Locating text in color documents.
Charalambos StrouthopoulosNikos PapamarkosAntonios AtsalakisChristodoulos ChamzasPublished in: ICIP (1) (2001)
Keyphrases
- text documents
- free text
- information retrieval
- digital documents
- web documents
- textual content
- keywords
- text collections
- automatic categorization
- semantic content
- text retrieval
- text analysis
- text information
- document processing
- text data
- plagiarism detection
- latent semantic analysis
- document content
- document analysis
- textual data
- text content
- electronic documents
- text clustering
- newspaper articles
- textual documents
- key concepts
- multimedia documents
- color images
- document collections
- text mining
- document categorization
- text corpus
- text extraction
- document level
- handwritten text
- document clustering
- semantic information
- natural language text
- textual information
- text segments
- information extraction
- printed documents
- text categorization
- multiword
- natural language processing
- document set
- page layout
- retrieval engine
- document structure
- scientific documents
- topic segmentation
- linguistic analysis
- metadata
- scientific literature
- xml documents
- complex background
- information retrieval systems
- relevant documents
- related documents
- text corpora
- document representation
- color space
- document retrieval
- journal articles
- spoken documents
- document repositories
- printed text
- vector space model
- text classifiers
- handwritten documents
- topic models
- text summarization
- co occurrence
- automatic summarization
- digital libraries
- sentence level