How can I blur a mask and smooth its edges?

Question

I want to change the color of the cheeks of this photo. I got a mask with sharp edges How can I blur a mask and smooth its edges? image mask

Thanks for posting this question! Can you post the code you have so far and explain how you are stuck? — Cam, Apr 15 '22 at 15:11
ok this code https://stackoverflow.com/questions/71874524/how-can-i-change-the-color-of-a-part-of-the-image-without-losing-the-texture-of problem: I want to change the color of the cheeks of this photo. I got a mask with sharp edges How can I blur a mask and smooth its edges? — zeinab.mostafavi, Apr 15 '22 at 15:21
May I suggest that you do some image processing tutorials? For example, if you work through some of these, you'll soon get the hang of things > https://scikit-image.org/docs/stable/auto_examples/ — Matt Hall, Apr 15 '22 at 15:25
See how I blur the mask and stretch it to blend the edges of the lips at https://stackoverflow.com/questions/71860084/how-can-i-change-the-color-of-the-lip-that-got-its-landmarks-without-disturbing/71864126#71864126 — fmw42, Apr 15 '22 at 15:31
Welcome to Stack Overflow. Please read the information guides in the **help center** (https://stackoverflow.com/help), in particular, "How to Ask A Good Question" (https://stackoverflow.com/help/how-to-ask) and "How to create a Minimal, Reproducible Example" (https://stackoverflow.com/help/minimal-reproducible-example). — fmw42, Apr 15 '22 at 15:32
Similar questions on this topic of changing make-up have been asked several times recently. Is this some school project? — fmw42, Apr 15 '22 at 15:33

score 1 · Accepted Answer · answered Apr 15 '22 at 15:44

# import the necessary packages
import argparse
import cv2
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", type=str, default="pca8e.png",
    help="path to input image")
args = vars(ap.parse_args())
# load the image, display it to our screen, and initialize a list of
# kernel sizes (so we can evaluate the relationship between kernel
# size and amount of blurring)
image = cv2.imread(args["image"])
cv2.imshow("Original", image)
kernelSizes = [(41,41)]
# loop over the kernel sizes
for (kX, kY) in kernelSizes:
    # apply a "Gaussian" blur to the image
    blurred = cv2.GaussianBlur(image, (kX, kY), 0)
    cv2.imshow("Gaussian ({}, {})".format(kX, kY), blurred)
    cv2.waitKey(0)

Try this code to blur the mask image. But I don't know how you're going to use it with your image.

You can use cv2.circle( ) method for detection the specified area and make it blur. and you may use np.where() method to select the pixels where you want blurred values and then replace them. — debugger, Apr 15 '22 at 16:16

How can I blur a mask and smooth its edges?

1 Answers1