定义matplotlib的inline模式，为了能够在ipython中显示图形
In [2]:
%matplotlib inline
导入需要使用的库
In [3]:
import matplotlib.pyplot as plt
import skimage.io as io
from skimage import filter, color
import skimage.measure as ms
来吧读入我们的小绵羊
In [5]:
img = io.imread('sheep.png')
gray=color.rgb2gray(img) # 把它转换成灰度图像
plt.imshow(gray, interpolation='nearest', cmap=plt.cm.gray) #灰灰的
Out[5]:
嗯，吧噪声抹去，只要边界，通过阈值抹去噪声
In [6]:
# otsu
thresh = filter.threshold_otsu(gray)
binary = gray <= thresh
plt.imshow(binary, interpolation='nearest', cmap=plt.cm.gray) #轮廓清晰了吧，看着也很萌哦
Out[6]:
我知道，我很萌，但是现在还是不能很好的卖萌，因为我是一堆像素，我需要得到轮廓坐标才可以更萌
In [7]:
labels = ms.label(binary, neighbors=8)
contours = ms.find_contours(labels, 0.8) #我的边界就在这里面，就是一串一串的坐标罢了
哎，终于可以卖萌了
In [8]:
# Display the image and plot all contours found
with plt.xkcd():
fig, ax = plt.subplots()
ax.imshow(binary, interpolation='nearest', cmap=plt.cm.gray)
for n, contour in enumerate(contours):
ax.plot(contour[:, 1], contour[:, 0], linewidth=1)
ax.annotate('Do you know?\n I\'m a cute sheep.', (0.2, 0.45), textcoords='axes fraction', size=20)
ax.axis('image')
ax.set_xticks([])
ax.set_yticks([])
plt.show()
你不用说，我知道我很萌，O(∩_∩)O~