对图像均值滤波并计算PSNR,SSIM的 python代码

以下是Python中对图像进行均值滤波并计算PSNR和SSIM的示例代码：

import cv2
import numpy as np
from skimage.measure import compare_ssim

# 读取图像
img = cv2.imread('image.jpg')

# 进行均值滤波
kernel = np.ones((5, 5), np.float32) / 25
img_smooth = cv2.filter2D(img, -1, kernel)

# 计算PSNR
mse = np.mean((img - img_smooth) ** 2)
psnr = 10 * np.log10(255 ** 2 / mse)

# 计算SSIM
ssim = compare_ssim(cv2.cvtColor(img, cv2.COLOR_BGR2GRAY),
                    cv2.cvtColor(img_smooth, cv2.COLOR_BGR2GRAY),
                    gaussian_weights=True,
                    sigma=1.5,
                    use_sample_covariance=False)

# 输出结果
print("PSNR:", psnr)
print("SSIM:", ssim)

注意，这里的输入图像文件名应该替换为你自己的图像文件名。

相关问题

给我评价两幅图像的ssim以及PSNR的Python代码

以下是给出两幅图像的 SSIM 和 PSNR 的 Python 代码：

import cv2
import numpy as np

def ssim(image1, image2):
    """Calculate the Structural Similarity Index (SSIM) between two images."""
    # Set constants
    C1 = (0.01 * 255) ** 2
    C2 = (0.03 * 255) ** 2

    # Convert the images to grayscale
    img1 = cv2.cvtColor(image1, cv2.COLOR_BGR2GRAY)
    img2 = cv2.cvtColor(image2, cv2.COLOR_BGR2GRAY)

    # Calculate means and variances
    mu1 = cv2.GaussianBlur(img1, (11, 11), 1.5)
    mu2 = cv2.GaussianBlur(img2, (11, 11), 1.5)
    mu1_sq = mu1 ** 2
    mu2_sq = mu2 ** 2
    mu1_mu2 = mu1 * mu2

    sigma1_sq = cv2.GaussianBlur(img1 ** 2, (11, 11), 1.5) - mu1_sq
    sigma2_sq = cv2.GaussianBlur(img2 ** 2, (11, 11), 1.5) - mu2_sq
    sigma12 = cv2.GaussianBlur(img1 * img2, (11, 11), 1.5) - mu1_mu2

    # Calculate SSIM
    num = (2 * mu1_mu2 + C1) * (2 * sigma12 + C2)
    den = (mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2)
    ssim = np.mean(num / den)

    return ssim

def psnr(image1, image2):
    """Calculate the Peak Signal-to-Noise Ratio (PSNR) between two images."""
    mse = np.mean((image1 - image2) ** 2)
    if mse == 0:
        return float('inf')
    else:
        max_pixel = 255.0
        psnr = 20 * np.log10(max_pixel / np.sqrt(mse))
        return psnr

其中，`image1` 和 `image2` 分别为两幅图像的 numpy 数组。使用方法如下：

# Load the two images
image1 = cv2.imread('image1.jpg')
image2 = cv2.imread('image2.jpg')

# Calculate SSIM and PSNR
ssim_value = ssim(image1, image2)
psnr_value = psnr(image1, image2)

# Print the results
print('SSIM:', ssim_value)
print('PSNR:', psnr_value)

请注意，这些度量标准仅作为图像质量的参考，它们并不能完全描述图像的质量。因此，建议在实际应用中结合其他度量标准进行分析。

请用python代码实现计算psnr和ssim

好的，下面是使用Python实现计算PSNR和SSIM的代码：

import cv2
import numpy as np

def psnr(img1, img2):
    mse = np.mean((img1 - img2) ** 2)
    if mse == 0:
        return float('inf')
    PIXEL_MAX = 255.0
    return 20 * np.log10(PIXEL_MAX / np.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 np.mean(ssim_map)

# 读取图片
img1 = cv2.imread('img1.png')
img2 = cv2.imread('img2.png')

# 计算PSNR和SSIM
print('PSNR:', psnr(img1, img2))
print('SSIM:', ssim(img1, img2))

其中，`psnr()`函数计算PSNR，`ssim()`函数计算SSIM。需要注意的是，需要安装OpenCV库才能运行该代码。