Running a python code to compare two images. It seems to compare most images well, that do not have white background but gets low results for equal images where white is not the same. Attaching the full code. original comparison I get a similarty of 50% or so which seems low since the images are identical.
import requests
import pandas as pd
import string
import time
import traceback
import os
import sys
import re
import os
import urllib.request
import io
import base64
import datetime
from lxml.html import fromstring
from functools import reduce
from itertools import cycle
from requests.exceptions import ConnectTimeout,ProxyError,ReadTimeout, ConnectionError
from bs4 import BeautifulSoup
from random import shuffle
from PIL import Image
from scipy.signal import gaussian
import numpy
from scipy.signal import fftconvolve
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
from PIL import Image, ImageChops
import cv2
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from selenium.webdriver.chrome.options import Options
from selenium import webdriver
file = r'Z:\Shared\Boto Egnyte\03 Resources\TOOLS\00 DESIGN rename\00 LIBRARY\TMP\orig.jpg'
a_to_z = string.ascii_uppercase
big_num = 0
def ssim(im1, im2, window, k=(0.01, 0.03), l=255):
"""See https://ece.uwaterloo.ca/~z70wang/research/ssim/"""
# Check if the window is smaller than the images.
for a, b in zip(window.shape, im1.shape):
if a > b:
return None, None
# Values in k must be positive according to the base implementation.
for ki in k:
if ki < 0:
return None, None
c1 = (k[0] * l) ** 2
c2 = (k[1] * l) ** 2
window = window/numpy.sum(window)
mu1 = fftconvolve(im1, window, mode='valid')
mu2 = fftconvolve(im2, window, mode='valid')
mu1_sq = mu1 * mu1
mu2_sq = mu2 * mu2
mu1_mu2 = mu1 * mu2
sigma1_sq = fftconvolve(im1 * im1, window, mode='valid') - mu1_sq
sigma2_sq = fftconvolve(im2 * im2, window, mode='valid') - mu2_sq
sigma12 = fftconvolve(im1 * im2, window, mode='valid') - mu1_mu2
if c1 > 0 and c2 > 0:
num = (2 * mu1_mu2 + c1) * (2 * sigma12 + c2)
den = (mu1_sq + mu2_sq + c1) * (sigma1_sq + sigma2_sq + c2)
ssim_map = num / den
else:
num1 = 2 * mu1_mu2 + c1
num2 = 2 * sigma12 + c2
den1 = mu1_sq + mu2_sq + c1
den2 = sigma1_sq + sigma2_sq + c2
ssim_map = numpy.ones(numpy.shape(mu1))
index = (den1 * den2) > 0
ssim_map[index] = (num1[index] * num2[index]) / (den1[index] * den2[index])
index = (den1 != 0) & (den2 == 0)
ssim_map[index] = num1[index] / den1[index]
mssim = ssim_map.mean()
return mssim, ssim_map
def save_image_as_base64(browser, url):
"""
"""
base = browser.execute_async_script("""
var done = arguments[0];
function toDataURL(url, callback) {
var xhr = new XMLHttpRequest();
xhr.onload = function() {
var reader = new FileReader();
reader.onloadend = function() {
callback(reader.result);
}
reader.readAsDataURL(xhr.response);
};
xhr.open('GET', url);
xhr.responseType = 'blob';
xhr.send();
}
setTimeout(function(){
done("notplayed");
}, 12000);
toDataURL('%s', done)""" % url)
base = base.split(',')[-1]
return base
def img_chk(img1, img2, big_num):
# Create a 2d gaussian for the window parameter
win = numpy.array([gaussian(11, 1.5)])
win2d = win * (win.T)
num_metrics = 2
for band1, band2 in zip(img1.split(), img2.split()):
b1 = numpy.asarray(band1, dtype=numpy.double)
b2 = numpy.asarray(band2, dtype=numpy.double)
# SSIM
res, smap = ssim(b1, b2, win2d)
print ("Result:", file, round(res,4))
match_change = False
if big_num == 0:
big_num = round(res,4)
row['Match'] = round(res,4)
match_change = True
if big_num < round(res,4):
row['Match'] = round(res,4)
big_num = round(res,4)
match_change = True
return match_change, big_num
def download_with_selenium(url):
print('getting ',url)
browser.get(url)
time.sleep(1)
html, title = browser.page_source, browser.title
#open(urlparse(url).path[4:]+'.htmk','w',encoding='utf-8').write(html)
return html, title
def expand2square(pil_img, background_color):
width, height = pil_img.size
if width == height:
return pil_img
elif width > height:
result = Image.new(pil_img.mode, (width, width), background_color)
result.paste(pil_img, (0, (width - height) // 2))
return result
else:
result = Image.new(pil_img.mode, (height, height), background_color)
result.paste(pil_img, ((height - width) // 2, 0))
return result
chrome_options = Options()
chrome_options.headless = False
browser = webdriver.Chrome(
service=Service(ChromeDriverManager().install()), options=chrome_options)
df = pd.DataFrame()
row = {}
ok_img = "https://m.media-amazon.com/images/I/51qVJ6oJ7sL._AC_.jpg"
big_num = 0
base = save_image_as_base64(browser, ok_img)
image_file = io.BytesIO(base64.b64decode(base))
img = Image.open(image_file)
wi, hi = img.size
if wi != hi:
img = expand2square(img,(255,255,255))
orig = Image.open(file)
wi, hi = orig.size
if wi != hi:
orig = expand2square(orig,(255,255,255))
if img.size != orig.size:
orig = orig.resize(img.size, Image.ANTIALIAS)
match_change,big_num = img_chk(img, orig, big_num)
print(big_num)
