|
|
 |
| |
 |
| |
Press Releases
Google announces open source OCR
http://code.google.com/p/ocropus/
This was kind of cool, even though the code base they’re working with is like 20 years old. Google really appears to be dedicating some serious resources to developing this stuff. Chris Riley of capture consultant Artsyl Technologies had this take on the potential impact of the project. "The real threat to the commercial OCR market could come from independent developers who decide to take the engine and run with it. The technology’s true power could be unleashed when it is set into motion for a niche type of processing, and fine-tuned to do it well.
An example of this could be ID card reading, or OCR of numbers and mathematic equations….The engine under initial testing is not viable for a production-level environment. It is, however, one of a limited number of Linux engines, and, even in the enterprise, Linux is becoming more common because of security and stability advantages. I suspect we will see many talented developers take the engine to higher levels with some impressive results, but I don’t think Google itself, or any other large commercial development pool, will take this engine to market sooner than the next two years." |
| |
|
About Us