圖像區域的最小邊界框？

Question

我找到了一種方法來計算圖像上封閉區域的最小邊界框（還考慮旋轉角度）。

我可以使用以下代碼來提取此圖像的質心坐標，邊框的寬度和長度以及旋轉角度：

from PIL import Image
import cv2
import numpy as np
from matplotlib import pyplot as plt

image_file = Image.open("binaryraster.png")
image_file = image_file.convert('1')
image_file.save('result.png')

img = cv2.imread('result.png',0)
edges = cv2.Canny(img,100,200)
plt.subplot(111),plt.imshow(edges,cmap = 'gray')
plt.title('Canny Edge detection'), plt.xticks([]), plt.yticks([])

ret,thresh = cv2.threshold(img,127,255,0)
contours,hierarchy = cv2.findContours(thresh, 1, 2)

cnt = contours[0]


leftmost = tuple(cnt[cnt[:,:,0].argmin()][0])
rightmost = tuple(cnt[cnt[:,:,0].argmax()][0])
topmost = tuple(cnt[cnt[:,:,1].argmin()][0])
bottommost = tuple(cnt[cnt[:,:,1].argmax()][0])

rect = cv2.minAreaRect(cnt)
box = cv2.cv.BoxPoints(rect)
box = np.int0(box)



M = cv2.moments(cnt)
centroid_x = int(M['m10']/M['m00'])
centroid_y = int(M['m01']/M['m00'])

print (leftmost)
print (rightmost)
print (topmost)
print (bottommost)

print(centroid_x)
print(centroid_y)

print(rect)
print(box)

plt.show()

當我在一幅圖像中有很多區域時，我的代碼無法提取所有這些信息。

你能幫我么

Answer 1

cnt = contours[0] # you're only checking the 1st contour here

您可能想遍歷所有找到的輪廓：

for cnt in contours:

    leftmost = tuple(cnt[cnt[:,:,0].argmin()][0])
    rightmost = tuple(cnt[cnt[:,:,0].argmax()][0])
    topmost = tuple(cnt[cnt[:,:,1].argmin()][0])
    bottommost = tuple(cnt[cnt[:,:,1].argmax()][0])

    rect = cv2.minAreaRect(cnt)
    box = cv2.cv.BoxPoints(rect)
    box = np.int0(box)



    M = cv2.moments(cnt)
    centroid_x = int(M['m10']/M['m00'])
    centroid_y = int(M['m01']/M['m00'])

    print (leftmost)
    print (rightmost)
    print (topmost)
    print (bottommost)

    print(centroid_x)
    print(centroid_y)

    print(rect)
    print(box)