Affine transformation – OpenCV 3.4 with python 3 Tutorial 14
import cv2
import numpy as np
img = cv2.imread("grid.jpg")
rows, cols, ch = img.shape
cv2.circle(img, (83, 90), 5, (0, 0, 255), -1)
cv2.circle(img, (447, 90), 5, (0, 0, 255), -1)
cv2.circle(img, (83, 472), 5, (0, 0, 255), -1)
pts1 = np.float32([[83, 90], [447, 90], [83, 472]])
pts2 = np.float32([[0, 0], [447, 90], [150, 472]])
matrix = cv2.getAffineTransform(pts1, pts2)
result = cv2.warpAffine(img, matrix, (cols, rows))
cv2.imshow("Image", img)
cv2.imshow("Affine transformation", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Files:
2 Comments
Leave a Reply Cancel reply
This site uses Akismet to reduce spam. Learn how your comment data is processed.
Opencv Beginner Tutorial
- 1) Loading images
- 2) Loading Video and Webcam
- 3) Drawing and writing on images
- 4) Basic operations on images
- 5) Add images and Threshold
- 6) Blending images
- 7) Bitwise Operators
- 8) Trackbars
- 9) Object detection using HSV Color space
- 10) Basic Thresholding
- 11) Histograms
- 12) Basic geometric transformations
- 13) Perspective transformation
- 14) Affine transformation
- 15) Adaptive thresholding5
- 16) Smoothing images
- 17) Morphological transformation
- 18) Edge detection
- 19) Find and Draw Contours
- 20) Template matching
- 21) Lines detection with Hough Transform
- 22) Corners detection
- 23) Image Pyramids
- 24) Image Pyramids (Blending and reconstruction)
- 25) Feature detection (SIFT, SURF, ORB)
- 26) Feature Matching (Brute-Force)
- 27) Mouse Events
- 28) Histogram and Back Projection
- 29) Object tracking with Mean-shift
- 30) Object tracking with Camshift
- 31) Optical Flow with Lucas-Kanade method
- 32) Background Subtraction
- 33) k-Nearest Neighbour classification
- 34) Object tracking using Homography
- 35) Fourier Transform
- 36) Knn handwritten digits recognition
- 37) Face detection using Haar Cascades
I got a information about warpAffine method. But I want to know one more about warpAffine .
import cv2
import numpy as np
pic = cv2.imread(‘image.jpeg’)
print(pic.shape)
cols = pic.shape[1]
rows = pic.shape[0]
M = np.float32([[1,0,25],[0,1,10]]) # This line is passed to warpAffine method. But in your video, you have explained another way. can you tell me what is the difference between this line and your method in your code?
shifted = cv2.warpAffine(pic, M, (cols,rows))
cv2.imshow(‘shifted’,shifted)
cv2.waitKey(0)
cv2.destroyAllWindows()
What if i want to translate back from the result to the original image ?