使用Numpy进行图像量化

Question

我想看看这个关于图像量化的示例代码，链接在这里。不过，这段代码有点老旧，Python和NumPy自那以后也发生了变化。

from pylab import imread,imshow,figure,show,subplot
from numpy import reshape,uint8,flipud
from scipy.cluster.vq import kmeans,vq

img = imread('clearsky.jpg')

# reshaping the pixels matrix
pixel = reshape(img,(img.shape[0]*img.shape[1],3))

# performing the clustering
# print(type(pixel))
centroids,_ = kmeans(pixel,6) # six colors will be found
# quantization
qnt,_ = vq(pixel,centroids)

# reshaping the result of the quantization
centers_idx = reshape(qnt,(img.shape[0],img.shape[1]))
clustered = centroids[centers_idx]

figure(1)
subplot(211)
imshow(flipud(img))
subplot(212)
imshow(flipud(clustered))
show()

代码在第12行出错了，具体是这行：centroids,_ = kmeans(pixel,6)

错误信息显示在文件 "D:\Python30\lib\site-packages\scipy\cluster\vq.py" 的第454行，出错的地方是调用了kmeans函数，里面有个地方叫做 _kmeans，具体在第309行。

错误提示是：TypeError: 不支持浮点数以外的类型。

我可以把6改成6.0，但对于传给kmeans的NParray，我有点困惑，不知道该怎么处理。

我需要做些什么来更新代码，让这个示例能够正常运行呢？

Answer 1

我觉得你只需要把图片的像素转换成浮点数。在把像素传给kmeans之前，先把它们转换成浮点数类型，这样才能确保它们能正常使用：

import matplotlib.pyplot as plt
import numpy as np
from scipy.cluster.vq import kmeans, vq

# Reading the image
img = plt.imread('clearsky.jpg')

# Convert image pixels to float
pixel = np.reshape(img, (img.shape[0]*img.shape[1], 3)).astype(float)

# Performing the clustering
centroids, _ = kmeans(pixel, 6.0)  # six colors will be found

# Quantization
qnt, _ = vq(pixel, centroids)

# Reshaping the result of the quantization
centers_idx = np.reshape(qnt, (img.shape[0], img.shape[1]))
clustered = centroids[centers_idx.astype(int)]

# Displaying the original and quantized images
plt.figure(figsize=(10, 5))
plt.subplot(121)
plt.imshow(img)
plt.title('Original Image')

plt.subplot(122)
plt.imshow(clustered.astype(np.uint8))
plt.title('Quantized Image')
plt.show()