find_duplicated_image.py

import os
import sys
from PIL import Image

def dhash(image, hash_size=8):
    image = image.convert('L').resize(
        (hash_size + 1, hash_size),
        Image.ANTIALIAS)

    diff = []
    for row in xrange(hash_size):
        for col in xrange(hash_size):
            pixel_left = image.getpixel((col, row))
            pixel_right = image.getpixel((col + 1, row))
            diff.append(pixel_left > pixel_right)

    decimal_value = 0
    hex_string = []

    for index, value in enumerate(diff):
        if value:
            decimal_value += 2**(index % 8)

        if index % 8 == 7:
            hex_string.append(hex(decimal_value)[2:].rjust(2, '0'))
            decimal_value = 0

    image.close()
    return ''.join(hex_string)


if __name__ == '__main__':
    basedir = sys.argv[1]
    images = [os.path.join(base, name)
              for base, dirs, names in os.walk(basedir)
              for name in names
              if os.path.splitext(name)[1].lower() in ('.jpg', '.png')]

    hashmap = {}
    for filename in images:
        image = Image.open(filename)
        dh = dhash(image)
        space = hashmap.get(dh, [])
        space.append(filename)
        hashmap[dh] = space
        image.close()

    print('\n\n'.join(
        '\n'.join(names) for names in hashmap.values()
        if len(names) > 1
    ))