图像内插
内插通常在图像放大、缩小、旋转和几何校正等任务中使用。内插并用它来调整图像的大小(缩小和放大),缩小和放大基本上采用图像重取样方法
最近邻内插,这种方法将原图像中最近邻的灰度赋给了每个新位置,这种方法简单,但会产生我们不想要的人为失真,如严重的直边失真。更合适的方法是双线性内插,它使用4个最近邻的灰度来计算给定位置的灰度。令
(
x
,
y
)
(x, y)
(x,y)表示待赋灰度值的位置(可将它相像为前面描述的网格点)的坐标,令
v
(
x
,
y
)
v(x, y)
v(x,y)表示灰度值。对于双线性内插方法,所赋的值由如下公式得到:
v
(
x
,
y
)
=
a
x
+
b
y
+
c
x
y
+
d
(2.17)
v(x, y) = ax + by + cxy + d \tag{2.17}
v(x,y)=ax+by+cxy+d(2.17)
4 个系数可由点(x, y)的4个最近邻点写出的4个未知方程求出。双线性内插的结果要比最近邻内插的结果好得多,但计算量会随之增大。
def nearest_neighbor_interpolation(img, new_h, new_w):
"""
get nearest_neighbor_interpolation for image, can up or down scale image into any ratio
param: img: input image, grady image, 1 channel, shape like [512, 512]
param: new_h: new image height
param: new_w: new image width
return a nearest_neighbor_interpolation up or down scale image
"""
new_img = np.zeros([new_h, new_w])
src_height, src_width = img.shape[:2]
r = new_h / src_height
l = new_w / src_width
for i in range(new_h):
for j in range(new_w):
x0 = int(i / r)
y0 = int(j / l)
new_img[i, j] = img[x0, y0]
return new_img
# 最近邻插值法处理一通道的图像
img = cv2.imread('DIP_Figures/DIP3E_Original_Images_CH06/Fig0638(a)(lenna_RGB).tif', 0)
img_up = nearest_neighbor_interpolation(img, 1000, 1000)
plt.figure(figsize=(16, 8))
plt.subplot(121), plt.imshow(img, 'gray')
plt.subplot(122), plt.imshow(img_up, 'gray')
plt.tight_layout()
plt.show()
# 最近邻插值法处理RGB 3通过的图像
img = cv2.imread('DIP_Figures/DIP3E_Original_Images_CH06/Fig0638(a)(lenna_RGB).tif', -1)
img = img[..., ::-1]
img_up_1 = nearest_neighbor_interpolation(img[..., 0], 800, 800)
img_up_2 = nearest_neighbor_interpolation(img[..., 1], 800, 800)
img_up_3 = nearest_neighbor_interpolation(img[..., 2], 800, 800)
img_up = np.uint8(np.dstack((img_up_1, img_up_2, img_up_3)))
plt.figure(figsize=(16, 8))
plt.subplot(121), plt.imshow(img, 'gray')
plt.subplot(122), plt.imshow(img_up, 'gray')
plt.tight_layout()
plt.show()
双线性插值
又称为双线性内挺。在数学上,双线性插值是有两个变量的插值函数的线性插值扩展,其核心思想是在两个方向分别进行一次线性插值。
假设我们想得到未知函数 f 在 点 P = ( x , y ) f在点 P=(x,y) f在点P=(x,y)的值,假设我们已知函数 f 在 Q 11 = ( x 1 , y 1 ) , Q 12 = ( x 1 , y 2 ) , Q 21 = ( x 2 , y 1 ) , Q 22 = ( x 2 , y 2 ) f在Q_{11} = (x_1, y_1),Q_{12}=(x_1, y_2), Q_{21} = (x_2, y_1),Q_{22} = (x_2, y_2) f在Q11=(x1,y1),Q12=(x1,y2),Q21=(x2,y1),Q22=(x2,y2)四个点的值。首先在x方向进行线性插值,得到:
f
(
R
1
)
≈
x
2
−
x
x
2
−
x
1
f
(
Q
11
)
+
x
−
x
1
x
2
−
x
1
f
(
Q
21
)
,
w
h
e
r
e
R
1
=
(
x
,
y
1
)
f(R_1) \approx \frac{x_2 - x}{x_2 - x_1} f(Q_{11}) + \frac{x-x_1}{x_2 - x_1} f(Q_{21}), where R_1 = (x, y_1)
f(R1)≈x2−x1x2−xf(Q11)+x2−x1x−x1f(Q21),whereR1=(x,y1)
f
(
R
2
)
≈
x
2
−
x
x
2
−
x
1
f
(
Q
12
)
+
x
−
x
1
x
2
−
x
1
f
(
Q
22
)
,
w
h
e
r
e
R
2
=
(
x
,
y
2
)
f(R_2) \approx \frac{x_2 - x}{x_2 - x_1} f(Q_{12}) + \frac{x-x_1}{x_2 - x_1} f(Q_{22}), where R_2 = (x, y_2)
f(R2)≈x2−x1x2−xf(Q12)+x2−x1x−x1f(Q22),whereR2=(x,y2)
然后在y方向进行线性插值,得到
f
(
P
)
≈
y
2
−
y
y
2
−
y
1
f
(
R
1
)
+
y
−
y
1
y
2
−
y
1
f
(
R
2
)
f(P) \approx \frac{y_2 - y}{y_2 - y_1} f(R_{1}) + \frac{y-y_1}{y_2 - y_1} f(R_{2})
f(P)≈y2−y1y2−yf(R1)+y2−y1y−y1f(R2)
def bilinear_interpolation(img, new_h, new_w):
"""
get nearest_neighbor_interpolation for image, can up or down scale image into any ratio
param: img: input image, grady image, 1 channel, shape like [512, 512]
param: new_h: new image height
param: new_w: new image width
return a nearest_neighbor_interpolation up or down scale image
"""
src_height, src_width = img.shape[:2]
if new_h == src_height and new_w == src_width:
return img.copy()
new_img = np.zeros([new_h, new_w])
for i in range(new_h):
for j in range(new_w):
# 首先要找到在原图中对应点的(x, y)
x = (i+0.5) * src_height / new_h - 0.5
y = (j+0.5) * src_width / new_w - 0.5
# find the coordinates of the points which will be used to compute the interpolation
src_x0 = int(np.floor(x))
src_x1 = min(src_x0 + 1 , src_height - 1)
src_y0 = int(np.floor(y))
src_y1 = min(src_y0 + 1, src_width - 1)
# calculate the interpolation
temp0 = (src_x1 - x) * img[src_x0, src_y0] + (x - src_x0) * img[src_x1, src_y0]
temp1 = (src_x1 - x) * img[src_x0, src_y1] + (x - src_x0) * img[src_x1, src_y1]
new_img[i, j] = int((src_y1 - y) * temp0 + (y - src_y0) * temp1)
return new_img
# 最近邻插值法处理一通道的图像
img = cv2.imread('DIP_Figures/DIP3E_Original_Images_CH06/Fig0638(a)(lenna_RGB).tif', 0)
img_up = bilinear_interpolation(img, 800, 800)
plt.figure(figsize=(16, 8))
plt.subplot(121), plt.imshow(img, 'gray')
plt.subplot(122), plt.imshow(img_up, 'gray')
plt.tight_layout()
plt.show()
双三次内插
双三次插值的目的就是通过找到一种关系,或者说系数,可以把这16个像素对于P处像素值的影响因子找出来,从而根据这个影响因子来获得目标图像对应点的像素值,达到图像缩放的目的。
Bicubic基函数形式如下:
W
(
x
)
=
{
(
a
+
2
)
∣
x
∣
3
−
(
a
+
3
)
∣
x
∣
2
+
1
,
∣
x
∣
≤
1
a
∣
x
∣
3
−
5
a
∣
x
∣
2
+
8
a
∣
x
∣
−
4
a
,
1
<
∣
x
∣
<
2
0
,
otherwise
W(x) =\begin{cases} (a+2) |x|^3 - (a+3)|x|^2 + 1, & |x| \leq 1 \\a|x|^3 -5a|x|^2 + 8a|x| -4a, & 1 < |x| < 2 \\ 0, & \text{otherwise}\end{cases}
W(x)=⎩⎪⎨⎪⎧(a+2)∣x∣3−(a+3)∣x∣2+1,a∣x∣3−5a∣x∣2+8a∣x∣−4a,0,∣x∣≤11<∣x∣<2otherwise
a
=
−
1
a=-1
a=−1
注
a
=
−
0.5
a=-0.5
a=−0.5才能完美的实现内插
插值计算公式:
∑
i
=
0
3
∑
j
=
0
3
a
i
j
x
i
y
i
\sum_{i=0}^3 \sum_{j=0}^3 a_{ij}x^iy^i
i=0∑3j=0∑3aijxiyi
def bicubic(x):
"""
BiCubic primary fuction
"""
x = abs(x)
a = -0.5
if x <= 1:
return (a + 2) * (x**3) - (a + 3) * (x**2) + 1
elif x < 2:
return a * (x**3) - 5 * a * (x**2) + (8 * a * x) - (4 * a)
else:
return 0
def bicubic_interpolation(img, new_h, new_w):
src_height, src_width = img.shape[:2]
new_img = np.zeros([new_h, new_w])
for h in range(new_h):
for w in range(new_w):
src_x = h * (src_height / new_h)
src_y = w * (src_width / new_w)
x = int(np.floor(src_x))
y = int(np.floor(src_y))
u = src_x - x
v = src_y - y
temp = 0
for i in range(-1, 2):
for j in range(-1, 2):
if x + i < 0 or y + j < 0 or x + i >= src_height or y + j >= src_width:
continue
temp += img[x+i, y+j] * bicubic(i - u) * bicubic(j - v)
new_img[h, w] = np.clip(temp, 0, 255)
return new_img
# 最近邻插值法处理一通道的图像
img = cv2.imread('DIP_Figures/DIP3E_Original_Images_CH06/Fig0638(a)(lenna_RGB).tif', 0)
img_up = bicubic_interpolation(img, 800, 800)
# img_up = cv2.resize(img, (800, 800), cv2.INTER_CUBIC)
plt.figure(figsize=(16, 8))
plt.subplot(121), plt.imshow(img, 'gray')
plt.subplot(122), plt.imshow(img_up, 'gray')
plt.tight_layout()
plt.show()
# 先裁剪图像,然后把裁剪的图像缩小,再进行最近邻、双线内插、双三次内插放大,对比效果
img = cv2.imread('DIP_Figures/DIP3E_Original_Images_CH02/Fig0220(a)(chronometer 3692x2812 2pt25 inch 1250 dpi).tif', 0)
img = img[1100:3500, 200:2600]
img = cv2.resize(img, (200, 200), interpolation=cv2.INTER_CUBIC)
new_h, new_w = 2400, 2400
img_nearest = nearest_neighbor_interpolation(img, new_h, new_w)
img_bilinear = bilinear_interpolation(img, new_h, new_w)
img_bicubic = bicubic_interpolation(img, new_h, new_w)
plt.figure(figsize=(18, 6))
plt.subplot(131), plt.imshow(img_nearest, 'gray'), plt.title('Nearest'), #plt.xticks([]), plt.yticks([])
plt.subplot(132), plt.imshow(img_bilinear, 'gray'), plt.title('Bilinear'), #plt.xticks([]), plt.yticks([])
plt.subplot(133), plt.imshow(img_bicubic, 'gray'), plt.title('Bicubic'), #plt.xticks([]), plt.yticks([])
plt.tight_layout()
plt.show()
放大图像
def up_sample_2d(img):
"""
up sample 2d image, if your image is RGB, you could up sample each channel, then use np.dstack to merge a RGB image
param: input img: it's a 2d gray image
return a 2x up sample image
"""
height, width = img.shape[:2]
temp = np.zeros([height*2, width*2])
temp[::2, ::2] = img
temp[1::2, 1::2] = img
temp[0::2, 1::2] = img
temp[1::2, 0::2] = img
return temp
# up sample image using Numpy
img = np.random.random([12, 12])
up = up_sample_2d(img)
down = np.zeros([12, 12])
down = up[::2, ::2]
plt.figure(figsize=(15, 5))
plt.subplot(1,3,1), plt.imshow(img),# plt.xticks([]), plt.yticks([])
plt.subplot(1,3,2), plt.imshow(up),# plt.xticks([]), plt.yticks([])
plt.subplot(1,3,3), plt.imshow(down),# plt.xticks([]), plt.yticks([])
plt.show()
# 等比2倍放大
img_ori = cv2.imread("DIP_Figures/DIP3E_Original_Images_CH06/Fig0638(a)(lenna_RGB).tif")
img_ori = img_ori[:, :, ::-1]
temp = []
for i in range(img_ori.shape[-1]):
temp.append(up_sample_2d(img_ori[:, :, i]))
up1 = np.uint8(np.dstack(temp))
temp = []
for i in range(up1.shape[-1]):
temp.append(up_sample_2d(up1[:, :, i]))
up2 = np.uint8(np.dstack(temp))
plt.figure(figsize=(21, 7))
plt.subplot(1,3,1), plt.imshow(img_ori), plt.title("Original"),# plt.xticks([]), plt.yticks([])
plt.subplot(1,3,2), plt.imshow(up1), plt.title("2X"),# plt.xticks([]), plt.yticks([])
plt.subplot(1,3,3), plt.imshow(up2), plt.title("4X"),# plt.xticks([]), plt.yticks([])
plt.tight_layout()
plt.show()