Extraction of text words in document images based on a statistical characterization.
Su S. ChenRobert M. HaralickIhsin T. PhillipsPublished in: J. Electronic Imaging (1996)
Keyphrases
- document images
- printed text
- printed documents
- text lines
- word level
- document analysis
- historical documents
- line extraction
- word spotting
- indian languages
- document image analysis
- document processing
- optical character recognition
- handwritten documents
- ocr systems
- text extraction
- word recognition
- page layout
- text regions
- document image understanding
- scanned document images
- language identification
- scanned documents
- word segmentation
- mathematical formulas
- text detection
- machine printed text
- text processing
- keywords
- document image retrieval
- text documents
- information extraction
- page segmentation
- scanned images
- character recognition
- document layout
- text analysis
- handwriting recognition
- structure extraction
- natural language processing
- digital libraries