Opencv learning notes 1

Basic operation of image

Environment configuration address ：

• Anaconda:https://www.anaconda.com/download/

• Python_whl:https://www.lfd.uci.edu/~gohlke/pythonlibs/#opencv

• eclipse: As you like , Choose one that can debug Just fine

data fetch - Images

• cv2.IMREAD_COLOR： Color images
• cv2.IMREAD_GRAYSCALE： Grayscale image

import cv2 #opencv The reading format is BGR
import matplotlib.pyplot as plt
import numpy as np 
%matplotlib inline 

img=cv2.imread('cat.jpg')

img

array([[[142, 151, 160],
        [146, 155, 164],
        [151, 160, 169],
        ...,
        [156, 172, 185],
        [155, 171, 184],
        [154, 170, 183]],

       [[107, 118, 126],
        [112, 123, 131],
        [117, 128, 136],
        ...,
        [155, 171, 184],
        [154, 170, 183],
        [153, 169, 182]],

       [[108, 119, 127],
        [112, 123, 131],
        [118, 129, 137],
        ...,
        [154, 170, 183],
        [153, 169, 182],
        [152, 168, 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],
        ...,
        [167, 187, 188],
        [123, 143, 144],
        [104, 124, 125]],

       [[154, 178, 190],
        [154, 178, 190],
        [121, 145, 157],
        ...,
        [185, 198, 200],
        [130, 143, 145],
        [129, 142, 144]]], dtype=uint8)

# Image display , You can also create multiple windows 
cv2.imshow('image',img) 
#  Waiting time , millisecond ,0 Any key termination 
cv2.waitKey(0) 
cv2.destroyAllWindows()

def cv_show(name,img):
    cv2.imshow(name,img) 
    cv2.waitKey(0) 
    cv2.destroyAllWindows()

img.shape

(414, 500, 3)

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)

# Image display , You can also create multiple windows 
cv2.imshow('image',img) 
#  Waiting time , millisecond ,0 Any key termination 
cv2.waitKey(10000) 
cv2.destroyAllWindows()  # Destroy the image window just displayed 

# preservation 
cv2.imwrite('mycat.png',img)

True

type(img)

numpy.ndarray

img.size

207000

img.dtype

dtype('uint8')

data fetch - video

• cv2.VideoCapture The camera can capture , Use numbers to control different devices , for example 0,1.
• If it's a video file , You can directly specify a good path .

vc = cv2.VideoCapture('test.mp4')

#  Check that it is opened correctly 
if vc.isOpened(): 
    oepn, frame = vc.read() # The first parameter is bool Verify that the return is correct , The second parameter is the image 
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()

Capture part of the image data

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

Color channel extraction

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

r

array([[160, 164, 169, ..., 185, 184, 183],
       [126, 131, 136, ..., 184, 183, 182],
       [127, 131, 137, ..., 183, 182, 181],
       ...,
       [198, 193, 178, ..., 206, 195, 174],
       [176, 183, 175, ..., 188, 144, 125],
       [190, 190, 157, ..., 200, 145, 144]], dtype=uint8)

r.shape

(414, 500)

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

(414, 500, 3)

#  Only keep R
cur_img = img.copy()
cur_img[:,:,0] = 0
cur_img[:,:,1] = 0
cv_show('R',cur_img)
cur_img.shape

(414, 500, 3)

#  Only keep G
cur_img = img.copy()
cur_img[:,:,0] = 0
cur_img[:,:,2] = 0
cv_show('G',cur_img)

#  Only keep B
cur_img = img.copy()
cur_img[:,:,1] = 0
cur_img[:,:,2] = 0
cv_show('B',cur_img)

Border filling

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： Replication , That is to copy the edge pixels .
• BORDER_REFLECT： Reflection , Copy the pixels in the image of interest on both sides, for example ：fedcba|abcdefgh|hgfedcb
• BORDER_REFLECT_101： Reflection , That is, take the most edge pixel as the axis , symmetry ,gfedcb|abcdefgh|gfedcba
• BORDER_WRAP： The outer packing method cdefgh|abcdefgh|abcdefg
• BORDER_CONSTANT： Constant method , Constant value filling .

Numerical calculation

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

img_cat2= img_cat +10 # Every pixel is added 10
img_cat[:5,:,0]

array([[142, 146, 151, ..., 156, 155, 154],
       [107, 112, 117, ..., 155, 154, 153],
       [108, 112, 118, ..., 154, 153, 152],
       [139, 143, 148, ..., 156, 155, 154],
       [153, 158, 163, ..., 160, 159, 158]], dtype=uint8)

img_cat2[:5,:,0]

array([[152, 156, 161, ..., 166, 165, 164],
       [117, 122, 127, ..., 165, 164, 163],
       [118, 122, 128, ..., 164, 163, 162],
       [149, 153, 158, ..., 166, 165, 164],
       [163, 168, 173, ..., 170, 169, 168]], dtype=uint8)

# amount to % 256
(img_cat + img_cat2)[:5,:,0] 

array([[ 38,  46,  56, ...,  66,  64,  62],
       [224, 234, 244, ...,  64,  62,  60],
       [226, 234, 246, ...,  62,  60,  58],
       [ 32,  40,  50, ...,  66,  64,  62],
       [ 60,  70,  80, ...,  74,  72,  70]], dtype=uint8)

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

array([[255, 255, 255, ..., 255, 255, 255],
       [224, 234, 244, ..., 255, 255, 255],
       [226, 234, 246, ..., 255, 255, 255],
       [255, 255, 255, ..., 255, 255, 255],
       [255, 255, 255, ..., 255, 255, 255]], dtype=uint8)

Image fusion

img_cat + img_dog  # Because the length and width are different, you can't directly add 

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

<ipython-input-111-ffa3cdc5d6b8> in <module>()
----> 1 img_cat + img_dog


ValueError: operands could not be broadcast together with shapes (414,500,3) (429,499,3) 

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)

<matplotlib.image.AxesImage at 0x20a6b5f39e8>

res = cv2.resize(img, (0, 0), fx=4, fy=4)
plt.imshow(res)

<matplotlib.image.AxesImage at 0x20a6b58b908>

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

<matplotlib.image.AxesImage at 0x20a6b7bcb00>

Reference resources

OpenCV From introduction to practice The whole course