从图像中提取 N 个补丁

Question

我有一个维度的图像155 x 240。就像下面这样：

我想提取某些形状的补丁(25 x 25)。 我不想从整个图像中修补。

我想从图像的非零（非背景）区域提取 N 个补丁。我怎样才能做到这一点？任何想法、建议或实施将不胜感激。您可以尝试使用 Matlab 或 Python。

注意： 我生成了一个随机图像，以便您可以对其进行处理以进行修补。image_process变量是这段代码中的图像。

import numpy as np

from scipy.ndimage.filters import convolve

import matplotlib.pyplot as plt

background = np.ones((155,240))

background[78,120] = 2

n_d = 50

y,x = np.ogrid[-n_d: n_d+1, -n_d: n_d+1]

mask = x**2+y**2 <= n_d**2

mask = 254*mask.astype(float)

image_process = convolve(background, mask)-sum(sum(mask))+1

image_process[image_process==1] = 0

image_process[image_process==255] = 1

plt.imshow(image_process)

Answer 1

假设您要省略的像素值为 0。在这种情况下，您可以做的是，首先找到非零值的索引，然后在 / 位置对图像进行切片min以max仅获得所需的区域，然后简单地应用extract_patches_2d所需的窗口大小和补丁数量。例如，考虑到您提供的虚拟图像：import numpy as npfrom scipy.ndimage.filters import convolveimport matplotlib.pyplot as pltbackground = np.ones((155,240))background[78,120] = 2n_d = 50y,x = np.ogrid[-n_d: n_d+1, -n_d: n_d+1]mask = x**2+y**2 <= n_d**2mask = 254*mask.astype(float)image_process = convolve(background, mask)-sum(sum(mask))+1image_process[image_process==1] = 0image_process[image_process==255] = 1plt.figure()plt.imshow(image_process)plt.show()from sklearn.feature_extraction.image import extract_patches_2dx, y = np.nonzero(image_process)xl,xr = x.min(),x.max()yl,yr = y.min(),y.max()only_desired_area = image_process[xl:xr+1, yl:yr+1]window_shape = (25, 25)B = extract_patches_2d(only_desired_area, window_shape, max_patches=100)&nbsp; # B shape will be (100, 25, 25)如果绘制它，only_desired_area您将得到以下图像：这是主要逻辑，如果您希望更紧的边界，您应该适当调整切片。