不带子对象的轮廓

Question

再见

我在图像上使用了cv2.findContours。然后，提取了轮廓和层次信息。从那里，我如何过滤并只绘制没有子对象的轮廓（据我所知，层次结构数组的第3列中的值为-1）？在

下面是我的代码：my image

from imutils import perspective
from imutils import contours
import numpy as np
import imutils
import cv2

img = cv2.imread('TESTING.png') 
imgs = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edged = imgs

cnts = cv2.findContours(edged,cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
hierarchy = cnts[2]
ChildContour = hierarchy [0, :,2]
WithoutChildContour = (ChildContour==-1).nonzero()[0]

cntsA = cnts[0] if imutils.is_cv2() else cnts[1]
if not cntsA:
    print ("no contours")



(cntsB, _) = contours.sort_contours(cntsA)

orig = cv2.imread('TESTING.png')
for c in cntsB:


    if cv2.contourArea(c) < 100: 
        continue

    box = cv2.minAreaRect(c)
    box = cv2.boxPoints(box) if imutils.is_cv2() else cv2.boxPoints(box)
    box = np.array(box, dtype="int")
    box = perspective.order_points(box)
    cv2.drawContours(orig, [box.astype("int")], -1, (0, 255, 0), 2)

screen_res = 972, 648
scale_width = screen_res[0] / img.shape[1]
scale_height = screen_res[1] / img.shape[0]
scale = min(scale_width, scale_height)
window_width = int(img.shape[1] * scale)
window_height = int(img.shape[0] * scale)

cv2.namedWindow('Image', cv2.WINDOW_NORMAL)
cv2.resizeWindow('Image', window_width, window_height)

cv2.imshow("Image", orig)
cv2.waitKey(0)       
cv2.destroyAllWindows()

Answer 1

findContours返回的hierarchy有四列：[下一列，上一列，第一列子列，父列]。正如您所指出的，我们对索引2感兴趣，即第一个孩子。要过滤并只绘制没有子对象的轮廓，可以在WithoutChildContour中的索引上循环。在

cntsA=[ cntsA[i] for i in WithoutChildContour]

下面是相应的片段：

注意：自从opencv 4.0以来，findContours只返回2个值（cnt和层次结构）。在

# ...
hierarchy = cnts[1] #changed index
ChildContour = hierarchy [0, :,2]
WithoutChildContour = (ChildContour==-1).nonzero()[0]

cntsA = cnts[0]
# get contours from indices
cntsA=[ cntsA[i] for i in WithoutChildContour]
# ...

在示例图像上运行：