# how to use python to detect ellipse

I want to detect the simple shapes in an image. I use cv2.approxPolyDP to detect vertices, but the result of ellipse is 4, same as square, how to differ them? Or, how to detect an ellipse, given the contour?

This is part of the code, "c" is the contour. I find ellipse's approx is 4, same as square.

    shape = "unidentified"
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.04 * peri, True)

# if the shape is a triangle, it will have 3 vertices
if len(approx) == 3:
shape = "triangle"

# if the shape has 4 vertices, it is either a square or
# a rectangle
elif len(approx) == 4:

edit retag close merge delete

1

I think you can't do that just with approxPolyDP(). Instead you could use some circularity attributes (inertia ratio), take a look at this article. Another option would be to use scikit-image, which provides an elliptical hough transform, see here.

( 2016-08-19 02:03:05 -0500 )edit

so, your concept hit a little wall there, no ? ;)

(counting corners on round things, hmmm)

( 2016-08-19 05:15:19 -0500 )edit

Sort by ยป oldest newest most voted

Just search the web, there are so many references. Depending on your situation you might find many ways to solve.
For example:
Hough Transform 1 .
Hough Transform Paper.
Using fit ellipse

more

Official site

GitHub

Wiki

Documentation