在您的问题中尚不清楚，您是要实际裁剪轮廓中定义的信息还是要屏蔽与所选轮廓无关的信息。我将探讨在两种情况下该怎么做。

掩盖信息

假设您

cv2.findContours

idx

cv2.drawContours

img

import numpy as npimport cv2img = cv2.imread('...', 0) # Read in your image# contours, _ = cv2.findContours(...) # Your call to find the contours using OpenCV 2.4.x_, contours, _ = cv2.findContours(...) # Your call to find the contoursidx = ... # The index of the contour that surrounds your objectmask = np.zeros_like(img) # Create mask where white is what we want, black otherwisecv2.drawContours(mask, contours, idx, 255, -1) # Draw filled contour in maskout = np.zeros_like(img) # Extract out the object and place into output imageout[mask == 255] = img[mask == 255]# Show the output imagecv2.imshow('Output', out)cv2.waitKey(0)cv2.destroyAllWindows()

如果你真的想种…

如果要 裁剪
图像，则需要定义轮廓定义的区域的最小跨度边界框。您可以找到边界框的左上角和右下角，然后使用索引来裁剪出所需的内容。该代码将与以前相同，但是将有一个附加的裁剪步骤：

import numpy as npimport cv2img = cv2.imread('...', 0) # Read in your image# contours, _ = cv2.findContours(...) # Your call to find the contours using OpenCV 2.4.x_, contours, _ = cv2.findContours(...) # Your call to find the contoursidx = ... # The index of the contour that surrounds your objectmask = np.zeros_like(img) # Create mask where white is what we want, black otherwisecv2.drawContours(mask, contours, idx, 255, -1) # Draw filled contour in maskout = np.zeros_like(img) # Extract out the object and place into output imageout[mask == 255] = img[mask == 255]# Now crop(y, x) = np.where(mask == 255)(topy, topx) = (np.min(y), np.min(x))(bottomy, bottomx) = (np.max(y), np.max(x))out = out[topy:bottomy+1, topx:bottomx+1]# Show the output imagecv2.imshow('Output', out)cv2.waitKey(0)cv2.destroyAllWindows()

裁剪代码的工作原理是，当我们定义蒙版以提取轮廓所定义的区域时，我们还会找到定义轮廓左上角的最小水平和垂直坐标。同样，我们找到了定义轮廓左下角的最大水平和垂直坐标。然后，我们使用这些坐标的索引来裁剪实际需要的内容。请注意，这会对
蒙版 图像进行裁切，该图像将除去除最大轮廓中包含的信息以外的所有内容。

注意与OpenCV 3.x

应该注意的是，以上代码假定您使用的是OpenCV2.4.x。请注意，在OpenCV
3.x中，的定义

cv2.findContours

cv2.findContours

_, contours, _ = cv2.findContours(...) # Your call to find contours