tesseract

The magic of Sikuli is its use of the OpenCV library under the hood (and Tesseract for OCR).

If you are using OpenCV and tesseract, you might have a look at Scene Text Detection in OpenCV 3.

This'll dramaticlly help Tesseract out, but it can increase some of the complexity you'll have to juggle.

We've had great success with CCV's SWT to indentify text zones and Tesseract to extract it.

If you're doing real time street sign recognition or involved with a book scanning and archival startup, investigate Tesseract for sure.

We found that Tesseract had too many built-in goodies for image scanning, like warped characters, lighting and shadow defects, and photographic artifacts.

You could skip the Sikuli part and just use OpenCV and Tesseract directly.

I used the go wrappers for tesseract[0] in my full text search indexer for disks[1] and it worked great.

There are options to adjust the image in various ways and once Tesseract runs, it's easy to get the result in various formats.

It seems this is just built on top of Tesseract as well.

As the parent of this comment thread mentions, Tesseract is not very great for mass usage due to the error rate with Abbyy much better.

A counter anecdote, I've used Tesseract for a largish project and it's worked wonderfully.

_________________ Gotta have something now: Tesseract Not saying it's "bad" but it ain't as great as you want.

Constrain your problem as a computer-vision one to segment nice pieces of work for Tesseract.

I think something like that happened with Tesseract, Google stepped in to make something than was not running, viable.

Now, crop each of these regions of interest and feed them into Tesseract.