透视变换Python OpenCV

在透视转换中，我们可以更改给定图像或视频的透视，以便更好地了解所需信息。在透视变换中，我们需要通过改变透视来提供图像上要从中收集信息的点。我们还需要提供要在其中显示图像的点。然后，我们从给定的两组点中得到透视变换，并将其与原始图像包裹起来。

我们使用cv2.getPerspectiveTransform然后cv2.warpPerspective 。

cv2.getPerspectiveTransform method 

Syntax: cv2.getPerspectiveTransform(src, dst) 

Parameters: 

• src: Coordinates of quadrangle vertices in the source image.
• dst: Coordinates of the corresponding quadrangle vertices in the destination image.

cv2.wrapPerspective method 

Syntax: cv2.warpPerspective(src, dst, dsize)

Parameters: 

• src: Source Image
• dst: output image that has the size dsize and the same type as src.
• dsize: size of output image

下面是解释透视变换的Python代码：

Python3

# import necessary libraries
 
import cv2
import numpy as np
 
# Turn on Laptop's webcam
cap = cv2.VideoCapture(0)
 
while True:
     
    ret, frame = cap.read()
 
    # Locate points of the documents
    # or object which you want to transform
    pts1 = np.float32([[0, 260], [640, 260],
                       [0, 400], [640, 400]])
    pts2 = np.float32([[0, 0], [400, 0],
                       [0, 640], [400, 640]])
     
    # Apply Perspective Transform Algorithm
    matrix = cv2.getPerspectiveTransform(pts1, pts2)
    result = cv2.warpPerspective(frame, matrix, (500, 600))
     
    # Wrap the transformed image
    cv2.imshow('frame', frame) # Initial Capture
    cv2.imshow('frame1', result) # Transformed Capture
 
    if cv2.waitKey(24) == 27:
        break
 
cap.release()
cv2.destroyAllWindows()

输出：