Text Steganography based on Font Type in MS-Word Documents.
Wesam BhayaAbdul Monem S. RahmaDhamyaa Al-NasrawiPublished in: J. Comput. Sci. (2013)
Keyphrases
- text corpus
- printed documents
- text segments
- natural language text
- text documents
- keywords
- sentence level
- word pairs
- page layout
- character recognition
- spoken documents
- linguistic information
- sentence similarity
- information retrieval
- optical character recognition
- digital documents
- multiword
- word frequency
- document analysis
- free text
- latent semantic analysis
- printed text
- document level
- word co occurrence
- related documents
- related words
- historical manuscripts
- handwritten documents
- co occurrence
- web documents
- word spotting
- ocr systems
- syntactic information
- concept space
- stop words
- document images
- text information
- text collections
- character n grams
- text queries
- text corpora
- document collections
- text mining
- training corpus
- keyword extraction
- word level
- text lines
- semantic information
- sentiment polarity
- information retrieval systems
- text retrieval
- term frequency
- word sense
- scanned documents
- word sense disambiguation
- noun phrases
- newspaper articles
- latent topics
- document clustering
- relevant documents
- information extraction
- indian languages
- spoken document retrieval
- text summarization
- word recognition
- handwritten text
- semantic similarity
- n gram
- topic models
- text regions
- search engine