File size: 7,981 Bytes
36d9761 |
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 |
import numpy as np
import torch
def rgb2ycbcr(img, y_only=False):
"""Convert a RGB image to YCbCr image.
This function produces the same results as Matlab's `rgb2ycbcr` function.
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: `RGB <-> 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, [65.481, 128.553, 24.966]) + 16.0
else:
out_img = np.matmul(
img, [[65.481, -37.797, 112.0], [128.553, -74.203, -93.786], [24.966, 112.0, -18.214]]) + [16, 128, 128]
out_img = _convert_output_type_range(out_img, img_type)
return out_img
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
def ycbcr2rgb(img):
"""Convert a YCbCr image to RGB image.
This function produces the same results as Matlab's ycbcr2rgb function.
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: `YCrCb <-> RGB`.
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].
Returns:
ndarray: The converted RGB image. The output image has the same type
and range as input image.
"""
img_type = img.dtype
img = _convert_input_type_range(img) * 255
out_img = np.matmul(img, [[0.00456621, 0.00456621, 0.00456621], [0, -0.00153632, 0.00791071],
[0.00625893, -0.00318811, 0]]) * 255.0 + [-222.921, 135.576, -276.836] # noqa: E126
out_img = _convert_output_type_range(out_img, img_type)
return out_img
def ycbcr2bgr(img):
"""Convert a YCbCr image to BGR image.
The bgr version of ycbcr2rgb.
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: `YCrCb <-> BGR`.
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].
Returns:
ndarray: The converted BGR image. The output image has the same type
and range as input image.
"""
img_type = img.dtype
img = _convert_input_type_range(img) * 255
out_img = np.matmul(img, [[0.00456621, 0.00456621, 0.00456621], [0.00791071, -0.00153632, 0],
[0, -0.00318811, 0.00625893]]) * 255.0 + [-276.836, 135.576, -222.921] # noqa: E126
out_img = _convert_output_type_range(out_img, img_type)
return out_img
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
conversion 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(f'The img type should be np.float32 or np.uint8, 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 conversion
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(f'The dst_type should be np.float32 or np.uint8, but got {dst_type}')
if dst_type == np.uint8:
img = img.round()
else:
img /= 255.
return img.astype(dst_type)
def rgb2ycbcr_pt(img, y_only=False):
"""Convert RGB images to YCbCr images (PyTorch version).
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.
Args:
img (Tensor): Images with shape (n, 3, h, w), the range [0, 1], float, RGB format.
y_only (bool): Whether to only return Y channel. Default: False.
Returns:
(Tensor): converted images with the shape (n, 3/1, h, w), the range [0, 1], float.
"""
if y_only:
weight = torch.tensor([[65.481], [128.553], [24.966]]).to(img)
out_img = torch.matmul(img.permute(0, 2, 3, 1), weight).permute(0, 3, 1, 2) + 16.0
else:
weight = torch.tensor([[65.481, -37.797, 112.0], [128.553, -74.203, -93.786], [24.966, 112.0, -18.214]]).to(img)
bias = torch.tensor([16, 128, 128]).view(1, 3, 1, 1).to(img)
out_img = torch.matmul(img.permute(0, 2, 3, 1), weight).permute(0, 3, 1, 2) + bias
out_img = out_img / 255.
return out_img
|