2021-02-21

OpenCV

1. Basic image read、show、write

import cv2
import numpy as np

img = cv2.imread("lenna.jpg")
cv2.imshow("image",img)
k = cv2.waitKey(0)
if k==27:
	cv2.destroyAllWindows()
elif k==ord('s'):
	cv2.imwrite("lenna_write.jpg",img)
	cv2.destroyAllWindows()

2. Video and Camera

import numpy as np
import cv2

cap = cv2.VideoCapture(0) # from camera
cap2 = cv2.VideoCapture("test.mp4") # from video file

fourcc = cv2.VideoWriter_fourcc(*'XVID')
out = cv2.VideoWriter('output.mp4',fourcc,20.0,(640,480))

while True:
	ret, frame = cap.read()
	out.write(frame)
	gray = cv2.cvtColor(frame,cv2.BGR2GRAY)
	cv2.imshow("camera",gray)
cap.release()
out.release()
cv2.destroyAllWindows()

more details

3. Drawing

import numpy as np
import cv2

img = np.zeros((512,512,3),np.uint8)

img = cv2.line(img,(0,0),(255,255),(255,0,0),5)
# img,start,end,color,line-thickness
img = cv2.rectangle(img,(10,10),(120,180),(0,255,0),3)
# img,left-top,right-bottom,color,line-thickness
img = cv2.circle(img,(250,250),50,(0,0,255),-1)
# -1 means fill this circle
img = cv2.ellipse(img,(256,256),(100,50),0,0,180,255,-1)
# img,center,axis scope,direction,start-angle,end-angle,fill

# Polygon: a group of lines
pts = np.array([[10,5],[20,30],[70,20],[50,10]],np.int32)
pts = pts.reshape((-1,1,2))
img = cv2.polylines(img,[pts],True,(0,255,255))

# Text
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(img,'OpenCV',(10,400),font,4,(255,255,255),2,cv2.LINE_AA)
# img,text,start,font-family,font-scale,color,thickness,lineType

cv2.imshow("Draw Example",img)
cv2.waitKey()
cv2.destroyAllWindows()

4. Mouse Handling

task: draw a circle where mouse clicked

import numpy as np
import cv2

def draw_circle(event,x,y,flags,param):
	if event == cv2.EVENT_LBUTTONDBLCLK:
		cv2.circle(img,(x,y),100,(255,255,0),-1)
img = np.zeros((512,512,3),np.uint8)
cv2.namedWindow('image_window')
cv2.setMouseCallback('image_window',draw_circle)

while True:
	cv2.imshow('image_window',img)
	if cv2.waitKey(20) &0xFF==27:
		break
cv2.destroyAllWindows()

about &0xFF

5. colorbar

import cv2
import numpy as np

def nothing(x):
    pass

# Create a black image, a window
img = np.zeros((300,512,3), np.uint8)
cv2.namedWindow('image')

# create trackbars for color change
cv2.createTrackbar('R','image',0,255,nothing)
cv2.createTrackbar('G','image',0,255,nothing)
cv2.createTrackbar('B','image',0,255,nothing)

# create switch for ON/OFF functionality
switch = '0 : OFF \n1 : ON'
cv2.createTrackbar(switch, 'image',0,1,nothing)

while(1):
    cv2.imshow('image',img)
    k = cv2.waitKey(1) & 0xFF
    if k == 27:
        break

    # get current positions of four trackbars
    r = cv2.getTrackbarPos('R','image')
    g = cv2.getTrackbarPos('G','image')
    b = cv2.getTrackbarPos('B','image')
    s = cv2.getTrackbarPos(switch,'image')

    if s == 0:
        img[:] = 0
    else:
        img[:] = [b,g,r]

cv2.destroyAllWindows()

pixel modify

import numpy as np
import cv2

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

# access
px = img[100,100] # or px = img.item(100,100)
px_blue = img[100,100,0]
px_green = img[100,100,1]
px_red = img[100,100,2]

# modify
img[100,100] = [255,255,0] # or img.itemset((100,100,0),255)

Image Properties

img.shape # (height,width,channels)
img.size # size == shape[0]*shape[1]*shape[2]
img.dtype # uint8

ROI

region of image
region of interest

>>> ball = img[280:340, 330:390]
>>> img[273:333, 100:160] = ball

split channel

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

b,g,r = img[:,:,0],img[:,:,1],img[:,:,2]

Border for Image

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

BLUE = [255,0,0]

img1 = cv2.imread('opencv_logo.png')

replicate = cv2.copyMakeBorder(img1,10,10,10,10,cv2.BORDER_REPLICATE)
reflect = cv2.copyMakeBorder(img1,10,10,10,10,cv2.BORDER_REFLECT)
reflect101 = cv2.copyMakeBorder(img1,10,10,10,10,cv2.BORDER_REFLECT_101)
wrap = cv2.copyMakeBorder(img1,10,10,10,10,cv2.BORDER_WRAP)
constant= cv2.copyMakeBorder(img1,10,10,10,10,cv2.BORDER_CONSTANT,value=BLUE)

plt.subplot(231),plt.imshow(img1,'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()

cv2.add(img1,img2)

cv2.addWeighted(img1,w1,img2,w2,0)

# w1+w2=1
dst = cv2.addWeighted(img1,0.7,img2,0.3,0)

AND,OR,NOT,XOR

# Load two images
img1 = cv2.imread('messi5.jpg')
img2 = cv2.imread('opencv_logo.png')

# I want to put logo on top-left corner, So I create a ROI
rows,cols,channels = img2.shape
roi = img1[0:rows, 0:cols ]

# Now create a mask of logo and create its inverse mask also
img2gray = cv2.cvtColor(img2,cv2.COLOR_BGR2GRAY)
ret, mask = cv2.threshold(img2gray, 10, 255, cv2.THRESH_BINARY)
mask_inv = cv2.bitwise_not(mask)

# Now black-out the area of logo in ROI
img1_bg = cv2.bitwise_and(roi,roi,mask = mask_inv)

# Take only region of logo from logo image.
img2_fg = cv2.bitwise_and(img2,img2,mask = mask)

# Put logo in ROI and modify the main image
dst = cv2.add(img1_bg,img2_fg)
img1[0:rows, 0:cols ] = dst

cv2.imshow('res',img1)
cv2.waitKey(0)
cv2.destroyAllWindows()

Time evaluate & Optimize

e1 = cv2.getTickCount()
# your code execution
e2 = cv2.getTickCount()
time = (e2 - e1)/ cv2.getTickFrequency()

# check if optimized
print(cv2.useOptimized())
# if not,set it True
cv2.setUseOptimized(True)