Text Localization and Binarization in Complex Color Documents.
Euthimios BadekasNikos A. NikolaouNikos PapamarkosPublished in: MLDM Posters (2007)
Keyphrases
- information retrieval
- text documents
- web documents
- text analysis
- keywords
- free text
- document processing
- text collections
- document analysis
- digital documents
- latent semantic analysis
- text information
- document collections
- information retrieval systems
- plagiarism detection
- document images
- text content
- text data
- newspaper articles
- automatic categorization
- textual data
- document categorization
- gray scale images
- multimedia documents
- document content
- key concepts
- color images
- text retrieval
- text mining
- text categorization
- textual information
- color information
- topic segmentation
- text corpora
- scientific literature
- document level
- page layout
- query expansion
- text corpus
- semantic information
- text clustering
- semantic content
- natural language text
- text extraction
- text classifiers
- electronic documents
- printed documents
- document structure
- visual features
- co occurrence
- xml documents
- metadata