Layout Analysis and Content Classification in Digitized Books.
Andrea CorbelliLorenzo BaraldiFabrizio BalducciCostantino GranaRita CucchiaraPublished in: IRCDL (2016)
Keyphrases
- machine learning
- image classification
- preprocessing
- supervised classification
- pattern classification
- pattern recognition
- feature vectors
- classification accuracy
- data mining
- automatic classification
- model selection
- multimedia
- decision trees
- text classification
- neural network
- benchmark datasets
- classification method
- scientific papers
- classification process
- user generated content
- classification rate
- classification models
- machine learning methods
- support vector machine
- cross validation
- semantic information
- class labels
- unsupervised learning
- feature extraction
- training data
- supervised learning