A little something to remove similar concurrent (only concurrent) images in a folder(s) in Python.

imgsimfilter.py

import math, operator
from functools import reduce
from PIL import Image
from os import listdir, remove
from os.path import isfile, join
import sys

def update(currImage, totalImages, suffix=''):
    filledSize = int(round(20 * currImage / float(totalImages)))
    perc = round(100.0 * currImage / float(totalImages), 1)
    bar = '=' * filledSize + '-' * (20 - filledSize)

    sys.stdout.write('[%s] %s%s ...%s\r' % (bar, perc, '%', suffix))
    sys.stdout.flush()

def compare(file1, file2):
    
    h1 = Image.open(file1).histogram()
    h2 = Image.open(file2).histogram()

    return math.sqrt(reduce(operator.add, map(lambda a,b: (a-b)**2, h1, h2)) / len(h1))


if __name__ == '__main__':

    if len(sys.argv) <= 1:
        
        print("Usage: filter.py folder1 [,folder2] [,folderN]")
    
    else:
        
        for path in sys.argv[1:]:

            files = [join(path, f) for f in listdir(path) if isfile(join(path, f))]

            for i in range(len(files) - 2, -1, -1):
                
                update(len(files) - i, len(files), files[i])
                
                if (compare(files[i], files[i + 1]) < 150):
                    remove(files[i])
                    files.remove(files[i])

            print()