Multiple Classifier Systems In Offline Handwritten Word Recognition - On The Influence Of Training Set And Vocabulary Size.
Simon GünterHorst BunkePublished in: Int. J. Pattern Recognit. Artif. Intell. (2004)
Keyphrases
- handwritten word recognition
- multiple classifier systems
- training set
- classification accuracy
- hidden markov models
- word recognition
- base classifiers
- test set
- data sets
- nearest neighbor
- neural network
- training data
- dynamic classifier selection
- classification systems
- training samples
- supervised learning
- feature space
- pattern recognition
- test data
- active learning
- classifier combination
- machine learning