Opencv

[keyfall]

opencv模块功能

[keyfall]

通道交换

因为BGR有3个颜色通道，排序是B,R,R,而RGB三个通道排序是R,G,B，把通道转换就可以把BGR换成RGB

BGR通道
b=img[,,0]
g=img[,,1]
r=img[,,2]

灰度化

灰度是一种图像亮度的表示方法，将彩色图像转化成为灰度图像的过程称为图像的灰度化处理。 R=G=B的值叫灰度值 灰度值有3种方法 最大值法：取通道中最大的一个为灰度值 平均值：3个通道取平均值 加权平均：由于人眼对绿色的敏感最高，对蓝色敏感最低，因此，按下式对RGB三分量进行加权平均能得到较合理的灰度图像 Y = 0.2126 R + 0.7152 G + 0.0722 B

import cv2
import numpy as np

# Read image
img = cv2.imread("imori.jpg").astype(np.float)
b = img[:, :, 0].copy()
g = img[:, :, 1].copy()
r = img[:, :, 2].copy()

# Gray scale
out = 0.2126 * r + 0.7152 * g + 0.0722 * b
out = out.astype(np.uint8)

# Save result
cv2.imwrite("out.jpg", out)
cv2.imshow("result", out)
cv2.waitKey(0)
cv2.destroyAllWindows()

大津二值化法

作用是对二值化的最佳阈值进行确定 从类内方差和类间方差的比值计算得来

import cv2
import numpy as np

# Read image
img = cv2.imread("imori.jpg").astype(np.float)

H, W, C = img.shape

# Grayscale
out = 0.2126 * img[..., 2] + 0.7152 * img[..., 1] + 0.0722 * img[..., 0]
out = out.astype(np.uint8)

# Determine threshold of Otsu's binarization
max_sigma = 0
max_t = 0

for _t in range(1, 255):
    v0 = out[np.where(out < _t)]
    m0 = np.mean(v0) if len(v0) > 0 else 0.
    w0 = len(v0) / (H * W)
    v1 = out[np.where(out >= _t)]
    m1 = np.mean(v1) if len(v1) > 0 else 0.
    w1 = len(v1) / (H * W)
    sigma = w0 * w1 * ((m0 - m1) ** 2)
    if sigma > max_sigma:
        max_sigma = sigma
        max_t = _t

# Binarization
print("threshold >>", max_t)
th = max_t
out[out < th] = 0
out[out >= th] = 255

# Save result
cv2.imwrite("out.jpg", out)
cv2.imshow("result", out)
cv2.waitKey(0)
cv2.destroyAllWindows()

HSV

减色处理（色彩量化）

把每个通道的256个数值，分级变换为固定值

val = {  32  (  0 <= val <  64)
         96  ( 64 <= val < 128)
        160  (128 <= val < 192)
        224  (192 <= val < 256)

import cv2
import numpy as np

# Read image
img = cv2.imread("imori.jpg")

# Dicrease color
out = img.copy()
#整除64，再乘以64，得到特定的4个值(64以内的余数没有了)，加上初始32
out = out // 64 * 64 + 32

cv2.imwrite("out.jpg", out)
cv2.imshow("result", out)
cv2.waitKey(0)
cv2.destroyAllWindows()

[keyfall]

平均池化

将图片按照固定大小网格分割，网格内的像素值取网格内所有像素的平均值。我们将这种把图片使用均等大小网格分割，并求网格内代表值的操作称为池化

import cv2
import numpy as np

# Read image
img = cv2.imread("imori.jpg")

# Average Pooling
out = img.copy()

H, W, C = img.shape
G = 8
Nh = int(H / G)
Nw = int(W / G)

for y in range(Nh):
    for x in range(Nw):
        for c in range(C):
            out[G*y:G*(y+1), G*x:G*(x+1), c] = np.mean(out[G*y:G*(y+1), G*x:G*(x+1), c]).astype(np.int)

# Save result
cv2.imwrite("out.jpg", out)
cv2.imshow("result", out)
cv2.waitKey(0)
cv2.destroyAllWindows()

最大池化

网格内的值使用网格中最大值替代 平均池化代码中ng.mean改成np.max即可

[keyfall]

滤波：消除噪点 均值滤波：基本原理是用平均值代替原图像中的各个像素值

import cv2
import numpy as np

# mean filter
def mean_filter(img, K_size=3):
    H, W, C = img.shape

    # zero padding
    pad = K_size // 2
    out = np.zeros((H + pad * 2, W + pad * 2, C), dtype=np.float)
    out[pad: pad + H, pad: pad + W] = img.copy().astype(np.float)
    tmp = out.copy()

    # filtering
    for y in range(H):
        for x in range(W):
            for c in range(C):
                out[pad + y, pad + x, c] = np.mean(tmp[y: y + K_size, x: x + K_size, c])

    out = out[pad: pad + H, pad: pad + W].astype(np.uint8)

    return out

# Read image
img = cv2.imread("imori.jpg")

# Mean Filter
out = mean_filter(img, K_size=3)

# Save result
cv2.imwrite("out.jpg", out)
cv2.imshow("result", out)
cv2.waitKey(0)
cv2.destroyAllWindows()

高斯滤波:将中心像素周围的像素按照高斯分布加权平均

import cv2
import numpy as np

# Read image
img = cv2.imread("imori_noise.jpg")
H, W, C = img.shape

# Gaussian Filter
K_size = 3
sigma = 1.3

## Zero padding
pad = K_size // 2
out = np.zeros((H + pad*2, W + pad*2, C), dtype=np.float)
out[pad:pad+H, pad:pad+W] = img.copy().astype(np.float)

## Kernel
K = np.zeros((K_size, K_size), dtype=np.float)
for x in range(-pad, -pad+K_size):

    for y in range(-pad, -pad+K_size):
        K[y+pad, x+pad] = np.exp( -(x**2 + y**2) / (2* (sigma**2)))
K /= (sigma * np.sqrt(2 * np.pi))
K /= K.sum()

tmp = out.copy()

for y in range(H):
    for x in range(W):
        for c in range(C):
            out[pad+y, pad+x, c] = np.sum(K * tmp[y:y+K_size, x:x+K_size, c])

out = out[pad:pad+H, pad:pad+W].astype(np.uint8)

# Save result
cv2.imwrite("out.jpg", out)
cv2.imshow("result", out)
cv2.waitKey(0)
cv2.destroyAllWindows()

中值滤波:基本原理是把数字图像或数字序列中一点的值用该点的一个邻域中各点值的中值代替，让周围的像素值接近的真实值，从而消除孤立的噪声点。

import cv2
import numpy as np

# Read image
img = cv2.imread("imori_noise.jpg")
H, W, C = img.shape

# Median Filter
K_size = 3

## Zero padding
pad = K_size // 2
out = np.zeros((H + pad*2, W + pad*2, C), dtype=np.float)
out[pad:pad+H, pad:pad+W] = img.copy().astype(np.float)

tmp = out.copy()

for y in range(H):
    for x in range(W):
        for c in range(C):
            out[pad+y, pad+x, c] = np.median(tmp[y:y+K_size, x:x+K_size, c])

out = out[pad:pad+H, pad:pad+W].astype(np.uint8)

# Save result
cv2.imwrite("out.jpg", out)
cv2.imshow("result", out)
cv2.waitKey(0)
cv2.destroyAllWindows()

其他滤波器

MAX-MIN滤波器使用网格内像素的最大值和最小值的差值对网格内像素重新赋值。通常用于边缘检测。

import cv2
import numpy as np

# Gray scale

def BGR2GRAY(img):
    b = img[:, :, 0].copy()
    g = img[:, :, 1].copy()
    r = img[:, :, 2].copy()

    # Gray scale
    out = 0.2126 * r + 0.7152 * g + 0.0722 * b
    out = out.astype(np.uint8)

    return out

# max-min filter

def max_min_filter(img, K_size=3):
    H, W = img.shape

    # Zero padding
    pad = K_size // 2
    out = np.zeros((H + pad * 2, W + pad * 2), dtype=np.float)
    out[pad: pad + H, pad: pad + W] = gray.copy().astype(np.float)
    tmp = out.copy()

    # filtering
    for y in range(H):
        for x in range(W):
            out[pad + y, pad + x] = np.max(tmp[y: y + K_size, x: x + K_size]) - \
                np.min(tmp[y: y + K_size, x: x + K_size])

    out = out[pad: pad + H, pad: pad + W].astype(np.uint8)

    return out

# Read image
img = cv2.imread("../imori.jpg").astype(np.float)

# grayscale
gray = BGR2GRAY(img)

# Max-Min filtering
out = max_min_filter(gray, K_size=3)

# Save result
cv2.imwrite("out.jpg", out)
cv2.imshow("result", out)
cv2.waitKey(0)
cv2.destroyAllWindows()

[keyfall]

伽马校正

伽马校正用来对照相机等电子设备传感器的非线性光电转换特性进行校正。如果图像原样显示在显示器等上，画面就会显得很暗。伽马校正通过预先增大 RGB 的值来排除显示器的影响，达到对图像修正的目的。

def gamma_correction(img, c=1, g=2.2):
    out = img.copy()
    out /= 255.
    out = (1/c * out) ** (1/g)

    out *= 255
    out = out.astype(np.uint8)

    return out

[keyfall]

最邻近插值和双线性插值

图像放大时补充的像素取最临近的像素的值。由于方法简单，所以处理速度很快，但是放大图像画质劣化明显。

import cv2
import numpy as np
import matplotlib.pyplot as plt

# Nereset Neighbor interpolation
def nn_interpolate(img, ax=1, ay=1):
    H, W, C = img.shape

    aH = int(ay * H)
    aW = int(ax * W)

    y = np.arange(aH).repeat(aW).reshape(aW, -1)
    x = np.tile(np.arange(aW), (aH, 1))
    y = np.round(y / ay).astype(np.int)
    x = np.round(x / ax).astype(np.int)

    out = img[y,x]

    out = out.astype(np.uint8)

    return out

import cv2
import numpy as np
import matplotlib.pyplot as plt

# Bi-Linear interpolation
def bl_interpolate(img, ax=1., ay=1.):
    H, W, C = img.shape

    aH = int(ay * H)
    aW = int(ax * W)

    # get position of resized image
    y = np.arange(aH).repeat(aW).reshape(aW, -1)
    x = np.tile(np.arange(aW), (aH, 1))

    # get position of original position
    y = (y / ay)
    x = (x / ax)

    ix = np.floor(x).astype(np.int)
    iy = np.floor(y).astype(np.int)

    ix = np.minimum(ix, W-2)
    iy = np.minimum(iy, H-2)

    # get distance 
    dx = x - ix
    dy = y - iy

    dx = np.repeat(np.expand_dims(dx, axis=-1), 3, axis=-1)
    dy = np.repeat(np.expand_dims(dy, axis=-1), 3, axis=-1)

    # interpolation
    out = (1-dx) * (1-dy) * img[iy, ix] + dx * (1 - dy) * img[iy, ix+1] + (1 - dx) * dy * img[iy+1, ix] + dx * dy * img[iy+1, ix+1]

    out = np.clip(out, 0, 255)
    out = out.astype(np.uint8)

    return out

[keyfall]

仿射变换

仿射变换，又称仿射映射，是指在几何中，一个向量空间进行一次线性变换并接上一个平移，变换为另一个向量空间. 如何进行放大缩小？

1. 使用仿射变换，将图片在x方向上放大1.3倍，在y方向上缩小至原来的0.8
2. 在上面的条件下，同时在x方向上向右平移30，在y方向上向上平移−30

[keyfall]

图像处理基础

访问图像像素点和修改像素点