K-means算法应用：图片压缩

from sklearn.datasets import load_sample_image
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

china = load_sample_image("china.jpg")
plt.imshow(china)
plt.show()

 

读取一张示例图片或本身准备的图片，观察图片存放数据特色。

import matplotlib.image as img
ge = img.imread('F:\\ge.jpg')
plt.imshow(ge)
plt.show()

plt.imshow(ge[:,:,0])

print(ge.shape)
ge

 

根据图片的分辨率，可适当下降分辨率

ges = ge[::3,::3]
plt.imshow(ges)
plt.show()

from sklearn.datasets import load_sample_image
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

china = load_sample_image("china.jpg")
plt.imshow(china)
plt.show()

image = china[::3, ::3]
X = image.reshape(-1,3)
print(china.shape,image.shape,X.shape)

n_colors = 64
model = KMeans(n_colors)
labels = model.fit_predict(X)
colors = model.cluster_centers_

new_image=colors[labels]

new_image=new_image.reshape(image.shape) 

plt.imshow(new_image.astype(np.uint8))

 plt.show()

 

 

import sys
print(sys.getsizeof(china))
print(sys.getsizeof(new_image))

 

 

理解贝叶斯定理