Hi,
My target:
I'm trying to grab the text from an image which contains several text
area, each area is bounded by a rectangle.
What I did:
I tried to 'OCR' the text from the complete image (using tesseract) but
ended up with poor results.
I read some articles about how tesseract works and figured out that the
poor results might be the outcome of the 'noise' caused by elements
outside of the bounded areas.
I decided to try a different approach: instead of 'OCRing' the complete
picture, I will first process the image to get the bounded rectangles.
After that I will send each rectangle to the OCR engine.
I'm now able to run OpenCV samples for android on my device.
I'm looking for a way to get the list of rectangles from my image, I
found several examples for rectangle detecting but they were all C++.
My questions:
I'm new to OCR and image processing, does my approach for grabbing the
text make sense?
Is there an Android-opencv API for grabbing the rectangles from the Mat?
Apologize for the cross posting but I thought this might be relevant for
tesseract developers too.
I also apologize for my English, it's only my second language.
Thanks
/Poncho
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/tesseract-ocr?hl=en
