结构相似性指数

在比较图像时，均方误差（MSE）虽然实现简单，但并不能很好地指示感知的相似性。结构相似性旨在通过考虑纹理来解决这一不足 [1], [2]。

该示例展示了输入图像的两种修改，每种修改的均方误差（MSE）相同，但平均结构相似性指数差异很大。

[1]

Zhou Wang; Bovik, A.C.; ,“均方误差：爱它还是离开它？信号保真度测量新视角”，信号处理杂志，IEEE，第26卷，第1期，第98-117页，2009年1月。

[2]

Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, Apr. 2004.

import numpy as np
import matplotlib.pyplot as plt

from skimage import data, img_as_float
from skimage.metrics import structural_similarity as ssim
from skimage.metrics import mean_squared_error


img = img_as_float(data.camera())
rows, cols = img.shape

noise = np.ones_like(img) * 0.2 * (img.max() - img.min())
rng = np.random.default_rng()
noise[rng.random(size=noise.shape) > 0.5] *= -1

img_noise = img + noise
img_const = img + abs(noise)

fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(10, 4), sharex=True, sharey=True)
ax = axes.ravel()

mse_none = mean_squared_error(img, img)
ssim_none = ssim(img, img, data_range=img.max() - img.min())

mse_noise = mean_squared_error(img, img_noise)
ssim_noise = ssim(img, img_noise, data_range=img_noise.max() - img_noise.min())

mse_const = mean_squared_error(img, img_const)
ssim_const = ssim(img, img_const, data_range=img_const.max() - img_const.min())

ax[0].imshow(img, cmap=plt.cm.gray, vmin=0, vmax=1)
ax[0].set_xlabel(f'MSE: {mse_none:.2f}, SSIM: {ssim_none:.2f}')
ax[0].set_title('Original image')

ax[1].imshow(img_noise, cmap=plt.cm.gray, vmin=0, vmax=1)
ax[1].set_xlabel(f'MSE: {mse_noise:.2f}, SSIM: {ssim_noise:.2f}')
ax[1].set_title('Image with noise')

ax[2].imshow(img_const, cmap=plt.cm.gray, vmin=0, vmax=1)
ax[2].set_xlabel(f'MSE: {mse_const:.2f}, SSIM: {ssim_const:.2f}')
ax[2].set_title('Image plus constant')

plt.tight_layout()
plt.show()