Tuesday, September 05, 2006

Open Source To Rescue OCR

This blog is not entirely about open source intentionally. It just happens that open source technology is where all the action and innovation appears to be happening in software today. I just bumped upon an article about OCR that interested me. "Google releases open source OCR tool". If you thought at OCR was a stagnant technology then you just joined the crowd and Google's viewpoint.

What is interesting is the fact that it took an open source mentality, a stagnant technology (OCR), and a few bright Google engineers to reinvigorate the OCR technology space. The new open source product called, Tesseract, is released under an Apache Software License. Google hopes that the open source community will create solutions and new products for the OCR technology.

Prior to reading this article, I was not aware that OCR technology has literally stagnated for the last 10-years. HP and UNLV released their OCR technology into open source to re-generate interest. Well, it appears that Google does have the interest. Remember the digital library initiative that caused an uproar. Well, open source OCR looks like it is par for the course of working towards that goal.