File size: 12,944 Bytes
ca362b6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
import cv2
import numpy as np
import torch


def calculate_psnr(img1, img2, crop_border, input_order='HWC', test_y_channel=False):
    """Calculate PSNR (Peak Signal-to-Noise Ratio).

    Ref: https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio

    Args:
        img1 (ndarray): Images with range [0, 255].
        img2 (ndarray): Images with range [0, 255].
        crop_border (int): Cropped pixels in each edge of an image. These
            pixels are not involved in the PSNR calculation.
        input_order (str): Whether the input order is 'HWC' or 'CHW'.
            Default: 'HWC'.
        test_y_channel (bool): Test on Y channel of YCbCr. Default: False.

    Returns:
        float: psnr result.
    """

    assert img1.shape == img2.shape, (f'Image shapes are differnet: {img1.shape}, {img2.shape}.')
    if input_order not in ['HWC', 'CHW']:
        raise ValueError(f'Wrong input_order {input_order}. Supported input_orders are ' '"HWC" and "CHW"')
    img1 = reorder_image(img1, input_order=input_order)
    img2 = reorder_image(img2, input_order=input_order)
    img1 = img1.astype(np.float64)
    img2 = img2.astype(np.float64)

    if crop_border != 0:
        img1 = img1[crop_border:-crop_border, crop_border:-crop_border, ...]
        img2 = img2[crop_border:-crop_border, crop_border:-crop_border, ...]

    if test_y_channel:
        img1 = to_y_channel(img1)
        img2 = to_y_channel(img2)

    mse = np.mean((img1 - img2) ** 2)
    if mse == 0:
        return float('inf')
    return 20. * np.log10(255. / np.sqrt(mse))


def _ssim(img1, img2):
    """Calculate SSIM (structural similarity) for one channel images.

    It is called by func:`calculate_ssim`.

    Args:
        img1 (ndarray): Images with range [0, 255] with order 'HWC'.
        img2 (ndarray): Images with range [0, 255] with order 'HWC'.

    Returns:
        float: ssim result.
    """

    C1 = (0.01 * 255) ** 2
    C2 = (0.03 * 255) ** 2

    img1 = img1.astype(np.float64)
    img2 = img2.astype(np.float64)
    kernel = cv2.getGaussianKernel(11, 1.5)
    window = np.outer(kernel, kernel.transpose())

    mu1 = cv2.filter2D(img1, -1, window)[5:-5, 5:-5]
    mu2 = cv2.filter2D(img2, -1, window)[5:-5, 5:-5]
    mu1_sq = mu1 ** 2
    mu2_sq = mu2 ** 2
    mu1_mu2 = mu1 * mu2
    sigma1_sq = cv2.filter2D(img1 ** 2, -1, window)[5:-5, 5:-5] - mu1_sq
    sigma2_sq = cv2.filter2D(img2 ** 2, -1, window)[5:-5, 5:-5] - mu2_sq
    sigma12 = cv2.filter2D(img1 * img2, -1, window)[5:-5, 5:-5] - mu1_mu2

    ssim_map = ((2 * mu1_mu2 + C1) * (2 * sigma12 + C2)) / ((mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2))
    return ssim_map.mean()


def calculate_ssim(img1, img2, crop_border, input_order='HWC', test_y_channel=False):
    """Calculate SSIM (structural similarity).

    Ref:
    Image quality assessment: From error visibility to structural similarity

    The results are the same as that of the official released MATLAB code in
    https://ece.uwaterloo.ca/~z70wang/research/ssim/.

    For three-channel images, SSIM is calculated for each channel and then
    averaged.

    Args:
        img1 (ndarray): Images with range [0, 255].
        img2 (ndarray): Images with range [0, 255].
        crop_border (int): Cropped pixels in each edge of an image. These
            pixels are not involved in the SSIM calculation.
        input_order (str): Whether the input order is 'HWC' or 'CHW'.
            Default: 'HWC'.
        test_y_channel (bool): Test on Y channel of YCbCr. Default: False.

    Returns:
        float: ssim result.
    """

    assert img1.shape == img2.shape, (f'Image shapes are differnet: {img1.shape}, {img2.shape}.')
    if input_order not in ['HWC', 'CHW']:
        raise ValueError(f'Wrong input_order {input_order}. Supported input_orders are ' '"HWC" and "CHW"')
    img1 = reorder_image(img1, input_order=input_order)
    img2 = reorder_image(img2, input_order=input_order)
    img1 = img1.astype(np.float64)
    img2 = img2.astype(np.float64)

    if crop_border != 0:
        img1 = img1[crop_border:-crop_border, crop_border:-crop_border, ...]
        img2 = img2[crop_border:-crop_border, crop_border:-crop_border, ...]

    if test_y_channel:
        img1 = to_y_channel(img1)
        img2 = to_y_channel(img2)

    ssims = []
    for i in range(img1.shape[2]):
        ssims.append(_ssim(img1[..., i], img2[..., i]))
    return np.array(ssims).mean()


def _blocking_effect_factor(im):
    block_size = 8

    block_horizontal_positions = torch.arange(7, im.shape[3] - 1, 8)
    block_vertical_positions = torch.arange(7, im.shape[2] - 1, 8)

    horizontal_block_difference = (
                (im[:, :, :, block_horizontal_positions] - im[:, :, :, block_horizontal_positions + 1]) ** 2).sum(
        3).sum(2).sum(1)
    vertical_block_difference = (
                (im[:, :, block_vertical_positions, :] - im[:, :, block_vertical_positions + 1, :]) ** 2).sum(3).sum(
        2).sum(1)

    nonblock_horizontal_positions = np.setdiff1d(torch.arange(0, im.shape[3] - 1), block_horizontal_positions)
    nonblock_vertical_positions = np.setdiff1d(torch.arange(0, im.shape[2] - 1), block_vertical_positions)

    horizontal_nonblock_difference = (
                (im[:, :, :, nonblock_horizontal_positions] - im[:, :, :, nonblock_horizontal_positions + 1]) ** 2).sum(
        3).sum(2).sum(1)
    vertical_nonblock_difference = (
                (im[:, :, nonblock_vertical_positions, :] - im[:, :, nonblock_vertical_positions + 1, :]) ** 2).sum(
        3).sum(2).sum(1)

    n_boundary_horiz = im.shape[2] * (im.shape[3] // block_size - 1)
    n_boundary_vert = im.shape[3] * (im.shape[2] // block_size - 1)
    boundary_difference = (horizontal_block_difference + vertical_block_difference) / (
                n_boundary_horiz + n_boundary_vert)

    n_nonboundary_horiz = im.shape[2] * (im.shape[3] - 1) - n_boundary_horiz
    n_nonboundary_vert = im.shape[3] * (im.shape[2] - 1) - n_boundary_vert
    nonboundary_difference = (horizontal_nonblock_difference + vertical_nonblock_difference) / (
                n_nonboundary_horiz + n_nonboundary_vert)

    scaler = np.log2(block_size) / np.log2(min([im.shape[2], im.shape[3]]))
    bef = scaler * (boundary_difference - nonboundary_difference)

    bef[boundary_difference <= nonboundary_difference] = 0
    return bef


def calculate_psnrb(img1, img2, crop_border, input_order='HWC', test_y_channel=False):
    """Calculate PSNR-B (Peak Signal-to-Noise Ratio).

    Ref: Quality assessment of deblocked images, for JPEG image deblocking evaluation
    # https://gitlab.com/Queuecumber/quantization-guided-ac/-/blob/master/metrics/psnrb.py

    Args:
        img1 (ndarray): Images with range [0, 255].
        img2 (ndarray): Images with range [0, 255].
        crop_border (int): Cropped pixels in each edge of an image. These
            pixels are not involved in the PSNR calculation.
        input_order (str): Whether the input order is 'HWC' or 'CHW'.
            Default: 'HWC'.
        test_y_channel (bool): Test on Y channel of YCbCr. Default: False.

    Returns:
        float: psnr result.
    """

    assert img1.shape == img2.shape, (f'Image shapes are differnet: {img1.shape}, {img2.shape}.')
    if input_order not in ['HWC', 'CHW']:
        raise ValueError(f'Wrong input_order {input_order}. Supported input_orders are ' '"HWC" and "CHW"')
    img1 = reorder_image(img1, input_order=input_order)
    img2 = reorder_image(img2, input_order=input_order)
    img1 = img1.astype(np.float64)
    img2 = img2.astype(np.float64)

    if crop_border != 0:
        img1 = img1[crop_border:-crop_border, crop_border:-crop_border, ...]
        img2 = img2[crop_border:-crop_border, crop_border:-crop_border, ...]

    if test_y_channel:
        img1 = to_y_channel(img1)
        img2 = to_y_channel(img2)

    # follow https://gitlab.com/Queuecumber/quantization-guided-ac/-/blob/master/metrics/psnrb.py
    img1 = torch.from_numpy(img1).permute(2, 0, 1).unsqueeze(0) / 255.
    img2 = torch.from_numpy(img2).permute(2, 0, 1).unsqueeze(0) / 255.

    total = 0
    for c in range(img1.shape[1]):
        mse = torch.nn.functional.mse_loss(img1[:, c:c + 1, :, :], img2[:, c:c + 1, :, :], reduction='none')
        bef = _blocking_effect_factor(img1[:, c:c + 1, :, :])

        mse = mse.view(mse.shape[0], -1).mean(1)
        total += 10 * torch.log10(1 / (mse + bef))

    return float(total) / img1.shape[1]


def reorder_image(img, input_order='HWC'):
    """Reorder images to 'HWC' order.

    If the input_order is (h, w), return (h, w, 1);
    If the input_order is (c, h, w), return (h, w, c);
    If the input_order is (h, w, c), return as it is.

    Args:
        img (ndarray): Input image.
        input_order (str): Whether the input order is 'HWC' or 'CHW'.
            If the input image shape is (h, w), input_order will not have
            effects. Default: 'HWC'.

    Returns:
        ndarray: reordered image.
    """

    if input_order not in ['HWC', 'CHW']:
        raise ValueError(f'Wrong input_order {input_order}. Supported input_orders are ' "'HWC' and 'CHW'")
    if len(img.shape) == 2:
        img = img[..., None]
    if input_order == 'CHW':
        img = img.transpose(1, 2, 0)
    return img


def to_y_channel(img):
    """Change to Y channel of YCbCr.

    Args:
        img (ndarray): Images with range [0, 255].

    Returns:
        (ndarray): Images with range [0, 255] (float type) without round.
    """
    img = img.astype(np.float32) / 255.
    if img.ndim == 3 and img.shape[2] == 3:
        img = bgr2ycbcr(img, y_only=True)
        img = img[..., None]
    return img * 255.


def _convert_input_type_range(img):
    """Convert the type and range of the input image.

    It converts the input image to np.float32 type and range of [0, 1].
    It is mainly used for pre-processing the input image in colorspace
    convertion functions such as rgb2ycbcr and ycbcr2rgb.

    Args:
        img (ndarray): The input image. It accepts:
            1. np.uint8 type with range [0, 255];
            2. np.float32 type with range [0, 1].

    Returns:
        (ndarray): The converted image with type of np.float32 and range of
            [0, 1].
    """
    img_type = img.dtype
    img = img.astype(np.float32)
    if img_type == np.float32:
        pass
    elif img_type == np.uint8:
        img /= 255.
    else:
        raise TypeError('The img type should be np.float32 or np.uint8, ' f'but got {img_type}')
    return img


def _convert_output_type_range(img, dst_type):
    """Convert the type and range of the image according to dst_type.

    It converts the image to desired type and range. If `dst_type` is np.uint8,
    images will be converted to np.uint8 type with range [0, 255]. If
    `dst_type` is np.float32, it converts the image to np.float32 type with
    range [0, 1].
    It is mainly used for post-processing images in colorspace convertion
    functions such as rgb2ycbcr and ycbcr2rgb.

    Args:
        img (ndarray): The image to be converted with np.float32 type and
            range [0, 255].
        dst_type (np.uint8 | np.float32): If dst_type is np.uint8, it
            converts the image to np.uint8 type with range [0, 255]. If
            dst_type is np.float32, it converts the image to np.float32 type
            with range [0, 1].

    Returns:
        (ndarray): The converted image with desired type and range.
    """
    if dst_type not in (np.uint8, np.float32):
        raise TypeError('The dst_type should be np.float32 or np.uint8, ' f'but got {dst_type}')
    if dst_type == np.uint8:
        img = img.round()
    else:
        img /= 255.
    return img.astype(dst_type)


def bgr2ycbcr(img, y_only=False):
    """Convert a BGR image to YCbCr image.

    The bgr version of rgb2ycbcr.
    It implements the ITU-R BT.601 conversion for standard-definition
    television. See more details in
    https://en.wikipedia.org/wiki/YCbCr#ITU-R_BT.601_conversion.

    It differs from a similar function in cv2.cvtColor: `BGR <-> YCrCb`.
    In OpenCV, it implements a JPEG conversion. See more details in
    https://en.wikipedia.org/wiki/YCbCr#JPEG_conversion.

    Args:
        img (ndarray): The input image. It accepts:
            1. np.uint8 type with range [0, 255];
            2. np.float32 type with range [0, 1].
        y_only (bool): Whether to only return Y channel. Default: False.

    Returns:
        ndarray: The converted YCbCr image. The output image has the same type
            and range as input image.
    """
    img_type = img.dtype
    img = _convert_input_type_range(img)
    if y_only:
        out_img = np.dot(img, [24.966, 128.553, 65.481]) + 16.0
    else:
        out_img = np.matmul(
            img, [[24.966, 112.0, -18.214], [128.553, -74.203, -93.786], [65.481, -37.797, 112.0]]) + [16, 128, 128]
    out_img = _convert_output_type_range(out_img, img_type)
    return out_img