在图像中查找重心

skimage.measure.regionprops 会做你想做的事。下面是一个示例:

import imageio as iio
from skimage import filters
from skimage.color import rgb2gray  # only needed for incorrectly saved images
from skimage.measure import regionprops

image = rgb2gray(iio.imread('eyeball.png'))
threshold_value = filters.threshold_otsu(image)
labeled_foreground = (image > threshold_value).astype(int)
properties = regionprops(labeled_foreground, image)
center_of_mass = properties[0].centroid
weighted_center_of_mass = properties[0].weighted_centroid

print(center_of_mass)

在我的机器上,通过您的示例图像 (228.48663375508113, 200.85290046969845) .

我们可以画出一幅美丽的图画:

import matplotlib.pyplot as plt
from skimage.color import label2rgb

colorized = label2rgb(labeled_foreground, image, colors=['black', 'red'], alpha=0.1)
fig, ax = plt.subplots()
ax.imshow(colorized)
# Note the inverted coordinates because plt uses (x, y) while NumPy uses (row, column)
ax.scatter(center_of_mass[1], center_of_mass[0], s=160, c='C0', marker='+')
plt.show()

这给了我以下输出:

你会注意到有一些你可能不想要的前景,比如在图片的右下角。这完全是另一个答案,但你可以看看 scipy.ndimage.label , skimage.morphology.remove_small_objects ,更普遍的是 skimage.segmentation .

您可以使用 scipy.ndimage.center_of_mass 函数查找对象的质心。

例如,使用此问题的图像:

wget https://i.stack.imgur.com/ffDLD.jpg

import matplotlib.image as mpimg
import scipy.ndimage as ndi

img = mpimg.imread('ffDLD.jpg')
img = img.mean(axis=-1).astype('int')  # in grayscale

cy, cx = ndi.center_of_mass(img)

print(cy, cx)

228.75223713169711 197.40991592129836

你需要知道 Image Moments .

Here 有一个关于如何将其与opencv和python结合使用的教程