计算机视觉快速入门一 —— 图像基本操作(一)
1.数据读取
cv2.IMREAD_COLOR:彩色图像
cv2.IMREAD_GRAYSCALE:灰度图像
- 读取:img=cv2.imread('cat.jpg) # img是一个三维矩阵
- 展示:cv2.imshow(‘imagename’,img)
- 等待显示:cv2.waitKey(0) cv2.destroyAllWindows()
- img.shape # (height,width,w)
- 灰度图:img=cv2.imread(‘cat.jpg’,cv2.IMREAD_GRAYSCALE)
- 保存:cv2.imwrite(‘mycat.png’,img)
- type(img)
- img.size #像素点数
- img.dtype
import cv2 #opencv读取的格式是BGR
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
img=cv2.imread('cat.jpg')
#图像的显示,也可以创建多个窗口
cv2.imshow('image',img)
# 等待时间,毫秒级,0表示任意键终止
cv2.waitKey(0)
cv2.destroyAllWindows()
def cv_show(name,img):
cv2.imshow(name,img)
cv2.waitKey(0)
cv2.destroyAllWindows()
img.shape #(414, 500, 3)
#转灰度图
img=cv2.imread('cat.jpg',cv2.IMREAD_GRAYSCALE)
img #二维矩阵
img.shape #(414,500)
#图像的显示,也可以创建多个窗口
cv2.imshow('image',img)
# 等待时间,毫秒级,0表示任意键终止
cv2.waitKey(10000)
cv2.destroyAllWindows()
#保存
cv2.imwrite('mycat.png',img)
type(img) #numpy.ndarray
img(size) #207000
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’)
- gray =cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
vc = cv2.VideoCapture('test.mp4')
# 检查是否打开正确
if vc.isOpened():
oepn, 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(100) & 0xFF == 27:
break
vc.release()
cv2.destroyAllWindows()
3.图像操作
- 颜色通道提取:b,g,r=cv2.split(img)
- 图像融合:img=cv2.merge((b,g,r))
#截取部分图像数据
img=cv2.imread('cat.jpg')
cat=img[0:50,0:200]
cv_show('cat',cat)
#颜色通道提取
b,g,r=cv2.split(img)
r.shape #(414,500)二维数组
img=cv2.merge((b,g,r))
img.shape #(414,500,3)
# 只保留R
cur_img = img.copy()
cur_img[:,:,0] = 0
cur_img[:,:,1] = 0
cv_show('R',cur_img)
# 只保留G
cur_img = img.copy()
cur_img[:,:,0] = 0
cur_img[:,:,2] = 0
cv_show('G',cur_img)
# 只保留B
cur_img = img.copy()
cur_img[:,:,1] = 0
cur_img[:,:,2] = 0
cv_show('B',cur_img)
4.边界填充
#边界填充
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)
import matplotlib.pyplot as plt
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()
- 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。
5.数值计算
img_cat=cv2.imread('cat.jpg')
img_dog=cv2.imread('dog.jpg')
img_cat2= img_cat +10
img_cat[:5,:,0]
img_cat2[:5,:,0]
#相当于% 256
(img_cat + img_cat2)[:5,:,0]
cv2.add(img_cat,img_cat2)[:5,:,0]
6.图像融合
img_cat + img_dog
img_cat.shape #(414, 500, 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)
res = cv2.resize(img, (0, 0), fx=4, fy=4)
plt.imshow(res)
res = cv2.resize(img, (0, 0), fx=1, fy=3)
plt.imshow(res)