OpenCV图像基本操作

图像基本操作

注意opencv中三原色通道为BGR与matplotlib中的RBG顺序不同

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


def cv_show(name, img):
    # 图像显示
    cv2.imshow(name, img)
    # 等待时间 0表示任意键终止 单位毫秒
    cv2.waitKey(0)
    cv2.destroyAllWindows()


img01 = cv2.imread('image01.png')
print(img01)
print(img01.shape)  # 输出图像形状
print(type(img01))  # 输出图像类型
print(img01.size)   # 输出图像尺寸
print(img01.dtype)  # 输出图像数据类型

# 灰度图像
img02 = cv2.imread('image01.png', cv2.IMREAD_GRAYSCALE)
print(img02.shape)
cv_show('image', img02)

# 图像保存
cv2.imwrite('image02.png', img02)

# 截取部分图像数据
img03 = img01[0:50, 0:200]
cv_show('image03.png')

# 颜色通道提取
b,g,r = cv2.split(img01)
img04 = cv2.merge((b,g,r))  # 三原色整合

视频数据读取

cv2.VideoCapture可以捕获摄像头，用数字来控制不同的设备，例如0,1
如果是视频文件，直接指定好路径即可

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

# 数据读取-视频
vc = cv2.VideoCapture("test01.mp4")

# 检查是否打开正确
if vc.isOpened():
    open, frame = vc.read()
else:
    open = False

while open:
    ret, frame = vc.read()
    if frame is None:
        break
    if ret == True:
        gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
        cv2.imshow('result', gray)
        if cv2.waitKey(10) & 0xFF == 27:
            break
vc.release()
cv2.destroyAllWindows()

边界填充

• BORDER_REPLICATE：复制法，也就是复制最边缘像素
• BORDER_REFLECT：反射法，对感兴趣的图像中的像素在两边进行复制
• BORDER_REFLECT_101：反射法，也就是以最边缘像素为轴，对称
• BORDER_WRAP：外包装法
• BORDER_CONSTANT：常量法，常数值填充

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

top_size, bottom_size, left_size, right_size = (50, 50, 50, 50)

img = cv2.imread('image01.png')
replicate = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, borderType=cv2.BORDER_REPLICATE)
reflect = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, cv2.BORDER_REFLECT)
reflect101 = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, cv2.BORDER_REFLECT_101)
wrap = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, cv2.BORDER_WRAP)
constant = cv2.copyMakeBorder(img, top_size, bottom_size, left_size, right_size, cv2.BORDER_CONSTANT, value=0)

plt.subplot(231), plt.imshow(img), plt.title('ORIGINAL')
plt.subplot(232), plt.imshow(replicate, 'gray'), plt.title('REPLICATE')
plt.subplot(233), plt.imshow(reflect, 'gray'), plt.title('REFLECT')
plt.subplot(234), plt.imshow(reflect101, 'gray'), plt.title('REFLECT_101')
plt.subplot(235), plt.imshow(wrap, 'gray'), plt.title('WRAP')
plt.subplot(236), plt.imshow(constant, 'gray'), plt.title('CONSTANT')

plt.show()

注意opencv中三原色通道为BGR与matplotlib中的RBG顺序不同，用matplotlib读取opencv的图片会与原图有出入

数值计算

numpy中像素点值超过256会进行取余运算
而opencv中则是采取最大值255的方法

图像融合

也可以按照倍数重新设置大小res = cv2.resize(res, (0, 0), fx=1, fy=3)

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

img01 = cv2.imread('image01.png')
img02 = cv2.imread('lena.jpg')
img01 = cv2.resize(img01, (263, 263))

# 图像按0.6x+0.4y+0的方式生成新的图像
res = cv2.addWeighted(img01, 0.6, img02, 0.4, 0)
plt.imshow(res)
plt.show()

图像阈值

ret, dst = cv2.threshold(src, thresh, maxval, type)
src： 输入图，只能输入单通道图像，通常来说为灰度图
dst： 输出图
thresh： 阈值
maxval： 当像素值超过了阈值（或者小于阈值，根据type来决定），所赋予的值
type：二值化操作的类型，包含以下5种类型： cv2.THRESH_BINARY； cv2.THRESH_BINARY_INV； cv2.THRESH_TRUNC； cv2.THRESH_TOZERO；cv2.THRESH_TOZERO_INV
cv2.THRESH_BINARY 超过阈值部分取maxval（最大值），否则取0
cv2.THRESH_BINARY_INV THRESH_BINARY的反转
cv2.THRESH_TRUNC 大于阈值部分设为阈值，否则不变
cv2.THRESH_TOZERO 大于阈值部分不改变，否则设为0
cv2.THRESH_TOZERO_INV THRESH_TOZERO的反转

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

img = cv2.imread('image01.png')
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

ret, thresh1 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_BINARY)
ret, thresh2 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_BINARY_INV)
ret, thresh3 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TRUNC)
ret, thresh4 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TOZERO)
ret, thresh5 = cv2.threshold(img_gray, 127, 255, cv2.THRESH_TOZERO_INV)

titles = ['Original Image', 'BINARY', 'BINARY_INV', 'TRUNC', 'TOZERO', 'TOZERO_INV']
images = [img, thresh1, thresh2, thresh3, thresh4, thresh5]

for i in range(6):
    plt.subplot(2, 3, i + 1), plt.imshow(images[i], 'gray')
    plt.title(titles[i])
    plt.xticks([]), plt.yticks([])
plt.show()