-
Notifications
You must be signed in to change notification settings - Fork 116
/
image_proc.py
116 lines (93 loc) · 4.04 KB
/
image_proc.py
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
import random
from PIL import Image, ImageEnhance
import numpy as np
import cv2
def refine_foreground(image, mask, r=90):
if mask.size != image.size:
mask = mask.resize(image.size)
image = np.array(image) / 255.0
mask = np.array(mask) / 255.0
estimated_foreground = FB_blur_fusion_foreground_estimator_2(image, mask, r=r)
image_masked = Image.fromarray((estimated_foreground * 255.0).astype(np.uint8))
return image_masked
def FB_blur_fusion_foreground_estimator_2(image, alpha, r=90):
# Thanks to the source: https://github.com/Photoroom/fast-foreground-estimation
alpha = alpha[:, :, None]
F, blur_B = FB_blur_fusion_foreground_estimator(
image, image, image, alpha, r)
return FB_blur_fusion_foreground_estimator(image, F, blur_B, alpha, r=6)[0]
def FB_blur_fusion_foreground_estimator(image, F, B, alpha, r=90):
if isinstance(image, Image.Image):
image = np.array(image) / 255.0
blurred_alpha = cv2.blur(alpha, (r, r))[:, :, None]
blurred_FA = cv2.blur(F * alpha, (r, r))
blurred_F = blurred_FA / (blurred_alpha + 1e-5)
blurred_B1A = cv2.blur(B * (1 - alpha), (r, r))
blurred_B = blurred_B1A / ((1 - blurred_alpha) + 1e-5)
F = blurred_F + alpha * \
(image - alpha * blurred_F - (1 - alpha) * blurred_B)
F = np.clip(F, 0, 1)
return F, blurred_B
def preproc(image, label, preproc_methods=['flip']):
if 'flip' in preproc_methods:
image, label = cv_random_flip(image, label)
if 'crop' in preproc_methods:
image, label = random_crop(image, label)
if 'rotate' in preproc_methods:
image, label = random_rotate(image, label)
if 'enhance' in preproc_methods:
image = color_enhance(image)
if 'pepper' in preproc_methods:
image = random_pepper(image)
return image, label
def cv_random_flip(img, label):
if random.random() > 0.5:
img = img.transpose(Image.FLIP_LEFT_RIGHT)
label = label.transpose(Image.FLIP_LEFT_RIGHT)
return img, label
def random_crop(image, label):
border = 30
image_width = image.size[0]
image_height = image.size[1]
border = int(min(image_width, image_height) * 0.1)
crop_win_width = np.random.randint(image_width - border, image_width)
crop_win_height = np.random.randint(image_height - border, image_height)
random_region = (
(image_width - crop_win_width) >> 1, (image_height - crop_win_height) >> 1, (image_width + crop_win_width) >> 1,
(image_height + crop_win_height) >> 1)
return image.crop(random_region), label.crop(random_region)
def random_rotate(image, label, angle=15):
mode = Image.BICUBIC
if random.random() > 0.8:
random_angle = np.random.randint(-angle, angle)
image = image.rotate(random_angle, mode)
label = label.rotate(random_angle, mode)
return image, label
def color_enhance(image):
bright_intensity = random.randint(5, 15) / 10.0
image = ImageEnhance.Brightness(image).enhance(bright_intensity)
contrast_intensity = random.randint(5, 15) / 10.0
image = ImageEnhance.Contrast(image).enhance(contrast_intensity)
color_intensity = random.randint(0, 20) / 10.0
image = ImageEnhance.Color(image).enhance(color_intensity)
sharp_intensity = random.randint(0, 30) / 10.0
image = ImageEnhance.Sharpness(image).enhance(sharp_intensity)
return image
def random_gaussian(image, mean=0.1, sigma=0.35):
def gaussianNoisy(im, mean=mean, sigma=sigma):
for _i in range(len(im)):
im[_i] += random.gauss(mean, sigma)
return im
img = np.asarray(image)
width, height = img.shape
img = gaussianNoisy(img[:].flatten(), mean, sigma)
img = img.reshape([width, height])
return Image.fromarray(np.uint8(img))
def random_pepper(img, N=0.0015):
img = np.array(img)
noiseNum = int(N * img.shape[0] * img.shape[1])
for i in range(noiseNum):
randX = random.randint(0, img.shape[0] - 1)
randY = random.randint(0, img.shape[1] - 1)
img[randX, randY] = random.randint(0, 1) * 255
return Image.fromarray(img)