File size: 7,971 Bytes
97b6013 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 |
#!/usr/bin/python
#
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Python implementation of MS-SSIM.
Usage:
python msssim.py --original_image=original.png --compared_image=distorted.png
"""
import numpy as np
from scipy import signal
from scipy.ndimage.filters import convolve
import tensorflow as tf
tf.flags.DEFINE_string('original_image', None, 'Path to PNG image.')
tf.flags.DEFINE_string('compared_image', None, 'Path to PNG image.')
FLAGS = tf.flags.FLAGS
def _FSpecialGauss(size, sigma):
"""Function to mimic the 'fspecial' gaussian MATLAB function."""
radius = size // 2
offset = 0.0
start, stop = -radius, radius + 1
if size % 2 == 0:
offset = 0.5
stop -= 1
x, y = np.mgrid[offset + start:stop, offset + start:stop]
assert len(x) == size
g = np.exp(-((x**2 + y**2)/(2.0 * sigma**2)))
return g / g.sum()
def _SSIMForMultiScale(img1, img2, max_val=255, filter_size=11,
filter_sigma=1.5, k1=0.01, k2=0.03):
"""Return the Structural Similarity Map between `img1` and `img2`.
This function attempts to match the functionality of ssim_index_new.m by
Zhou Wang: http://www.cns.nyu.edu/~lcv/ssim/msssim.zip
Arguments:
img1: Numpy array holding the first RGB image batch.
img2: Numpy array holding the second RGB image batch.
max_val: the dynamic range of the images (i.e., the difference between the
maximum the and minimum allowed values).
filter_size: Size of blur kernel to use (will be reduced for small images).
filter_sigma: Standard deviation for Gaussian blur kernel (will be reduced
for small images).
k1: Constant used to maintain stability in the SSIM calculation (0.01 in
the original paper).
k2: Constant used to maintain stability in the SSIM calculation (0.03 in
the original paper).
Returns:
Pair containing the mean SSIM and contrast sensitivity between `img1` and
`img2`.
Raises:
RuntimeError: If input images don't have the same shape or don't have four
dimensions: [batch_size, height, width, depth].
"""
if img1.shape != img2.shape:
raise RuntimeError('Input images must have the same shape (%s vs. %s).',
img1.shape, img2.shape)
if img1.ndim != 4:
raise RuntimeError('Input images must have four dimensions, not %d',
img1.ndim)
img1 = img1.astype(np.float64)
img2 = img2.astype(np.float64)
_, height, width, _ = img1.shape
# Filter size can't be larger than height or width of images.
size = min(filter_size, height, width)
# Scale down sigma if a smaller filter size is used.
sigma = size * filter_sigma / filter_size if filter_size else 0
if filter_size:
window = np.reshape(_FSpecialGauss(size, sigma), (1, size, size, 1))
mu1 = signal.fftconvolve(img1, window, mode='valid')
mu2 = signal.fftconvolve(img2, window, mode='valid')
sigma11 = signal.fftconvolve(img1 * img1, window, mode='valid')
sigma22 = signal.fftconvolve(img2 * img2, window, mode='valid')
sigma12 = signal.fftconvolve(img1 * img2, window, mode='valid')
else:
# Empty blur kernel so no need to convolve.
mu1, mu2 = img1, img2
sigma11 = img1 * img1
sigma22 = img2 * img2
sigma12 = img1 * img2
mu11 = mu1 * mu1
mu22 = mu2 * mu2
mu12 = mu1 * mu2
sigma11 -= mu11
sigma22 -= mu22
sigma12 -= mu12
# Calculate intermediate values used by both ssim and cs_map.
c1 = (k1 * max_val) ** 2
c2 = (k2 * max_val) ** 2
v1 = 2.0 * sigma12 + c2
v2 = sigma11 + sigma22 + c2
ssim = np.mean((((2.0 * mu12 + c1) * v1) / ((mu11 + mu22 + c1) * v2)))
cs = np.mean(v1 / v2)
return ssim, cs
def MultiScaleSSIM(img1, img2, max_val=255, filter_size=11, filter_sigma=1.5,
k1=0.01, k2=0.03, weights=None):
"""Return the MS-SSIM score between `img1` and `img2`.
This function implements Multi-Scale Structural Similarity (MS-SSIM) Image
Quality Assessment according to Zhou Wang's paper, "Multi-scale structural
similarity for image quality assessment" (2003).
Link: https://ece.uwaterloo.ca/~z70wang/publications/msssim.pdf
Author's MATLAB implementation:
http://www.cns.nyu.edu/~lcv/ssim/msssim.zip
Arguments:
img1: Numpy array holding the first RGB image batch.
img2: Numpy array holding the second RGB image batch.
max_val: the dynamic range of the images (i.e., the difference between the
maximum the and minimum allowed values).
filter_size: Size of blur kernel to use (will be reduced for small images).
filter_sigma: Standard deviation for Gaussian blur kernel (will be reduced
for small images).
k1: Constant used to maintain stability in the SSIM calculation (0.01 in
the original paper).
k2: Constant used to maintain stability in the SSIM calculation (0.03 in
the original paper).
weights: List of weights for each level; if none, use five levels and the
weights from the original paper.
Returns:
MS-SSIM score between `img1` and `img2`.
Raises:
RuntimeError: If input images don't have the same shape or don't have four
dimensions: [batch_size, height, width, depth].
"""
if img1.shape != img2.shape:
raise RuntimeError('Input images must have the same shape (%s vs. %s).',
img1.shape, img2.shape)
if img1.ndim != 4:
raise RuntimeError('Input images must have four dimensions, not %d',
img1.ndim)
# Note: default weights don't sum to 1.0 but do match the paper / matlab code.
weights = np.array(weights if weights else
[0.0448, 0.2856, 0.3001, 0.2363, 0.1333])
levels = weights.size
downsample_filter = np.ones((1, 2, 2, 1)) / 4.0
im1, im2 = [x.astype(np.float64) for x in [img1, img2]]
mssim = np.array([])
mcs = np.array([])
for _ in range(levels):
ssim, cs = _SSIMForMultiScale(
im1, im2, max_val=max_val, filter_size=filter_size,
filter_sigma=filter_sigma, k1=k1, k2=k2)
mssim = np.append(mssim, ssim)
mcs = np.append(mcs, cs)
filtered = [convolve(im, downsample_filter, mode='reflect')
for im in [im1, im2]]
im1, im2 = [x[:, ::2, ::2, :] for x in filtered]
return (np.prod(mcs[0:levels-1] ** weights[0:levels-1]) *
(mssim[levels-1] ** weights[levels-1]))
def main(_):
if FLAGS.original_image is None or FLAGS.compared_image is None:
print('\nUsage: python msssim.py --original_image=original.png '
'--compared_image=distorted.png\n\n')
return
if not tf.gfile.Exists(FLAGS.original_image):
print('\nCannot find --original_image.\n')
return
if not tf.gfile.Exists(FLAGS.compared_image):
print('\nCannot find --compared_image.\n')
return
with tf.gfile.FastGFile(FLAGS.original_image) as image_file:
img1_str = image_file.read('rb')
with tf.gfile.FastGFile(FLAGS.compared_image) as image_file:
img2_str = image_file.read('rb')
input_img = tf.placeholder(tf.string)
decoded_image = tf.expand_dims(tf.image.decode_png(input_img, channels=3), 0)
with tf.Session() as sess:
img1 = sess.run(decoded_image, feed_dict={input_img: img1_str})
img2 = sess.run(decoded_image, feed_dict={input_img: img2_str})
print((MultiScaleSSIM(img1, img2, max_val=255)))
if __name__ == '__main__':
tf.app.run()
|