Layout Analysis for Arabic Historical Document Images Using Machine Learning.
Syed Saqib BukhariThomas M. BreuelAbedelkadir AsiJihad El-SanaPublished in: ICFHR (2012)
Keyphrases
- document images
- machine learning
- language identification
- historical documents
- printed documents
- optical character recognition
- handwritten documents
- ocr systems
- document image analysis
- printed text
- document analysis
- handwriting recognition
- document image understanding
- document processing
- information extraction
- scanned documents
- page segmentation
- line extraction
- page layout
- document image retrieval
- pattern recognition
- scanned document images
- mathematical formulas
- word spotting
- word recognition
- gray scale
- text mining
- document layout
- natural language processing