OPTICAL CHARACTER RECOGNITION

Abstract

The central objective of this project is demonstrating the capabilities of Artificial Neural Network implementations in recognizing extended sets of character. Optical Character Recognition, usually abbreviated to OCR, is the mechanical or electronic translation of images of handwritten, typewritten or printed text into machine. Character Recognition refers to the process of converting printed Text document into translated Unicode Text.

Lines are identified by an algorithm where we identify top & bottom of the line and in each line character boundaries are calculated by an algorithm, using these calculation character are isolated from the image and then we will classify each character by Back Propagation algorithm.

The Back Propagation algorithm work by what is known as supervised training.It first submits an input for a forward pass through a network. The network output is compared to the desired output ,which is specified by “supervisor” and the error for all the neurons in the output layer is calculated. The fundamental idea behind back propagation algorithm is that error is propagated backward to earlier layers so that a gradient descent algorithm can be applied.

In this project I have used Back propagation Neural Network for efficient recognition where the errors is corrected and rectified neuron values were transmitted by feed –forward method in the neural network of multiple layers.