Script and language determination from document images
- Fuji Xerox Palo Alto Laboratory, Palo Alto, CA (United States)
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.
- Research Organization:
- Nevada Univ., Las Vegas, NV (United States)
- OSTI ID:
- 68579
- Report Number(s):
- CONF-9404212-; TRN: 95:004349-0019
- 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
Similar Records
1988 International Conference on Computer Processing of Chinese and Oriental Languages, Toronto, Canada, Aug. 29-Sept. 1, 1988, Proceedings
Page segmentation using script identification vectors: A first look