Detect digits with the openCV Bounding Box algorithm in Python

Question

I'm working on a software which should recognise several digits. For cropping the digits of an image I am using openCV. The problem I've got is that the bounding box algorithm is not only detecting the digits. It is detecting the structure in a digit too.

The simplest way to solve this would be to set a minimum size the structure have to have. This doesn't work because I have to detect digits of any size. Has anybody an idea to solve this problem?

This is the code:

im = cv2.imread('img.jpg')
    gray=cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
    contours,hierarchy = cv2.findContours(gray,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
    idx = 0
    for cnt in contours:

            xe,ye,we,he = cv2.boundingRect(cnt)
            roi=im[ye-100:ye+he+100,xe-100:xe+we+100]

            if xe > 30:
                    if ye > 30:
                            if he > 30:
                                    if we > 30:
                                            idx += 1
                                            cv2.imwrite(str(idx) + '.jpg', roi)
                                            cv2.rectangle(im,(xe,ye),(xe+we,ye+he),(200,0,0),2)


                                            cv2.imwrite('dev.jpg', im)

try RETR_EXTERNAL instead of RETR_LIST It should extract only the outer contour if i understood the documentation correct. — M4rtini
– M4rtini, Commented Jan 23, 2016 at 17:10
@M4rtini: could you turn that into an answer for future reference? — gariepy
– gariepy, Commented Jan 23, 2016 at 17:26
@gariepy Yes, i've now done so. Included links to the docs and a list of the available modes of the function. — M4rtini
– M4rtini, Commented Jan 23, 2016 at 17:48

M4rtini · Accepted Answer · 2016-01-23 17:47:14Z

According to the documentation.

You can change the mode of the findContours method to only return the outermost contours by changing the paramter cv2.RETR_LIST to cv2.RETR_EXTERNAL

Contour retrieval mode (if you use Python see also a note below).

CV_RETR_EXTERNAL retrieves only the extreme outer contours. It sets hierarchy[i][2]=hierarchy[i][3]=-1 for all the contours.

CV_RETR_LIST retrieves all of the contours without establishing any hierarchical relationships.

CV_RETR_CCOMP retrieves all of the contours and organizes them into a two-level hierarchy. At the top level, there are external boundaries of the components. At the second level, there are boundaries of the holes. If there is another contour inside a hole of a connected component, it is still put at the top level.

CV_RETR_TREE retrieves all of the contours and reconstructs a full hierarchy of nested contours. This full hierarchy is built and shown
in the OpenCV contours.c demo.

Collectives™ on Stack Overflow

Detect digits with the openCV Bounding Box algorithm in Python

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related