1
$\begingroup$

The telecommunication operator in my country has coupons that used to recharge the balance

coupon

I want to develop an Android application, that with the camera can take the scratched number and recognize and automatic recharge.

I think finding the number box, and latter preform an OCR or a pattern match in because are numbers only

I'm new in computer vision I set the environment and test some opencv ups, but I'm losing witch algorithms or sequence of algorithms may use to achieve that I want Exist segmentation, feature detection, blob detection, ... template match but the image maybe rotates scale because the use of the camera

And I'm lose I wonder if exist one algorithm to find the 4 extreme points of a coupon in one image from here I know how to proceed until the OCR part I don't want the code to do it of course

What I want is a simple clue, answer like you may use X algorithm to have Y result

Thanks and sorry for my english

$\endgroup$
1
$\begingroup$

You may try an OCR detector like Teseract with OpenCV:

https://github.com/tesseract-ocr

Train the Teseract algorithm with text samples obtained from the numbers you want to detect and it will work.

EDIT: If you want a similar implementation of what you want you may check this:

http://answers.opencv.org/question/10985/how-can-i-determine-the-location-of-lcdled-display-in-an-image-with-opencv-and-perl/

$\endgroup$
  • $\begingroup$ I plain use Teseract with OpenCV, because i like to reconize the cupon first OpenCv and latter detect the code with tesserac $\endgroup$ – Rolando Corratge Nieves Dec 8 '15 at 18:16

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.