Revision history [back]

Here is example on how you can read sudoku puzzle on iPhone: http://sudokugrab.blogspot.com/2009/07/how-does-it-all-work.html. This task is a bit simpler than yours, but it highlights some important aspects of such applications. I would recommend to use scanner instead of camera, that will allow you to skip the distortion compensation step.

And I agree with @XCoder that it is a tough task, and you should provide a sample filled form.

You can also check the following links:

1. http://stackoverflow.com/questions/9413216/simple-digit-recognition-ocr-in-opencv-python
2. http://stackoverflow.com/questions/7542194/how-to-use-opencv-for-document-recognition-with-ocr

Here is an example on how you can read sudoku puzzle on iPhone: http://sudokugrab.blogspot.com/2009/07/how-does-it-all-work.html. This task is a bit simpler than yours, but it the post highlights some important aspects of such applications. I would recommend to use a scanner instead of camera, camera for getting forms in digital format, that will allow you to skip the distortion compensation step.

And I agree with @XCoder that it is a tough task, and you should provide a sample filled form.

You can also check the following links:

1. http://stackoverflow.com/questions/9413216/simple-digit-recognition-ocr-in-opencv-python
2. http://stackoverflow.com/questions/7542194/how-to-use-opencv-for-document-recognition-with-ocr