A Hybrid Intelligent System for Arabic Handwritten Number Recognition | ||||
IJCI. International Journal of Computers and Information | ||||
Article 6, Volume 1, Issue 1, July 2007, Page 50-60 PDF (169.15 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/ijci.2007.33932 | ||||
View on SCiNiTO | ||||
Authors | ||||
Reda M. Hussain 1; W. F. Abd El-wahed2; F. A. Torkey3 | ||||
1Faculty of computers & Information, Shiben El-Kom, Menoufia University, Egypt. | ||||
2Operations Research Dept. Faculty of computers & Information, Shiben El-Kom, Menoufia University, Egypt. | ||||
3Prof. of Computer Science & Engineering and President of Kafer El- Sheekh University, Egypt | ||||
Abstract | ||||
This paper shows how developments in the area of neural network combined with genetic algorithms can be used in the handwritten digit recognition. In this work, two approaches to the design of a feed-forward neural network that model the handwritten recognition system are discussed. The first approach focuses on constructing the network by using a trail-and error method the second approach is responsible for determining the appreciate parameters of the neural network and its learning algorithm by the mean of genetic algorithms. Results show that using genetic algorithm for selecting the near optimal parameters of the neural network, is improving classification performance on handwritten digits. | ||||
Keywords | ||||
Neural Networks; Genetic Algorithms; Handwritten numeral recognition | ||||
Statistics Article View: 186 PDF Download: 250 |
||||