α-Soft: An English Language OCR

Because of growing technology and fast living, business card are very much in demand. Most of the cards have fixed font size and style. That's why the OCR required for such documents does not need to be so expensive (computational cost) and complex (Artificial Neural Network). This paper presents a simple, efficient, and less costly approach to construct OCR for cards reading or any document that has fix font size and style. As English is an international language and almost every card have English characters on them. To achieve efficiency and less computational cost, OCR in this paper uses database instead of ANN (Artificial Neural Network) to recognize English characters which makes this OCR very simple to manage. As this paper is about English character recognition, so author is naming this OCR as α-soft, pronounced as "alpha soft". We have developed a prototype for this system. Different experiments are conducted to show that 100% accuracy is possible in OCR.