Optical Character Recognizer (OCR) !

Update: This article is part of a series. Check out the full series: Part 1, and Part 2

OCR ,Optical Character Recognizer is one of the very hot topics nowadays. It has been there in the picture since very long time.In simple words OCR processes the image, PDF or any other file and extract the textual information from it. It is very easy for human beings to recognize a word they know,but what about a word from different language which we don’t know.Same is the case with Computers,they don’t know anything about these words or characters .Now here comes Machine Learning in the picture. We can train our machine like a baby by showing different images to him. Isn’t this great !!!.

We can’t even imagine all the applications of OCR.Imagine a person without vision pointing his mobile towards a Medicine Packet and then the mobile reads all the important information to him like name of medicine,it’s expiry date ,it’s price and then may be searching on internet the prescription of that medicine. A machine converting very old precious book into PDF ,so that the whole world can enjoy that book. And even when me visiting a restaurant in China and converting the menu written in Chinese in English or Hindi so that I can order something to eat.

If you sit and think about all these applications of OCR ,you will find out that there are many that can change every one’s life.

In this series of blogs, I will cover different methods for OCR .From most basic one to most efficient one,I will cover different aspects and applications of OCR and how one can implement it. In the beginning of this series I will be using kNN for OCR and will move forward on different Machine Learning models .

I hope you will enjoy this journey :) .

To begin your journey in OCR please visit my next blog where I covered the basic OCR using kNN in OpenCV python.