How to copy image area using opencv in python?

Question

I am trying to implement license plate recognition software using the ideas of http://iamabhik.wordpress.com/category/opencv/ .

I implemented plate layout using opencv in python using "import cv2". It works fine, and now I need to copy the plate area to another image in order to segment the characters, and then part of the OCR (possibly using a neural network).

I found that the GetSubRect () function copies or isolates part of the image, but it does not seem to be available in python. Is there an alternative? ROI functions are also not implemented.

Is there any updated python interface documentation for opencv?

I compiled opencv from the svn repository (revision 7239) in a Debian wheezy / sid environment.

Feel free to suggest alternative methods / ideas to solve this problem.

Thanks in advance.

Answer 1

Both cv.GetSubRect and ROI functions are available in Python, but in the old mode import cv or import cv2.cv those. use cv2.cv.GetSubRect() or cv2.cv.SetImageROI if you are familiar with them.

On the other hand, it’s easy to install ROI without these features due to the numpy integration in the new cv2.

If (x1, y1) and (x2, y2) are the two opposite vertices of the plate that you received, then simply use the function:

 roi = gray[y1:y2, x1:x2] 

This is your image ROI.

So choose whichever you are.

Answer 2

Example. If you have several points and want to copy an area, it contains

 r = cv2.boundingRect(pts) cv2.imwrite('roi.png', im[r[0]:r[0]+r[2], r[1]:r[1]+r[3]])