Tesseract OCR for license plate recognition OpenCV ? [closed]

asked 2016-03-03 15:08:27 -0600

sam001
1 ●1 ●2 ●5

I have written this program which can detect license plate in a car and draw a rectangle around the detected area. Now, the idea is to extract text from the detected area using Tesseract OCR. But when i run the image through OCR, I get a blank text. I tried with the same images but of different sizes and still the same result. What could be the mistake? What are my options for character recognition?

Here are the images:-

image description

edit retag flag offensive reopen merge delete

Closed for the following reason duplicate question by sam001
close date 2016-03-05 15:38:20.923785

add a comment

1 answer

Sort by » oldest newest most voted

answered 2016-03-03 21:05:26 -0600

Tetragramm

7376 ●13 ●37

Frankly, we don't have anything to do with Tesseract. I'm going to go out on a limb here and take a guess though. Did you do any preprocessing or just hand it that image? I expect it wants something cleaner.

Try extracting just the yellow pixels in a binary mask and cropping the image to the square of the license plate. That will make black letters on a white background which is probably what it expects.

If that doesn't work, sorry, but you might want to try asking their forums, or whatever they use.