Skew correction in documents with several differently skewed text areas.
Panagiotis SaragiotisNikos PapamarkosPublished in: VISAPP (1) (2007)
Keyphrases
- text documents
- information retrieval
- free text
- text lines
- digital documents
- web documents
- text retrieval
- text collections
- text information
- plagiarism detection
- latent semantic analysis
- textual documents
- document analysis
- text clustering
- newspaper articles
- textual content
- text analysis
- document categorization
- text data
- keywords
- textual data
- document processing
- document content
- automatic categorization
- document collections
- text content
- textual information
- text categorization
- text segments
- multimedia documents
- text mining
- document structure
- document level
- electronic documents
- document set
- information extraction
- journal articles
- printed documents
- semantic information
- handwritten text
- relevant documents
- related documents
- key concepts
- extractive summarization
- text corpus
- skewed data
- scientific documents
- information retrieval systems
- spoken documents
- sentence level
- natural language text
- text classifiers
- scientific literature
- handwritten documents
- document clustering
- document retrieval
- retrieval engine
- document corpus
- semantic content
- text classification
- document representation
- news stories
- page layout
- structured documents
- topic segmentation
- topic models
- linguistic analysis
- query expansion
- data distribution
- text corpora
- multiword
- language model
- vector space model