Text extraction from degraded document image independent of character color based on MAP-MRF approach.
Hideaki KawanoHideaki OriiHiroshi MaedaNorikazu IkomaPublished in: FUZZ-IEEE (2009)
Keyphrases
- ocr systems
- text extraction
- document images
- optical character recognition
- markov random field
- text recognition
- natural scenes
- text processing
- text regions
- complex background
- text segmentation
- document classification
- object recognition
- character recognition
- color information
- graph cuts
- image processing
- document analysis
- gray scale
- scanned documents
- color images
- image retrieval
- image segmentation