Previous [ 1] [ 2] [ 3] [ 4] [ 5] [ 6] [ 7] [ 8] [ 9] [ 10] [ 11] [ 12]


Journal of Information Science and Engineering, Vol. 21 No. 2, pp. 453-473 (March 2005)

Hand Written Character Feature Extraction using Non-Linear Feedforward Neural Networks

A. Jalil, I. M. Qureshi, T. A. Cheema and A. Naveed
Engineering and Computer Sciences
M. A. Jinnah University
Islamabad, Pakistan
+Department of Electronics
Quaid-i-Azam University
Islamabad, Pakistan

In this paper, an artificial neural network is proposed for feature extraction of hand written characters. The learning algorithm is developed based on a proposed modified SammoníŽs stress for our feedforward neural networks, which can not only minimize intra class pattern distances but also preserve interclass distances in the output feature space. The proposed feature extraction method tries to calculate rough classes using a Competitive Learning neural network, which is an unsupervised neural network. Then the proposed neural network was used with modified SammoníŽs stress to perform feature extraction using information obtained by means of a Competitive Learning Network. The features thus obtained were compared with a standard PCA neural network and a neural network using SammoníŽs stress in terms of their classification accuracy. Two numerical criteria were used for performance evaluation of the features íV the normalized classification error rate and modified SammoníŽs stress. It is found that proposed modified SammoníŽs stress provides features that are more efficient based on these two numerical criteria.

Keywords: feature extraction, unsupervised neural networks, SammoníŽs stress, handwritten character recognition, LMS algorithm

Full Text (ą■Ąň└╔) Retrieve PDF document (200503_12.pdf)

Received March 11, 2003; revised July 8 and December 8, 2003; accepted February 2, 2004.
Communicated by Kuo-Chin Fan.