Today we will read on this page – How to remove similar images from the directory or folder in Python

The basic rationale behind this python program is to create a hash value for each image based not on its name but on its pixel value and calculation. Based on this hash value we are going to store the images in a dictionary, whose key hash value will be generated and the value will hold the binary value of the image itself.

Example to implement the program

import hashlib
from scipy.misc import imread, imresize, imshow
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
import numpy as np
import os
def file_hash(filename):
    with open(filename,'rb') as f:
        return md5(f.read()).hexdigest()
os.getcwd()
os.chdir(r'D:\pytest')
os.getcwd()
files_list = os.listdir('.')
print (len(files_list))
duplicates=[]
hash_keys=dict()
for index, filename in enumerate(os.listdir('.')):
    if os.path.isfile(filename):
        with open(filename, 'rb') as f:
            filehash = hashlib.md5(f.read()).hexdigest()
        if filehash not in hash_keys:
            hash_keys[filehash]=index
        else:
            duplicates.append((index,hash_keys[filehash]))
print(duplicates)
for file_indexes in duplicates[:30]:
    try:
        plt.subplot(121),plt.imshow(imread(files_list[file_indexes[1]]))
        plt.title(file_indexes[1]),plt.xticks([]),plt.yticks([])
        plt.subplot(122),plt.imshow(imread(files_list[file_indexes[0]]))
        plt.title(str(file_indexes[0])+ 'duplicate'),plt.xticks([]),plt.yticks([])
        plt.show()
    except OSError as e:
        continue
for index in duplicates:
    os.remove(files_list[index[0]])

Result

Removing the duplicate images using os.remove

Create the program and run on your computer…..