Leave-One-Out-Training and Leave-One-Out-Testing Hidden Markov Models for a Handwritten Numeral Recognizer: The Implications of a Single Classifier and Multiple Classifications.
Albert Hung-Ren KoPaulo Rodrigo CavalinRobert SabourinAlceu de Souza Britto Jr.Published in: IEEE Trans. Pattern Anal. Mach. Intell. (2009)
Keyphrases
- hidden markov models
- test set
- discriminative classifiers
- discriminative training
- training set
- baum welch
- multiple classifiers
- speech recognition
- training examples
- conditional random fields
- minimum classification error
- sequence classification
- training samples
- linear dynamical systems
- gesture recognition
- cross validation
- handwritten numerals
- viterbi algorithm
- automatic speech recognition
- training data
- sequential data
- recognition rate
- combining multiple
- learning algorithm
- feature set
- support vector machine
- hidden states
- genetic algorithm
- decision trees