第5章 Python 数字图像处理(DIP) - 图像复原与重建4 - 指数噪声

指数噪声

指数噪声的PDF为
$$P(z)=\{\begin{array}{ll}a{e}^{-az},& z\ge 0\\ 0,& z<0\end{array}\text{\hspace{1em}(5.10)}$$

均值和方差为
$$\bar{z}=\frac{1}{a}\text{\hspace{1em}(5.11)}$$
$${\sigma }^2=\frac{1}{a^2}\text{\hspace{1em}(5.12)}$$

def exponential_pdf(z, a=1):
    """
    create exponential PDF, math $$P(z) = \begin{cases} ae^{-az}, & z\geq 0 \\ 0, & z < 0 \end{cases}$$
    param: z: input grayscale value of iamge
    param: a: float,
    """
    exp = a * np.exp(-a * z)
    exp = np.where(z >= 0, exp, 0)
    
    return exp

更正下面代码，如果之前已经复制的，也请更正

def add_exponent_noise(img, scale=1.0):
    """
    add gamma noise for image
    param: img: input image, dtype=uint8
    param: mean: noise mean
    param: sigma: noise sigma
    return: image_out: image with gamma noise
    """
    # image = np.array(img/255, dtype=float) # 这是有错误的，将得不到正确的结果，修改如下
	image = np.array(img, dtype=float)
    noise = np.random.exponential(scale=scale, size=image.shape)
      
    image_out = image + noise
    image_out = np.uint8(normalize(image_out)*255)
    
    return image_out

# 指数噪声
a = 0.5
z = np.linspace(0, 10, 200)

z_ = 1 / a
sigma = 1 / a**2

print(f"z_ -> {z_}, sigma -> {sigma}")

exponet =  exponential_pdf(z, a=a)

plt.figure(figsize=(9, 6))
plt.plot(z, exponet)
plt.show()

z_ -> 2.0, sigma -> 4.0

# 指数噪声
img_ori = cv2.imread("DIP_Figures/DIP3E_Original_Images_CH05/Fig0503 (original_pattern).tif", 0)
# img_ori = np.ones((512, 512)) * 128
img_exponent = add_exponent_noise(img_ori, scale=20)

plt.figure(figsize=(9, 6))
plt.subplot(121), plt.imshow(img_ori, 'gray', vmin=0, vmax=255), plt.xticks([]), plt.yticks([])
plt.subplot(122), plt.imshow(img_exponent, 'gray', vmin=0, vmax=255), plt.xticks([]), plt.yticks([])

plt.tight_layout()
plt.show()

hist, bins = np.histogram(img_exponent.flatten(), bins=255, range=[0, 255], density=True)
bar = plt.bar(bins[:-1], hist[:])