On the choice of training set, architecture and combination rule of multiple MLP classifiers for multiresolution recognition of handwritten characters.
Ujjwal BhattacharyaSzilárd VajdaAnirban MallickB. B. ChaudhuriAbdel BelaïdPublished in: IWFHR (2004)
Keyphrases
- handwritten characters
- training set
- combination rule
- multiresolution
- character recognition
- handwritten character recognition
- test set
- training data
- dempster shafer theory
- classification algorithm
- training samples
- multi layer perceptron
- class labels
- belief functions
- evidence theory
- support vector machine
- data sets
- multilayer perceptron
- machine vision
- neural network
- alphanumeric characters
- svm classifier
- wavelet transform
- classification accuracy
- control system
- neural classifier
- recognition rate
- decision trees
- face recognition
- real time
- highest accuracy
- machine learning
- decision making
- object recognition
- feature space
- radial basis function
- supervised learning