cv2.warpPerspective does not work correctly. | opencv-python

Question

I put the dots: Top left, Bottom left, Bottom right, Top right. The "Warped" window just shows a white screen. I wanted the Warped window to display a distorted image. In the "four_point_transform" function, the "maxWidth" variable almost always gave 0, I do not know what this is related to.

Windows 11 64-bit, python 3.10.7, opencv-contrib-python 4.55.62

import numpy
import cv2
import numpy as np


def on_click(event, x, y, flags, param):
    global a_, b_, c_, d_, to_set
    if event == cv2.EVENT_LBUTTONDOWN:
        print("click")
        if to_set == 0:
            to_set = 1
            a_ = [x, y]
        elif to_set == 1:
            to_set = 2
            b_ = [x, y]
        elif to_set == 2:
            to_set = 3
            c_ = [x, y]
        elif to_set == 3:
            to_set = 0
            d_ = [x, y]


def order_points(pts):
    # initialzie a list of coordinates that will be ordered
    # such that the first entry in the list is the top-left,
    # the second entry is the top-right, the third is the
    # bottom-right, and the fourth is the bottom-left
    rect = np.zeros((4, 2), dtype="float32")

    # the top-left point will have the smallest sum, whereas
    # the bottom-right point will have the largest sum
    s = pts.sum(axis=1)
    rect[0] = pts[np.argmin(s)]
    rect[2] = pts[np.argmax(s)]

    # now, compute the difference between the points, the
    # top-right point will have the smallest difference,
    # whereas the bottom-left will have the largest difference
    diff = np.diff(pts, axis=1)
    rect[1] = pts[np.argmin(diff)]
    rect[3] = pts[np.argmax(diff)]

    # return the ordered coordinates
    return rect


def four_point_transform(image, pts):
    # obtain a consistent order of the points and unpack them
    # individually
    rect = order_points(pts)
    (tl, tr, br, bl) = rect

    # compute the width of the new image, which will be the
    # maximum distance between bottom-right and bottom-left
    # x-coordiates or the top-right and top-left x-coordinates
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA), int(widthB))

    # compute the height of the new image, which will be the
    # maximum distance between the top-right and bottom-right
    # y-coordinates or the top-left and bottom-left y-coordinates
    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA), int(heightB))

    # now that we have the dimensions of the new image, construct
    # the set of destination points to obtain a "birds eye view",
    # (i.e. top-down view) of the image, again specifying points
    # in the top-left, top-right, bottom-right, and bottom-left
    # order
    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype="float32")

    # compute the perspective transform matrix and then apply it
    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

    # return the warped image
    return warped


#cap = cv2.VideoCapture(1, cv2.CAP_DSHOW)
cv2.namedWindow("Corner points")
cv2.setMouseCallback("Corner points", on_click)
to_set = 0
a_ = b_ = c_ = d_ = [0, 0]
while True:
    big_img = cv2.imread("Test.png")
    #_, big_img = cap.read()
    ratio = big_img.shape[0] / 500.0
    org = big_img.copy()
    img = imutils.resize(big_img, height=500)
    cv2.putText(img, f"{to_set}", (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0))
    values = numpy.array([a_,
                          b_,
                          c_,
                          d_], dtype="float32")
    warped = four_point_transform(org, values * ratio)
    cv2.circle(img, a_, 5, (0, 0, 255))
    cv2.circle(img, b_, 5, (0, 0, 255))
    cv2.circle(img, c_, 5, (0, 0, 255))
    cv2.circle(img, d_, 5, (0, 0, 255))
    cv2.imshow("Warped", warped)
    cv2.imshow('Corner points', img)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
cv2.destroyAllWindows()

Answer 1

The code you based your question is taken from an article by Adrian

When trying to debug the code, there seemed to be an error in the order_points function. Turns out that Adrian himself has spotted the error.

He actually wrote an article lining out the error and an improved version of the order_points function.

The working code:

import numpy
import cv2
import numpy as np
from scipy.spatial import distance as dist

def on_click(event, x, y, flags, param):
    global a_, b_, c_, d_, to_set
    if event == cv2.EVENT_LBUTTONDOWN:
        print("click")
        if to_set == 0:
            to_set = 1
            a_ = [x, y]
        elif to_set == 1:
            to_set = 2
            b_ = [x, y]
        elif to_set == 2:
            to_set = 3
            c_ = [x, y]
        elif to_set == 3:
            to_set = 0
            d_ = [x, y]



def order_points(pts):
    # sort the points based on their x-coordinates
    xSorted = pts[np.argsort(pts[:, 0]), :]
    # grab the left-most and right-most points from the sorted
    # x-roodinate points
    leftMost = xSorted[:2, :]
    rightMost = xSorted[2:, :]
    # now, sort the left-most coordinates according to their
    # y-coordinates so we can grab the top-left and bottom-left
    # points, respectively
    leftMost = leftMost[np.argsort(leftMost[:, 1]), :]
    (tl, bl) = leftMost
    # now that we have the top-left coordinate, use it as an
    # anchor to calculate the Euclidean distance between the
    # top-left and right-most points; by the Pythagorean
    # theorem, the point with the largest distance will be
    # our bottom-right point
    D = dist.cdist(tl[np.newaxis], rightMost, "euclidean")[0]
    (br, tr) = rightMost[np.argsort(D)[::-1], :]
    # return the coordinates in top-left, top-right,
    # bottom-right, and bottom-left order
    return np.array([tl, tr, br, bl], dtype="float32")


def four_point_transform(image, pts):
    # obtain a consistent order of the points and unpack them
    # individually
    rect = order_points(pts)
    (tl, tr, br, bl) = rect

    # compute the width of the new image, which will be the
    # maximum distance between bottom-right and bottom-left
    # x-coordiates or the top-right and top-left x-coordinates
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA), int(widthB))

    # compute the height of the new image, which will be the
    # maximum distance between the top-right and bottom-right
    # y-coordinates or the top-left and bottom-left y-coordinates
    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA), int(heightB))

    # now that we have the dimensions of the new image, construct
    # the set of destination points to obtain a "birds eye view",
    # (i.e. top-down view) of the image, again specifying points
    # in the top-left, top-right, bottom-right, and bottom-left
    # order
    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype="float32")

    # compute the perspective transform matrix and then apply it
    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

    # return the warped image
    return warped


#cap = cv2.VideoCapture(1, cv2.CAP_DSHOW)
cv2.namedWindow("Corner points")
cv2.setMouseCallback("Corner points", on_click)
to_set = 0
a_ = b_ = c_ = d_ = [0, 0]
while True:
    img = cv2.imread("test1.png")
    #_, big_img = cap.read()
    ratio = img.shape[0] / 500.0
    org = img.copy()
    #img = cv2.resize(big_img, fx=ratio, fy=ratio)
    cv2.putText(img, f"{to_set}", (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0))
    values = numpy.array([a_,
                          b_,
                          c_,
                          d_], dtype="float32")
    
    # values = numpy.array(([[160. ,251.],
    #                         [560., 217.],
    #                         [241. ,304.],
    #                         [615., 257.]]))
    print(values)
    print('\n')
    warped = four_point_transform(org, values)
    cv2.circle(img, a_, 5, (0, 0, 255))
    cv2.circle(img, b_, 5, (0, 0, 255))
    cv2.circle(img, c_, 5, (0, 0, 255))
    cv2.circle(img, d_, 5, (0, 0, 255))
    cv2.imshow("Warped", warped)
    cv2.imshow('Corner points', img)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
cv2.destroyAllWindows()