Script and language determination from document images
Abstract
We have developed techniques for distinguishing which language is represented in an image of text. This work is restricted to a small but important subset of the world`s languages, using techniques that should be applicable across much more comprehensive samples. The method first classifies the script into two broad classes: European and Asian. This classification is based on the spatial relationships of fiducial points related to the upward concavities in character structures. Language identification within the Asian script class (Japanese, Chinese, Korean) is performed by analysis of the optical density distribution of the text images. Within the European script class, language identification is described in separate papers.
- Authors:
-
- Fuji Xerox Palo Alto Laboratory, Palo Alto, CA (United States)
- Publication Date:
- Research Org.:
- Nevada Univ., Las Vegas, NV (United States)
- OSTI Identifier:
- 68579
- Report Number(s):
- CONF-9404212-
TRN: 95:004349-0019
- Resource Type:
- Technical Report
- Resource Relation:
- Conference: 3. annual symposium on document analysis and information retrieval, Las Vegas, NV (United States), 11-13 Apr 1994; Other Information: PBD: 1994; Related Information: Is Part Of Third Annual Symposium on Document Analysis and Information Retrieval; PB: 484 p.
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 99 MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS; MACHINE TRANSLATIONS; ACCURACY; OPTICAL SCANNERS; SPATIAL DISTRIBUTION; CLASSIFICATION; INFORMATION; IMAGES
Citation Formats
Spitz, A L. Script and language determination from document images. United States: N. p., 1994.
Web.
Spitz, A L. Script and language determination from document images. United States.
Spitz, A L. 1994.
"Script and language determination from document images". United States.
@article{osti_68579,
title = {Script and language determination from document images},
author = {Spitz, A L},
abstractNote = {We have developed techniques for distinguishing which language is represented in an image of text. This work is restricted to a small but important subset of the world`s languages, using techniques that should be applicable across much more comprehensive samples. The method first classifies the script into two broad classes: European and Asian. This classification is based on the spatial relationships of fiducial points related to the upward concavities in character structures. Language identification within the Asian script class (Japanese, Chinese, Korean) is performed by analysis of the optical density distribution of the text images. Within the European script class, language identification is described in separate papers.},
doi = {},
url = {https://www.osti.gov/biblio/68579},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sat Dec 31 00:00:00 EST 1994},
month = {Sat Dec 31 00:00:00 EST 1994}
}