15 | 3.79 |
Thomas A. Nartker | 4 | 153 | 21.50 |