Development of Nom character segmentation for collecting patterns from historical document pages.
Truyen Van PhanBilan ZhuMasaki NakagawaPublished in: HIP@ICDAR (2011)
Keyphrases
- character segmentation
- keywords
- printed documents
- character recognition
- optical character recognition
- document images
- web documents
- text documents
- automatic recognition
- information retrieval
- document collections
- information retrieval systems
- text retrieval
- structured documents
- document processing
- text mining
- search engine