Text-Color-Independent Binarization for Degraded Document Image Based on MAP-MRF Approach.
Hideaki OriiHideaki KawanoHiroshi MaedaNorikazu IkomaPublished in: IEICE Trans. Fundam. Electron. Commun. Comput. Sci. (2011)
Keyphrases
- document images
- text regions
- document analysis
- document processing
- text documents
- maximum a posteriori
- markov random field
- digital documents
- information retrieval
- web documents
- printed text
- keywords
- text content
- printed documents
- text extraction
- document content
- color images
- text retrieval
- textual content
- maximum a posterior
- scientific documents
- text lines
- color information
- multimedia documents
- graph cuts
- scanned documents
- text collections
- structured documents
- semantic information
- color space
- document collections
- text recognition
- map estimation
- gray scale images
- document structure
- text mining
- text summarization
- scientific papers
- image binarization
- document corpus
- computer vision
- text clustering
- grayscale images
- information extraction
- energy function
- automatic text summarization
- image retrieval
- image preprocessing
- higher order
- information retrieval systems
- pairwise
- gray scale
- electronic documents
- handwritten documents
- web pages
- optical character recognition
- image segmentation
- image processing
- pdf files
- text classification
- binary images
- document clustering
- document representation
- text classifiers