Project Naptha – Images text simplified

Screenshot 2014-08-06 23.37.22

Have you ever experienced need to copy some text but found that it’s actually an image and you cant copy text from it? If yes, world isn’t same anymore. Introducing Project Naptha, According to its author,

Project Naptha automatically applies state-of-the-art computer vision algorithms on every image you see while browsing the web. The result is a seamless and intuitive experience, where you can highlight as well as copy and paste and even edit and translate the text formerly trapped within an image.

Simply put, Project Naptha is a college project build by Kevin Kwok which offers a chrome extension to allow users highlight, copy-paste, edit and translate on the go.

How it works:

It runs a text detection algorithm, Stroke Width transform along with Optical Character recognition. This project also uses algorithms like connected components analysis (identifying distinct letters), Otsu thresholding (determining word spacing), disjoint set forests (identifying lines of text). 

Over and above applying these algorithms, this project also watches cursor movements all the time to get the words you might be looking for.

Next time, when you go to web and find any image, be it informative or just an internet meme, with naptha in your armour, you know you can copy its text on the go.