Title :
Mongolian character recognition using multilayer perceptron (MLP)
Author :
Batsamhan, O. ; Singh, Y.P.
Author_Institution :
Fac. of Inf. Technol., Multimedia Univ., Selangor, Malaysia
Abstract :
This paper presents Mongolian character recognition using MLP. The study focuses on single size and single font Mongolian characters recognition by feedforward Neural Networks (NN). The training set consists of Mongolian character images in Arial Mon font. The performance of this MLP is evaluated based on a database of Mongolian character images. The simulation results are provided to show the performance of MIP classifier for Mongolian character recognition.
Keywords :
backpropagation; character recognition; image classification; multilayer perceptrons; MLP; Mongolian character recognition; backpropagation; feedforward neural networks; learning algorithm; multilayer perceptron; training set; Backpropagation algorithms; Character recognition; Cost function; Feedforward neural networks; Image recognition; Multi-layer neural network; Multilayer perceptrons; Neural networks; Neurons; Training data;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1198132
