Detect dublicate gif files without OCR

Now I wrote following script that check each two GIF files in a folder in very high speed! 

import cv2
import numpy as np
import os
from concurrent.futures import ProcessPoolExecutor, as_completed
import keyboard

def calculate_similarity_percentage(file1, file2):
    # Read the GIF files
    gif1 = cv2.VideoCapture(file1)
    gif2 = cv2.VideoCapture(file2)

    # Read the first frame of each GIF
    _, frame1 = gif1.read()
    _, frame2 = gif2.read()

    # Resize frames to a common size
    frame1 = cv2.resize(frame1, (640, 480))
    frame2 = cv2.resize(frame2, (640, 480))

    # Convert frames to grayscale
    gray1 = cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)
    gray2 = cv2.cvtColor(frame2, cv2.COLOR_BGR2GRAY)

    # Apply Gaussian blur to the frames
    blurred1 = cv2.GaussianBlur(gray1, (15, 15), 0)
    blurred2 = cv2.GaussianBlur(gray2, (15, 15), 0)

    # Find the absolute difference between the two blurred frames
    diff = cv2.absdiff(blurred1, blurred2)

    # Threshold the difference image
    _, thresholded = cv2.threshold(diff, 30, 255, cv2.THRESH_BINARY)

    # Calculate the difference percentage
    total_pixels = thresholded.size
    non_zero_pixels = cv2.countNonZero(thresholded)
    difference_percentage = (non_zero_pixels / total_pixels) * 100

    # Calculate the similarity percentage
    similarity_percentage = 100 - difference_percentage

    return similarity_percentage

def compare_files_chunk(files_chunk, directory):
    results = []
    for i in range(1, len(files_chunk)):
        file_path1 = os.path.join(directory, files_chunk[i - 1])
        file_path2 = os.path.join(directory, files_chunk[i])
        similarity_percentage = calculate_similarity_percentage(file_path1, file_path2)
        results.append(f"Comparison between {files_chunk[i - 1]} and {files_chunk[i]}: {similarity_percentage:.2f}%")

    return results

def compare_all_files(directory, output_file):
    files = sorted([f for f in os.listdir(directory) if f.lower().endswith('.gif')])
    num_files = len(files)
    chunk_size = min(num_files, os.cpu_count() * 4)  # Adjust the chunk size based on your system's capabilities

    with open(output_file, 'w') as f_out, ProcessPoolExecutor() as executor:
        futures = []

        for i in range(0, num_files, chunk_size):
            files_chunk = files[i:i + chunk_size]
            future = executor.submit(compare_files_chunk, files_chunk, directory)
            futures.append(future)

        for future in as_completed(futures):
            results = future.result()
            f_out.write('\n'.join(results) + '\n')

            # Check for 'F6' key press to stop the process
            if keyboard.is_pressed('F6'):
                print("Process stopped by user.")
                return

def main():
    directory = r'E:\Desktop\Armies\L1816_2'
    output_file = r'E:\Desktop\Armies\comparison_results.txt'

    try:
        compare_all_files(directory, output_file)
        print("Comparison completed. Results saved in:", output_file)

    except Exception as e:
        print(f"Error: {str(e)}")

if __name__ == "__main__":
    main()