I am trying to perform image registration for two RGB lung mask images of size 128x128. This had worked fine for other images when I was learning image registration but now somehow it throws such error. I am a newbie learning this, any help is appreciated.
I have attached the code of what I am trying to do below, where I have created a registerImage function by following GeeksForGeeks and passed images which I want to register.
import cv2
import numpy as np
def registerImage(img1,img2):
# Open the image files.
img1_color = img1 # Image to be aligned.
img2_color = img2 # Reference image.
# Convert to grayscale.
img1 = cv2.cvtColor(img1_color, cv2.COLOR_BGR2GRAY)
img2 = cv2.cvtColor(img2_color, cv2.COLOR_BGR2GRAY)
height, width = img2.shape
# Create ORB detector with 5000 features.
## used to creates keypoints on the reference image
orb_detector = cv2.ORB_create(5000)
# Find keypoints and descriptors.
# The first arg is the image, second arg is the mask
# (which is not required in this case).
kp1, d1 = orb_detector.detectAndCompute(img1, None)
kp2, d2 = orb_detector.detectAndCompute(img2, None)
# Match features between the two images.
# We create a Brute Force matcher with
# Hamming distance as measurement mode.
#Brute-Force matcher is simple.
#It takes the descriptor of one feature in first set and is matched with all other features in second set using some distance calculation. And the closest one is returned.
matcher = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck = True)
# Match the two sets of descriptors.
matches = matcher.match(d1, d2)
# Sort matches on the basis of their Hamming distance.
matches.sort(key = lambda x: x.distance)
# Take the top 90 % matches forward.
matches = matches[:int(len(matches)*0.9)]
no_of_matches = len(matches)
# Define empty matrices of shape no_of_matches * 2.
p1 = np.zeros((no_of_matches, 2))
p2 = np.zeros((no_of_matches, 2))
for i in range(len(matches)):
p1[i, :] = kp1[matches[i].queryIdx].pt
p2[i, :] = kp2[matches[i].trainIdx].pt
# Find the homography matrix.
homography, mask = cv2.findHomography(p1, p2, cv2.RANSAC)
# Use this matrix to transform the
# colored image wrt the reference image.
transformed_img = cv2.warpPerspective(img1_color,
homography, (width, height))
# Save the output.
# cv2.imwrite('output.jpg', transformed_img)
img1_show = cv2.resize(img1_color,(320,320))
img2_show = cv2.resize(img2_color,(320,320))
img3_show = cv2.resize(transformed_img,(320,320))
img = np.concatenate((img1_show,img2_show,img3_show), axis=1)
cv2_imshow(img)
ref_path = path + "/mask_0.png"
test_path = path + "/mask_8.png"
from google.colab.patches import cv2_imshow
ref_mask = cv2.imread(ref_path)
cv2_imshow(ref_mask)
test_mask = cv2.imread(test_path)
cv2_imshow(test_mask)
registerImage(ref_mask,test_mask)
############################################################################
Error:
---------------------------------------------------------------------------
error Traceback (most recent call last)
<ipython-input-18-b7a8933e693e> in <module>()
----> 1 registerImage(ref_mask,test_mask)
<ipython-input-2-3a703c66a8e0> in registerImage(img1, img2)
54 # colored image wrt the reference image.
55 transformed_img = cv2.warpPerspective(img1_color,
---> 56 homography, (width, height))
57
58 # Save the output.
error: OpenCV(4.1.2) /io/opencv/modules/imgproc/src/imgwarp.cpp:3167: error: (-215:Assertion failed) (M0.type() == CV_32F || M0.type() == CV_64F) && M0.rows == 3 && M0.cols == 3 in function 'warpPerspective'
Go backwards from where you got the error and trace it back to find what is giving you the error.
You're getting errors at this statement:
transformed_img = cv2.warpPerspective(img1_color,
homography, (width, height))
What I'd suggest is to check the variables themselves that are fed into the function. Here's a crude but simple way to do it.
# Place these statements prior to the error and check their values
print("hemography:",hemography) # In my case this was None, which is why I got an error
print("h:",height,"w:", width) # Check width/height seems correct
cv2_imshow(img1_color) # Check image is loaded properly
Also worth noting if it comes up while others are searching. For similar code I got an error at the matches.sort(..)
line due to the type being Tuple and not a list.
To fix it I changed it to the following:
matches = sorted(matches,key=lambda x:x.distance, reverse=False)
Debugging is a skill you'll pickup over time, as are asking/answering questions here. That error isn't simple to understand if you're new to python, which is how I found this in the first place. The documentation will become easier to understand over time also.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.