File size: 4,786 Bytes
98feea6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 |
import cv2
import numpy as np
from PIL import Image
import torchvision.transforms as transforms
def calculate_psnr(img, img2, crop_border, input_order='HWC', test_y_channel=False, **kwargs):
"""Calculate PSNR (Peak Signal-to-Noise Ratio).
Ref: https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio
Args:
img (ndarray): Images with range [0, 255].
img2 (ndarray): Images with range [0, 255].
crop_border (int): Cropped pixels in each edge of an image. These
pixels are not involved in the PSNR calculation.
input_order (str): Whether the input order is 'HWC' or 'CHW'.
Default: 'HWC'.
test_y_channel (bool): Test on Y channel of YCbCr. Default: False.
Returns:
float: psnr result.
"""
assert img.shape == img2.shape, (f'Image shapes are different: {img.shape}, {img2.shape}.')
if input_order not in ['HWC', 'CHW']:
raise ValueError(f'Wrong input_order {input_order}. Supported input_orders are ' '"HWC" and "CHW"')
img = img.astype(np.float64)
img2 = img2.astype(np.float64)
if crop_border != 0:
img = img[crop_border:-crop_border, crop_border:-crop_border, ...]
img2 = img2[crop_border:-crop_border, crop_border:-crop_border, ...]
if test_y_channel:
img = to_y_channel(img)
img2 = to_y_channel(img2)
mse = np.mean((img - img2)**2)
if mse == 0:
return float('inf')
return 20. * np.log10(255. / np.sqrt(mse))
def _ssim(img, img2):
"""Calculate SSIM (structural similarity) for one channel images.
It is called by func:`calculate_ssim`.
Args:
img (ndarray): Images with range [0, 255] with order 'HWC'.
img2 (ndarray): Images with range [0, 255] with order 'HWC'.
Returns:
float: ssim result.
"""
c1 = (0.01 * 255)**2
c2 = (0.03 * 255)**2
img = img.astype(np.float64)
img2 = img2.astype(np.float64)
kernel = cv2.getGaussianKernel(11, 1.5)
window = np.outer(kernel, kernel.transpose())
mu1 = cv2.filter2D(img, -1, window)[5:-5, 5:-5]
mu2 = cv2.filter2D(img2, -1, window)[5:-5, 5:-5]
mu1_sq = mu1**2
mu2_sq = mu2**2
mu1_mu2 = mu1 * mu2
sigma1_sq = cv2.filter2D(img**2, -1, window)[5:-5, 5:-5] - mu1_sq
sigma2_sq = cv2.filter2D(img2**2, -1, window)[5:-5, 5:-5] - mu2_sq
sigma12 = cv2.filter2D(img * img2, -1, window)[5:-5, 5:-5] - mu1_mu2
ssim_map = ((2 * mu1_mu2 + c1) * (2 * sigma12 + c2)) / ((mu1_sq + mu2_sq + c1) * (sigma1_sq + sigma2_sq + c2))
return ssim_map.mean()
def calculate_ssim(img, img2, crop_border, input_order='HWC', test_y_channel=False, **kwargs):
"""Calculate SSIM (structural similarity).
Ref:
Image quality assessment: From error visibility to structural similarity
The results are the same as that of the official released MATLAB code in
https://ece.uwaterloo.ca/~z70wang/research/ssim/.
For three-channel images, SSIM is calculated for each channel and then
averaged.
Args:
img (ndarray): Images with range [0, 255].
img2 (ndarray): Images with range [0, 255].
crop_border (int): Cropped pixels in each edge of an image. These
pixels are not involved in the SSIM calculation.
input_order (str): Whether the input order is 'HWC' or 'CHW'.
Default: 'HWC'.
test_y_channel (bool): Test on Y channel of YCbCr. Default: False.
Returns:
float: ssim result.
"""
assert img.shape == img2.shape, (f'Image shapes are different: {img.shape}, {img2.shape}.')
if input_order not in ['HWC', 'CHW']:
raise ValueError(f'Wrong input_order {input_order}. Supported input_orders are ' '"HWC" and "CHW"')
# img = reorder_image(img, input_order=input_order)
# img2 = reorder_image(img2, input_order=input_order)
img = img.astype(np.float64)
img2 = img2.astype(np.float64)
if crop_border != 0:
img = img[crop_border:-crop_border, crop_border:-crop_border, ...]
img2 = img2[crop_border:-crop_border, crop_border:-crop_border, ...]
if test_y_channel:
img = to_y_channel(img)
img2 = to_y_channel(img2)
ssims = []
for i in range(img.shape[2]):
ssims.append(_ssim(img[..., i], img2[..., i]))
return np.array(ssims).mean()
if __name__ == '__main__':
# test_transforms = transforms.Compose([transforms.Resize((512, 512)),transforms.ToTensor()])
# inp_img = Image.open("/mnt/disk1/yuwei/data/4Kdehaze/train/clear/0_000002.jpg").convert("RGB")
# img = test_transforms(inp_img)
img = cv2.imread("/mnt/disk1/yuwei/data/4Kdehaze/train/clear/0_000002.jpg")
psnr = calculate_psnr(img, img, 0)
ssim = calculate_ssim(img, img, 0)
print(psnr)
print(ssim) |