Text recognition system for Japanese documents.
Kozo BannoTakenori KawamataKeiji KobayashiHajime NambuPublished in: ICPR (1988)
Keyphrases
- text documents
- information retrieval
- free text
- ocr systems
- web documents
- digital documents
- keywords
- document analysis
- text collections
- textual content
- plagiarism detection
- text retrieval
- automatic categorization
- text analysis
- textual data
- latent semantic analysis
- text data
- document content
- multimedia documents
- document collections
- text content
- newspaper articles
- document processing
- optical character recognition
- textual documents
- textual information
- topic segmentation
- text mining
- text information
- electronic documents
- natural language text
- text segments
- text clustering
- text corpora
- document categorization
- document set
- document clustering
- digital libraries
- document images
- text corpus
- scanned documents
- handwritten text
- page layout
- information retrieval systems
- information extraction
- metadata
- semantic information
- retrieval engine
- document level
- key concepts
- document representation
- document structure
- document retrieval
- structured documents
- linguistic analysis
- automatic summarization
- printed documents
- document repositories
- handwritten documents
- news stories
- spoken documents
- scientific literature
- multiword
- semantic content
- vector space model
- text categorization
- wordnet
- text classification
- related documents
- journal articles
- handwriting recognition
- document corpus
- extractive summarization
- web pages