Making Two Vast Historical Manuscript Collections Searchable and Extracting Meaningful Textual Features Through Large-Scale Probabilistic Indexing.
Alejandro Héctor ToselliVerónica Romero-GomezJoan-Andreu SánchezEnrique Vidal-RuizPublished in: ICDAR (2019)
Keyphrases
- textual features
- extracting meaningful
- multimedia collections
- digital libraries
- information retrieval
- information extraction
- data mining
- probabilistic model
- bag of words
- bayesian networks
- real world
- document collections
- effective retrieval
- visual features
- controlled vocabulary
- support vector
- high dimensional
- information retrieval systems
- machine learning