如何计算两个图像之间的相似度百分比？

Question

我写了一个代码片段来计算结构相似性指数（SSIM），像素相似性，用于测量相似性的筛分功能以及两个图像之间的推土机距离。我想结合使用这四个指标来找到相似度百分比。

我尝试了度量标准中所有值的平均值，并将其转换为百分比。但是我对此方法非常怀疑

import warnings
from skimage.measure import compare_ssim
from skimage.transform import resize
from scipy.stats import wasserstein_distance
from scipy.misc import imsave
from scipy.ndimage import imread
import numpy as np
import cv2

##
# Globals
##

warnings.filterwarnings('ignore')

# specify resized image sizes
height = 2**10
width = 2**10

##
# Functions
##

def get_img(path, norm_size=True, norm_exposure=False):
  '''
  Prepare an image for image processing tasks
  '''
  # flatten returns a 2d grayscale array
  img = imread(path, flatten=True).astype(int)
  # resizing returns float vals 0:255; convert to ints for downstream tasks
  if norm_size:
    img = resize(img, (height, width), anti_aliasing=True, preserve_range=True)
  if norm_exposure:
    img = normalize_exposure(img)
  return img


def get_histogram(img):
  '''
  Get the histogram of an image. For an 8-bit, grayscale image, the
  histogram will be a 256 unit vector in which the nth value indicates
  the percent of the pixels in the image with the given darkness level.
  The histogram's values sum to 1.
  '''
  h, w = img.shape
  hist = [0.0] * 256
  for i in range(h):
    for j in range(w):
      hist[img[i, j]] += 1
  return np.array(hist) / (h * w) 


def normalize_exposure(img):
  '''
  Normalize the exposure of an image.
  '''
  img = img.astype(int)
  hist = get_histogram(img)
  # get the sum of vals accumulated by each position in hist
  cdf = np.array([sum(hist[:i+1]) for i in range(len(hist))])
  # determine the normalization values for each unit of the cdf
  sk = np.uint8(255 * cdf)
  # normalize each position in the output image
  height, width = img.shape
  normalized = np.zeros_like(img)
  for i in range(0, height):
    for j in range(0, width):
      normalized[i, j] = sk[img[i, j]]
  return normalized.astype(int)


def earth_movers_distance(path_a, path_b):
  '''
  Measure the Earth Mover's distance between two images
  @args:
    {str} path_a: the path to an image file
    {str} path_b: the path to an image file
  @returns:
    TODO
  '''
  img_a = get_img(path_a, norm_exposure=True)
  img_b = get_img(path_b, norm_exposure=True)
  hist_a = get_histogram(img_a)
  hist_b = get_histogram(img_b)
  return wasserstein_distance(hist_a, hist_b)


def structural_sim(path_a, path_b):
  '''
  Measure the structural similarity between two images
  @args:
    {str} path_a: the path to an image file
    {str} path_b: the path to an image file
  @returns:
    {float} a float {-1:1} that measures structural similarity
      between the input images
  '''
  img_a = get_img(path_a)
  img_b = get_img(path_b)
  sim, diff = compare_ssim(img_a, img_b, full=True) # if 1 they are similar
  return sim


def pixel_sim(path_a, path_b):
  '''
  Measure the pixel-level similarity between two images
  @args:
    {str} path_a: the path to an image file
    {str} path_b: the path to an image file
  @returns:
    {float} a float {-1:1} that measures structural similarity
      between the input images
  '''
  img_a = get_img(path_a, norm_exposure=True)
  img_b = get_img(path_b, norm_exposure=True)
  return np.sum(np.absolute(img_a - img_b)) / float(height*width) / 255


def sift_sim(path_a, path_b):
  '''
  Use SIFT features to measure image similarity
  @args:
    {str} path_a: the path to an image file
    {str} path_b: the path to an image file
  @returns:
    TODO
  '''
  # initialize the sift feature detector
  orb = cv2.ORB()

  # get the images
  img_a = cv2.imread(path_a, 0)
  img_b = cv2.imread(path_b, 0)

  # find the keypoints and descriptors with SIFT
  kp_a, desc_a = orb.detectAndCompute(img_a, None)
  kp_b, desc_b = orb.detectAndCompute(img_b, None)

  # initialize the bruteforce matcher
  bf = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck=True)

  # match.distance is a float between {0:100} - lower means more similar
  matches = bf.match(desc_a, desc_b)
  similar_regions = [i for i in matches if i.distance < 70]
  if len(matches) == 0:
    return 0
  return len(similar_regions) / float(len(matches))


if __name__ == '__main__':
  img_a = 'sample/image1.png'
  img_b = 'sample/image2.png' #sample/087_GR_ALL_RS_036.png
  # get the similarity values
  structural_sim = structural_sim(img_a, img_b) # 1 is perfect structural similarity. A value of -1 indicates no structural similarity
  pixel_sim = pixel_sim(img_a, img_b) # 0 is similar
  sift_sim = sift_sim(img_a, img_b) # 1 is similar
  emd = earth_movers_distance(img_a, img_b) # 0.0 is similar
  print(structural_sim, pixel_sim, sift_sim, emd)

我希望结果的百分比为75％，88％，90％。

[EDIT]考虑来自https://imgur.com/Ys2xXJu的image1 并考虑来自https://imgur.com/881sz0V

的image2