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)
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.