INFTY: an integrated OCR system for mathematical documents.
Masakazu SuzukiFumikazu TamariRyoji FukudaSeiichi UchidaToshihiro KanahoriPublished in: ACM Symposium on Document Engineering (2003)
Keyphrases
- printed documents
- document processing
- scanned documents
- information retrieval
- page layout
- information retrieval systems
- document analysis
- optical character recognition
- character recognition
- retrieval systems
- document collections
- relevant documents
- text documents
- document retrieval
- document image retrieval
- document classification
- document images
- metadata
- xml documents
- document clustering
- text analysis
- structured documents
- vector space model
- ocr systems
- scanned images
- web documents
- text lines
- legal documents
- post processing
- keywords
- database
- word spotting
- digital documents
- document image analysis
- handwriting recognition
- text recognition
- semantic information
- multi document summarization
- document representation
- user queries