Pattern Association For Character Recognition By Back-Propagation Algorithm Using Neural Network Approach

Abstract

The use of artificial neural network in applications can dramatically simplify the code and improve quality of recognition while achieving good performance. Another benefit of using neural network in application is extensibility of the system – ability to recognize more character sets than initially defined. Most of traditional systems are not extensible enough. In this paper recognition of characters is possible by using neural network back propagation algorithm. What is neural network Neural network are simplified models of the biological nervous system and therefore have drawn their motivation from the kind of computing performed by a human brain. An NN in general is a highly interconnected of a large number of processing elements called neurons in an architecture inspired by the brain. An NN can be massively parallel and therefore is said to exhibit parallel distributed processing. Neural Network exhibits characteristics such as mapping capabilities or pattern association, generalization, robustness, fault tolerance, and parallel and high speed information processing. Neural network learn by example. They can therefore be trained with known examples of a problem to acquire knowledge about it. Once appropriate trained the network can be put to effective use in solving ‘unknown’ or ‘untrained’ instances of the problem. Neural network adopt various learning mechanism of which supervised learning and unsupervised learning methods have turned out to be very popular. In supervised learning, a teacher is assumed to be present during the learning process, i.e. the network aims to minimize he error between target (desired) output presented by the teacher and the computed output to achieve better performance. However, in unsupervised learning, there is no teacher present to hand over the desired output and the network therefore tries to learn by itself, organizing the input instances of the problem.NN Architecture has been broadly classified as single layer feed forward networks, multilayer feed forward networks and recurrent networks, over the year several other NN.Architecture have evolved .some of the well known NN system include backpropogation network, perceptron, ADALINE ,Boltzmann machine ,adaptive resonance theory, Self-organized feature map, and Hopfield network. Neural Network has been successfully applied to problem in the field of pattern recognition, image processing, data compression, forecasting and optimization to quote a few. International Journal of Computer Science & Engineering Survey (IJCSES) Vol.3, No.1, February 2012 128 Backpropagation algorithm The architecture of the neural network is the one of a basically backpropagation network with only one hidden layer (although it is the same techniques with more layers). The input layer is constituted of 35 neuron (one per input pixel in the matrix, of course)., they are 8 hidden neurons, and 26 output neurons(one per letter) in this problem domain of character recognition. The weight matrix gives the weight factor for each input of each neuron. These matrices are what we can call the memory of the neural network. The learning process is done by adjusting these weight so that for each given input the output is as near as possible of a wanted output (Here the full activation of the output neuron corresponding to the character to be recognized) [1]. The training patterns are applied in some random order one by one, and the weights are adjusted using the backpropagation learning law. Each application of the training set patterns is called a cycle. The patterns have to be applied for several training cycles to obtain the output error to an acceptable low value. Once the network is trained, it can be used to recall the appropriate pattern for a new input pattern. The computation for recall is straightforward, in the sense that the weights and the output functions of the units in different layers are used to compute the activation values and the output signals. The signals from the output layer correspond to the output[2]. Backpropagation learning emerged as the most significant result in the field of artificial neural networks. The backpropagation learning involves propagation of the error backwards from the output layer to the hidden layers in order to determine the update for the weights leading to the units in a hidden layer. The error at the output layer itself is computed using the difference between the desired output and the actual output at each of the output units. The actual output for a given input training pattern is determined by computing the outputs of units for each hidden layer in the forward pass of the input data. The error in the output is propagated backwards only to determine the weight updates [6].