Duplication Detector 

import os

from PIL import Image

import imagehash

import matplotlib.pyplot as plt

import time

# Starttime for runtime measurement

start = time.time()

# Function to calculate perceptual hash for an image

def get_image_hash(image_path):

    #Open image and compute a perceptual hash (pHash) for an image

    with Image.open(image_path) as img:

        return imagehash.phash(img) 

# Function to find duplicate images in a dataset

def find_duplicates(image_folder):

    hashes = {}         # Dictionary to store image hashes and their associated files

    duplicates = []     # List to store paths of duplicate image pairs

    count = 0           # Number of images trakced

    # Iterate through the files in the USB 

    for image_filename in os.listdir(image_folder):

        # Create full file path

        image_path = os.path.join(image_folder, image_filename)

        # Check if the file is an image (this is kinda optional, but makes it safe)

        if image_filename.lower().endswith(('.png', '.jpg', '.jpeg', '.tiff', '.bmp', '.gif')):

            try:

                image_hash = get_image_hash(image_path)     # Calculate the hash for the current image

                count = count+1

                print(count)

            except Exception as e:

                print(f"Error processing image {image_filename}: {e}")  # Skip file if there's an error

                continue

            # If the hash already exists, it's a duplicate

            if image_hash in hashes:

                duplicates.append((image_filename, hashes[image_hash])) # If the hash exists, add 

            else:

                hashes[image_hash] = image_filename

    return duplicates

def display_image_pairs(image_folder, duplicates):

    for dup in duplicates:

        img1_path = os.path.join(image_folder, dup[0])

        img2_path = os.path.join(image_folder, dup[1])

        # img1 = Image.open(img1_path)

        # img2 = Image.open(img2_path)

        print("Duplicate: ", img1_path, img2_path)

        # Plot the images side by side - shown for demonstration

        # fig, axes = plt.subplots(1, 2, figsize=(10, 5))

        # axes[0].imshow(img1)

        # axes[0].set_title(f'Duplicate 1: {dup[0]}')

        # axes[0].axis('off')

        # axes[1].imshow(img2)

        # axes[1].set_title(f'Duplicate 2: {dup[1]}')

        # axes[1].axis('off')

        # plt.show()

# Set the path to the USB (D:\) <-- This is the SPLASHSTICK 

image_folder = 'D:\\'

# Find and print duplicate images

duplicates = find_duplicates(image_folder)

if duplicates:

    pass

    # Display the duplicates

    display_image_pairs(image_folder, duplicates)

else:

    print("No duplicate images found.")

end = time.time()

print("Runtime: ", end - start," seconds")