本文共 6193 字，大约阅读时间需要 20 分钟。

计算机视觉-opencv图像基本操作

1 数据读取-图像

• cv2.IMREAD_COLOR：彩色图像
• cv2.IMREAD_GRAYSCALE：灰度图像

import cv2import matplotlib.pyplot as pltimport numpy as np%matplotlib inline#读取彩色图像img = cv2.imread("cat.jpg")

img

array([[[142, 151, 160],        [146, 155, 164],        [151, 160, 170],        ...,        [156, 172, 185],        [155, 171, 184],        [154, 170, 183]],       [[108, 117, 126],        [112, 123, 131],        [118, 127, 137],        ...,        [155, 171, 184],        [154, 170, 183],        [153, 169, 182]],       [[108, 119, 127],        [110, 123, 131],        [118, 128, 138],        ...,        [156, 169, 183],        [155, 168, 182],        [154, 167, 181]],       ...,       [[162, 186, 198],        [157, 181, 193],        [142, 166, 178],        ...,        [181, 204, 206],        [170, 193, 195],        [149, 172, 174]],       [[140, 164, 176],        [147, 171, 183],        [139, 163, 175],        ...,        [169, 187, 188],        [125, 143, 144],        [106, 124, 125]],       [[154, 178, 190],        [154, 178, 190],        [121, 145, 157],        ...,        [183, 198, 200],        [128, 143, 145],        [127, 142, 144]]], dtype=uint8)

# 图像的显示cv2.imshow("image",img)# 等待时间 毫秒级 0表示任意键终止cv2.waitKey(0)cv2.destroyAllWindows()plt.imshow(img)

# 直接定义一个opencv显示的函数def cv_show(name,img):    cv2.imshow(name,img)    cv2.waitKey(0)    cv2.destroyAllWindows()

# 看一下图片的维度 h w cimg.shape

(414, 500, 3)

# 读取灰度图像img = cv2.imread("cat.jpg",cv2.IMREAD_GRAYSCALE)img

array([[153, 157, 162, ..., 174, 173, 172],       [119, 124, 129, ..., 173, 172, 171],       [120, 124, 130, ..., 172, 171, 170],       ...,       [187, 182, 167, ..., 202, 191, 170],       [165, 172, 164, ..., 185, 141, 122],       [179, 179, 146, ..., 197, 142, 141]], dtype=uint8)

img.shape

(414, 500)

cv_show("image",img)

# 保存图像cv2.imwrite("mycat.png",img)

True

# 看一下读取图像的类型type(img)

numpy.ndarray

# 图像的大小img.size

207000

# 图像的类型img.dtype

dtype('uint8')

2 数据读取-视频

• 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

vc = cv2.VideoCapture("test.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:            breakvc.release()cv2.destroyAllWindows()

3 截取部分图像数据

img = cv2.imread("cat.jpg")cat = img[0:50,0:200]cv_show("cat",cat)plt.imshow(cat)

4 颜色通道提取

b,g,r = cv2.split(img)

b

array([[142, 146, 151, ..., 156, 155, 154],       [108, 112, 118, ..., 155, 154, 153],       [108, 110, 118, ..., 156, 155, 154],       ...,       [162, 157, 142, ..., 181, 170, 149],       [140, 147, 139, ..., 169, 125, 106],       [154, 154, 121, ..., 183, 128, 127]], dtype=uint8)

b.shape

(414, 500)

img = cv2.merge((b,g,r))img.shape

(414, 500, 3)

# 只保留Rcur_img = img.copy()cur_img[:,:,0] = 0cur_img[:,:,1] = 0cv_show("R",cur_img)plt.imshow(cur_img)

# 只保留Gcur_img = img.copy()cur_img[:,:,0] = 0cur_img[:,:,2] = 0cv_show("G",cur_img)plt.imshow(cur_img)

# 只保留Bcur_img = img.copy()cur_img[:,:,1] = 0cur_img[:,:,2] = 0cv_show("B",cur_img)plt.imshow(cur_img)

5 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例如：fedcba|abcdefgh|hgfedcb
• BORDER_REFLECT_101：反射法，也就是以最边缘像素为轴，对称，gfedcb|abcdefgh|gfedcba
• BORDER_WRAP：外包装法cdefgh|abcdefgh|abcdefg
• BORDER_CONSTANT：常量法，常数值填充。

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

6 数值计算

img_cat = cv2.imread("cat.jpg")img_dog = cv2.imread("dog.jpg")

img_cat2 = img_cat + 10img_cat[:5,:,0]

array([[142, 146, 151, ..., 156, 155, 154],       [108, 112, 118, ..., 155, 154, 153],       [108, 110, 118, ..., 156, 155, 154],       [139, 141, 148, ..., 156, 155, 154],       [153, 156, 163, ..., 160, 159, 158]], dtype=uint8)

img_cat2[:5,:,0]

array([[152, 156, 161, ..., 166, 165, 164],       [118, 122, 128, ..., 165, 164, 163],       [118, 120, 128, ..., 166, 165, 164],       [149, 151, 158, ..., 166, 165, 164],       [163, 166, 173, ..., 170, 169, 168]], dtype=uint8)

# 相当于%256(img_cat+img_cat2)[:5,:,0]

array([[ 38,  46,  56, ...,  66,  64,  62],       [226, 234, 246, ...,  64,  62,  60],       [226, 230, 246, ...,  66,  64,  62],       [ 32,  36,  50, ...,  66,  64,  62],       [ 60,  66,  80, ...,  74,  72,  70]], dtype=uint8)

cv2.add(img_cat,img_cat2)[:5,:,0]

array([[255, 255, 255, ..., 255, 255, 255],       [226, 234, 246, ..., 255, 255, 255],       [226, 230, 246, ..., 255, 255, 255],       [255, 255, 255, ..., 255, 255, 255],       [255, 255, 255, ..., 255, 255, 255]], dtype=uint8)

图像融合

# 若直接相加，会报错img_cat + img_dog

---------------------------------------------------------------------------ValueError                                Traceback (most recent call last)
   
     in 
    
           1 # 若直接相加，会报错----> 2 img_cat + img_dogValueError: operands could not be broadcast together with shapes (414,500,3) (429,499,3)
    
   

img_cat.shape

(414, 500, 3)

img_dog.shape

(429, 499, 3)

img_dog = cv2.resize(img_dog,(500,414))

img_dog.shape

(414, 500, 3)

res = cv2.addWeighted(img_cat,0.4,img_dog,0.6,0)

plt.imshow(res)

# 尺寸变换resizeres = cv2.resize(img, (0, 0), fx=4, fy=4)plt.imshow(res)

# 尺寸变换res = cv2.resize(img, (0, 0), fx=1, fy=3)plt.imshow(res)

转载地址：https://codingchaozhang.blog.csdn.net/article/details/99473640 如侵犯您的版权，请留言回复原文章的地址，我们会给您删除此文章，给您带来不便请您谅解！