OpenCV：区分两个非常相似的轮廓

Question

I use openCV to find contours in images. The problem is, that some of the contours are just some artifacts I do not want to identify. In the following image you see an example:

I am interested in the countours 20 and 21. 19 should be ignored.

UPDATE: I am not interested in the size of the contours, the pixels within the contiour is what differntiates them. here is another example:

Countour 18 is kindy blurry, has no "sharp contours" within it. Countour 16 has clearer edges and the colorintensity is focused in the center. I would like to know if there is a way to identify contours like that? I tried it with blurry detection ( see here ) but the output between the multiple images was very very differnet...

Thanks for any help!

Answer 1

after finding contours you can find the area of that individual contour and set a if else condition to select that contours

(contours, hierarchy) = cv2.findContours(control, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
 for pic, contour in enumerate(contours):
      area = cv2.contourArea(contour)
            if (area > 200):

in a program i used that contours whose are more than 200 you can also use this