Workshop: Making a Simple App to Read Printed Text using Tesseract (OCR)
To add the capability of reading some printed text into your application for further use!
Have you ever wanted to input some text by the user, and that was printed on the paper? This workshop will help you getting that text into your application, while maintaining user experience!
We’ll do this by using a fork of Tesseract Android Tools by Robert Theis called Tess Two. It is based on the Tesseract OCR Engine (mainly maintained by Google) and Leptonica image processing libraries.
The process starts by building and importing Tess Two, adding the code to capture & process an image from the camera, and then finally filtering that image for the text, ie. performing OCR.
We’ll also explore possibilities and use cases of this, for example searching, translating text, storing receipts digitally, etc.
Android device, laptop, a zip file that will have the pre-requisities
Gautam is a 17 year old self-taught programmer and stickler from Gurgaon. He co-developed the social media sharing plugin for WordPress called SexyBookmarks in the 8th grade (that was later acquired by Shareaholic) and was also a part of the formative team of sportskeeda.com in the 9th grade during its inception period, now the largest sports network in India! He also likes contributing to open source softwares and has won Google Code-in twice! Late last year, he was an Entrepreneur in Residence at GSF India’s Startup Accelerator.
He’s currently working on some of his in-brain ideas while hacking around and blogging on www.Gaut.am. Hit him up!