A new warping technique for normalizing likelihood of multiple classifiers and its effectiveness in combined on-line/off-line japanese character recognition.
Ondrej VelekStefan JägerMasaki NakagawaPublished in: IWFHR (2002)
Keyphrases
- character recognition
- multiple classifiers
- handwritten chinese
- combining multiple
- machine vision
- chinese characters
- hand written
- handwritten characters
- printed characters
- character segmentation
- question answering
- ensemble learning
- real time
- classification algorithm
- training data
- image segmentation
- optical character recognition
- classifier ensemble
- classifier combination
- machine learning
- neural network