import cv2 import numpy as np import matplotlib.pyplot as plt import os # Correcting the image paths image_before_path = './all_before.png' image_after_path = './all_after.png' # Check if files exist if not os.path.exists(image_before_path): raise FileNotFoundError(f"The file {image_before_path} does not exist.") if not os.path.exists(image_after_path): raise FileNotFoundError(f"The file {image_after_path} does not exist.") # Load the images image_before = cv2.imread(image_before_path, cv2.IMREAD_GRAYSCALE) image_after = cv2.imread(image_after_path, cv2.IMREAD_GRAYSCALE) # Ensure images are the same size if image_before.shape != image_after.shape: print("Images are not the same size. Resizing...") image_after = cv2.resize(image_after, (image_before.shape[1], image_before.shape[0])) # Compute the absolute difference abs_diff = cv2.absdiff(image_before, image_after) # Threshold the difference to highlight erased regions _, thresholded = cv2.threshold(abs_diff, 30, 255, cv2.THRESH_BINARY) # Divide the image into 5 horizontal regions height, width = thresholded.shape line_height = height // 5 erased_pixels_per_line = [] for i in range(5): # Extract the region corresponding to the current line line_region = thresholded[i * line_height:(i + 1) * line_height, :] # Count the number of erased pixels in the region erased_pixels = np.sum(line_region > 0) erased_pixels_per_line.append(erased_pixels) # Identify the line with the most erased pixels most_erased_line = np.argmax(erased_pixels_per_line) + 1 # Display results for i, pixels in enumerate(erased_pixels_per_line): print(f"Line {i + 1}: {pixels} erased pixels") print(f"The line with the most erasures is Line {most_erased_line}.") # Plot the erased regions plt.figure(figsize=(10, 8)) plt.title("Erased Regions") plt.imshow(thresholded, cmap='gray') plt.axis('off') plt.show()

import cv2 import numpy as np import matplotlib.pyplot as plt import os # Correcting the image path image_path = './after_dust.png' # Check if the file exists if not os.path.exists(image_path): raise FileNotFoundError(f"The file {image_path} does not exist.") # Load the image image = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE) if image is None: raise FileNotFoundError(f"The image at path {image_path} could not be loaded. Please check the format or file corruption.") # Preprocessing to enhance dust detection blurred = cv2.GaussianBlur(image, (5, 5), 0) # Apply adaptive thresholding thresholded = cv2.adaptiveThreshold( blurred, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 11, 2 ) # Focus on the bottom three lines by dividing the image into 5 regions height, width = thresholded.shape line_height = height // 5 dust_count_per_line = [] for i in range(5): # Extract the region corresponding to the current line line_region = thresholded[i * line_height:(i + 1) * line_height, :] # Count the number of dust particles (non-zero pixels) dust_pixels = np.sum(line_region > 0) dust_count_per_line.append(dust_pixels) # Identify the lines with the most dust most_dust_lines = np.argsort(dust_count_per_line)[-3:] # Bottom 3 lines with the most dust # Display results for i, dust in enumerate(dust_count_per_line): print(f"Line {i + 1}: {dust} dust particles") print(f"The lines with the most dust are: {', '.join(['Line ' + str(i + 1) for i in most_dust_lines[::-1]])}") # Plot the original image and the thresholded image plt.figure(figsize=(12, 6)) plt.subplot(1, 2, 1) plt.title("Original Image") plt.imshow(image, cmap='gray') plt.axis('off') plt.subplot(1, 2, 2) plt.title("Thresholded (Dust Highlighted)") plt.imshow(thresholded, cmap='gray') plt.axis('off') plt.tight_layout() plt.show()