# 测量PSNR-SSIM平均值

'''
calculate the PSNR and SSIM.
same as MATLAB's results
'''
import os
import math
import numpy as np
import cv2
import glob

def main():
# Configurations

# GT - 原图
# Gen: 生成的图片
folder_GT = ''
folder_Gen = ''

crop_border = 4#边缘剪裁
suffix = ''
test_Y = True  # True: test Y channel only; False: test RGB channels True:只测试Y通道;False:测试RGB通道

PSNR_all = []
SSIM_all = []
# 前面用一个sorted的排序函数对glob遍历出来的数据进行排序并将输出结果保存至img_list列表中。
img_list = sorted(glob.glob(folder_GT + '/*'))

if test_Y:
print('Testing Y channel.')
else:
print('Testing RGB channels.')
# enumerate 函数用于遍历序列中的元素以及它们的下标：
for i, img_path in enumerate(img_list):
base_name = os.path.splitext(os.path.basename(img_path))[0]
# 归一化GT
# 归一化Gen
im_Gen = cv2.imread(os.path.join(folder_Gen, base_name + '.png')) / 255.

if test_Y and im_GT.shape[2] == 3:  # evaluate on Y channel in YCbCr color spaceYCbCr颜色空间中Y通道的评价
im_GT_in = bgr2ycbcr(im_GT)
im_Gen_in = bgr2ycbcr(im_Gen)
else:
im_GT_in = im_GT
im_Gen_in = im_Gen

# crop borders 边界剪裁
if im_GT_in.ndim == 3:#维度

cropped_GT = im_GT_in[crop_border:-crop_border, crop_border:-crop_border, :]
cropped_Gen = im_Gen_in[crop_border:-crop_border, crop_border:-crop_border, :]
elif im_GT_in.ndim == 2:
cropped_GT = im_GT_in[crop_border:-crop_border, crop_border:-crop_border]
cropped_Gen = im_Gen_in[crop_border:-crop_border, crop_border:-crop_border]
else:
raise ValueError('Wrong image dimension: {}. Should be 2 or 3.'.format(im_GT_in.ndim))

# calculate PSNR and SSIM
PSNR = calculate_psnr(cropped_GT * 255, cropped_Gen * 255)

SSIM = calculate_ssim(cropped_GT * 255, cropped_Gen * 255)
print('{:3d} - {:25}. \tPSNR: {:.6f} dB, \tSSIM: {:.6f}'.format(
i + 1, base_name, PSNR, SSIM))
PSNR_all.append(PSNR)# 所有图片的PSNR
SSIM_all.append(SSIM)
print('Average: PSNR: {:.6f} dB, SSIM: {:.6f}'.format(
sum(PSNR_all) / len(PSNR_all),
sum(SSIM_all) / len(SSIM_all)))

def calculate_psnr(img1, img2):
# img1 and img2 have range [0, 255]
img1 = img1.astype(np.float64)
img2 = img2.astype(np.float64)
mse = np.mean((img1 - img2)**2)
if mse == 0:
return float('inf')
return 20 * math.log10(255.0 / math.sqrt(mse))

def ssim(img1, img2):
C1 = (0.01 * 255)**2
C2 = (0.03 * 255)**2

img1 = img1.astype(np.float64)
img2 = img2.astype(np.float64)
kernel = cv2.getGaussianKernel(11, 1.5)
window = np.outer(kernel, kernel.transpose())

mu1 = cv2.filter2D(img1, -1, window)[5:-5, 5:-5]  # valid
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(img1**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(img1 * 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(img1, img2):
'''calculate SSIM
the same outputs as MATLAB's
img1, img2: [0, 255]
'''
if not img1.shape == img2.shape:
raise ValueError('Input images must have the same dimensions.')
if img1.ndim == 2:
return ssim(img1, img2)
elif img1.ndim == 3:
if img1.shape[2] == 3:
ssims = []
for i in range(3):
ssims.append(ssim(img1, img2))
return np.array(ssims).mean()
elif img1.shape[2] == 1:
return ssim(np.squeeze(img1), np.squeeze(img2))
else:
raise ValueError('Wrong input image dimensions.')

def bgr2ycbcr(img, only_y=True):
'''same as matlab rgb2ycbcr
only_y: only return Y channel
Input:
uint8, [0, 255]
float, [0, 1]
'''
in_img_type = img.dtype
img.astype(np.float32)
if in_img_type != np.uint8:
img *= 255.
# convert
if only_y:
rlt = np.dot(img, [24.966, 128.553, 65.481]) / 255.0 + 16.0
else:
rlt = np.matmul(img, [[24.966, 112.0, -18.214], [128.553, -74.203, -93.786],
[65.481, -37.797, 112.0]]) / 255.0 + [16, 128, 128]
if in_img_type == np.uint8:
rlt = rlt.round()
else:
rlt /= 255.
return rlt.astype(in_img_type)

if __name__ == '__main__':
main()

• 点赞
• 评论
• 分享
x

海报分享

扫一扫，分享海报

• 收藏
• 手机看

分享到微信朋友圈

x

扫一扫，手机阅读

• 打赏

打赏

不动脑筋

你的鼓励将是我创作的最大动力

C币 余额
2C币 4C币 6C币 10C币 20C币 50C币
• 一键三连

点赞Mark关注该博主, 随时了解TA的最新博文
11-08

06-05
03-15 2万+
10-04 1万+
11-13 4083
09-12 2608
07-07 4万+
07-14 621