用Python实现通过哈希算法检测图片重复的教程

>>> from PIL import Image
>>> test_image = Image.open('data/test_image.jpg')
 
# The image is an RGB image with a size of 8x8 pixels.
>>> print 'Image Mode: %s' % test_image.mode
Image Mode: RGB
>>> print 'Width: %s px, Height: %s px' % (test_image.size[0], test_image.size[1])
Width: 4 px, Height: 4 px
 
# Get the pixel values from the image and print them into rows based on
# the image's width.
>>> width, height = test_image.size
>>> pixels = list(test_image.getdata())
>>> for col in xrange(width):
...  print pixels[col:col+width]
...
[(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 255)]
[(0, 0, 0), (212, 45, 45), (51, 92, 154), (130, 183, 47)]
[(206, 210, 198), (131, 78, 8), (131, 156, 180), (117, 155, 201)]
[(104, 133, 170), (215, 130, 20), (153, 155, 155), (104, 142, 191)]

现在我们回到dHash算法，该算法有四个步骤，本文详细说明每一步并验证它在原始图像和修改后图像的效果。前三个像素的红绿蓝颜色强度值分别为255，其余两个颜色强度值分别为0，纯黑色像素三原色为0，纯白色像素三原色为255。其它颜色像素则是由不同强度三原色值组成的。

1.图像灰度化

通过灰度化图像，将像素值减少到一个发光强度值。例如,白色像素(255、255、255)成为255而黑色像素(0,0,0)强度值将成为0。

2.将图像缩小到一个常见大小

将图像缩减到一个常见基础尺寸，比如宽度大高度一个像素值的9*8像素大小（到第三步你就能明白为什么是这个尺寸）。通过这个方法将图像中的高频和细节部分移除，从而获得一个有72个强度值的样本。由于调整或者拉伸图像并不会改变它的哈希值，所以将所有图像归一化到该大小。

3.比较邻域像素

前两步实现后得到一个强度值列表，比较该二进制值数组的每一行的相邻像素。

>>> from PIL import Image
>>> img = Image.open('data/cat_grumpy_orig_after_step_2.png')
>>> width, height = img.size
>>> pixels = list(img.getdata())
>>> for col in xrange(width):
...  print pixels[col:col+width]
...
[254, 254, 255, 253, 248, 254, 255, 254, 255]
[254, 255, 253, 248, 254, 255, 254, 255, 255]
[253, 248, 254, 255, 254, 255, 255, 255, 222]
[248, 254, 255, 254, 255, 255, 255, 222, 184]
[254, 255, 254, 255, 255, 255, 222, 184, 177]
[255, 254, 255, 255, 255, 222, 184, 177, 184]
[254, 255, 255, 255, 222, 184, 177, 184, 225]
[255, 255, 255, 222, 184, 177, 184, 225, 255]

>>> difference = []
>>> for row in xrange(height):
...  for col in xrange(width):
...   if col != width:
...    difference.append(pixels[col+row] > pixels[(col+row)+1])
...
>>> for col in xrange(width-1):
...  print difference[col:col+(width-1)]
...
[False, False, True, True, False, False, True, False]
[False, True, True, False, False, True, False, False]
[True, True, False, False, True, False, False, False]
[True, False, False, True, False, False, False, True]
[False, False, True, False, False, False, True, True]
[False, True, False, False, False, True, True, False]
[True, False, False, False, True, True, False, False]
[False, False, False, True, True, False, False, True]

def dhash(image, hash_size = 8):
  # Grayscale and shrink the image in one step.
  image = image.convert('L').resize(
    (hash_size + 1, hash_size),
    Image.ANTIALIAS,
  )
 
  pixels = list(image.getdata())
 
  # Compare adjacent pixels.
  difference = []
  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))
      difference.append(pixel_left > pixel_right)
 
  # Convert the binary array to a hexadecimal string.
  decimal_value = 0
  hex_string = []
  for index, value in enumerate(difference):
    if value:
      decimal_value += 2**(index % 8)
    if (index % 8) == 7:
      hex_string.append(hex(decimal_value)[2:].rjust(2, '0'))
      decimal_value = 0
 
  return ''.join(hex_string)

>>> from PIL import Image
>>> from utility import dhash, hamming_distance
>>> orig = Image.open('data/cat_grumpy_orig.png')
>>> modif = Image.open('data/cat_grumpy_modif.png')
>>> dhash(orig)
'4c8e3366c275650f'
>>> dhash(modif)
'4c8e3366c275650f'
>>> dhash(orig) == dhash(modif)
True

如果有一

SELECT pk, hash, file_path FROM image_hashes
  WHERE hash = '4c8e3366c275650f';

SELECT pk, hash, BIT_COUNT(
  CONV(hash, 16, 10) ^ CONV('4c8e3366c275650f', 16, 10)
) as hamming_distance
  FROM image_hashes
  HAVING hamming_distance < 4
  ORDER BY hamming_distance ASC;