A corpus for OCR research on mathematical expressions.
Utpal GarainB. B. ChaudhuriPublished in: Int. J. Document Anal. Recognit. (2005)
Keyphrases
- mathematical expressions
- character recognition
- optical character recognition
- mathematical formulas
- character segmentation
- machine vision
- preprocessing
- post processing
- document images
- open domain
- real time
- document analysis
- real world
- recognition errors
- supervised machine learning
- handwriting recognition
- test set
- computer vision
- manually annotated
- document processing
- scanned documents
- error correction
- text classification
- natural language
- spoken dialog