Investigating the Effect of Using Synthetic and Semi-synthetic Images for Historical Document Font Classification.
Konstantina NikolaidouRicha UpadhyayMathias SeuretMarcus LiwickiPublished in: DAS (2022)
Keyphrases
- document classification
- classification algorithm
- pattern recognition
- machine learning
- preprocessing
- classification systems
- classification scheme
- automatic classification
- text documents
- document images
- class labels
- classification accuracy
- feature selection
- decision trees
- information retrieval systems
- real world
- character recognition
- classification models
- pattern classification
- feature extraction
- support vector
- text classification
- image classification
- feature vectors
- keywords
- web documents
- classification method
- document collections
- document retrieval
- classification rules
- support vector machine svm
- model selection
- historical data
- search engine
- information retrieval