Using Automatic Features for Text-image Classification in Amharic Documents.
Birhanu BelayTewodros HabtegebrialGebeyehu BelayDidier StrickerPublished in: ICPRAM (2020)
Keyphrases
- image classification
- feature extraction
- image features
- text documents
- textual features
- information retrieval
- retrieval engine
- bag of words
- document analysis
- digital documents
- automatic text
- web documents
- keywords
- free text
- semantic information
- text retrieval
- class specific
- latent semantic analysis
- document retrieval
- metadata
- textual content
- electronic documents
- word pairs
- vector space model
- multiword
- text classifiers
- textual data
- english language
- printed documents
- document clustering
- visual words
- automatic categorization
- multimedia documents
- semi structured
- information retrieval systems
- text mining
- sentiment polarity