Open CV – Auto Contrast, Brightness, Sharpening – Python Code

After searching for hours for this code, below is Python code for automatically optimizing image contrast and brightness. The code then auto sharpens the image with conservative settings. I applied this to an ESRGAN output in Google Colab. Enjoy!

#@title SHARPEN, AUTO BRIGHTNESS AND CONTRAST, .WEBP VIA CV2
from tqdm import tqdm
import os
import glob
import cv2
import numpy as np
from matplotlib import pyplot as plt


rootdir = "/content/drive/My Drive/Colab-ESRGAN/output/" #@param

extention = '.webp' #@param [".webp", ".jpg"] {allow-input: false}

files = glob.glob(rootdir + '/**/*.png', recursive=True)

# Automatic brightness and contrast optimization with optional histogram clipping
def automatic_brightness_and_contrast(image, clip_hist_percent=1):
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    
    # Calculate grayscale histogram
    hist = cv2.calcHist([gray],[0],None,[256],[0,256])
    hist_size = len(hist)
    
    # Calculate cumulative distribution from the histogram
    accumulator = []
    accumulator.append(float(hist[0]))
    for index in range(1, hist_size):
        accumulator.append(accumulator[index -1] + float(hist[index]))
    
    # Locate points to clip
    maximum = accumulator[-1]
    clip_hist_percent *= (maximum/100.0)
    clip_hist_percent /= 2.0
    
    # Locate left cut
    minimum_gray = 0
    while accumulator[minimum_gray] < clip_hist_percent:
        minimum_gray += 1
    
    # Locate right cut
    maximum_gray = hist_size -1
    while accumulator[maximum_gray] >= (maximum - clip_hist_percent):
        maximum_gray -= 1
    
    # Calculate alpha and beta values
    alpha = 255 / (maximum_gray - minimum_gray)
    beta = -minimum_gray * alpha
    
    '''
    # Calculate new histogram with desired range and show histogram 
    new_hist = cv2.calcHist([gray],[0],None,[256],[minimum_gray,maximum_gray])
    plt.plot(hist)
    plt.plot(new_hist)
    plt.xlim([0,256])
    plt.show()
    '''

    auto_result = cv2.convertScaleAbs(image, alpha=alpha, beta=beta)
    return (auto_result, alpha, beta)

#sharpening_kernel = np.array([[-1, -1, -1], [-1, 9.2, -1], [-1, -1, -1]])
sharpening_kernel = np.array([[0, -1, 0], [-1, 5.3, -1], [0, -1, 0]])

for file in tqdm(files):
    image = cv2.imread(file)
    auto_result, alpha, beta = automatic_brightness_and_contrast(image)
    image_sharp = cv2.filter2D(src=auto_result, ddepth=-1, kernel=sharpening_kernel)
    cv2.imwrite(os.path.join(rootdir, os.path.splitext(os.path.basename(file))[0] + extention), image_sharp)
    os.remove(file)