Hybrid Feature Selection for Historical Document Layout Analysis.
Hao WeiKai ChenRolf IngoldMarcus LiwickiPublished in: ICFHR (2014)
Keyphrases
- feature selection
- text categorization
- document clustering
- text documents
- historical documents
- retrieval systems
- feature extraction
- information retrieval
- document images
- web documents
- document collections
- redundant features
- document classification
- microarray data
- machine learning
- high dimensionality
- document retrieval
- keywords
- information retrieval systems
- feature set
- text classification
- irrelevant features
- retrieved documents
- feature selection algorithms
- document representation
- information gain
- high dimensional
- multi class
- feature space
- feature subset
- support vector
- vector space model
- classification accuracy
- knn
- selected features
- structured documents
- semantic information
- model selection
- database