Neural Networks and character Recognition

What is an Artificial Neural Network?

A kind of computer model, loosely inspired by the neural network structure of the brain, and consisting of interconnected processing units that send signals to one another and turn on or off depending on the sum of their incoming signals. Artificial neural networks may be composed of either computer software or hardware or both.

One of the most typical problems to which a neural network is applied is that of optical character recognition. Recognizing characters is a problem that at first seems extremely simple- but it’s extremely difficult in practice to program a computer to do it. And yet, automated character recognition is of vital importance in many industries such as banking and shipping. The U.S. post office uses an automatic scanning system to recognize the digits in ZIP codes. You may have used scanning software that can take an image of a printed page and generate an ASCII document from it.

Below is an intro text from my mini-project (Character Recognition Software)————————————————-

Optical Character Recognition (OCR) is a process of converting printed materials into text or word processing files that can be easily edited and stored. The technology has enabled such materials to be stored using much less storage space than the hard copy materials. OCR technology has made a huge impact on the way information is stored, shared and edited. Prior to Optical Character Recognition, if someone wanted to turn a book into a word processing file, each page would have to be typed word for word.

While Optical Character Recognition has made huge advances in recent years, it still does not perform well in recognizing handwriting or fonts that look similar to handwriting. There are systems within the banking industry that use OCR technology to try to read the amounts on hand written checks, to go along with the computer’s ability to read the routing and account numbers.

In OCR processing, the scanned-in image or bitmap is analyzed for light and dark areas in order to identify each alphabetic letter or numeric digit. When a character is recognized, it is converted into an ASCII code.

The project ‘Character Recognition System’ is software that can recognize and convert bitmap images containing text into machine editable ASCII text files. The software is a based on a simple design which can recognize a small set of fonts.

The project is composed of two sections. The first section trains a neural network with input patterns which are to be recognized by the recognition system. The second section, which is the recognizer, reads the file created by the trainer and uses it to identify characters in the input bitmap image.

The trainer requires above two minutes to create the network. The trainer module has a test facility which can test a character’s recognizability. After the creation it can be stored into a file. It is this file that the recognition part uses to convert the image into text.

A few links that might be useful

 

 

Mathematical Model of an artificial neuron

Mathematical Model of an artificial neuron

Leave a comment

Liked it here?
Why not try sites on the blogroll...