How to remove edge noises from an object in an image

Question

I created a clothes mask to extract the clothes object from a image, but there are some white noises included in the mask, the following is the illustration (the outside black area is the background).

I want to get rid of the "white" edge noise from the mask, and I have tried using the naive method of checking if the pixel value is >= 240, the result improves but still not perfect, as shown below:

I want to completely remove the white noise but not sure how to do that. I am using python opencv and would appreciate if anyone could help me on this.

Thanks!

score 1 · Answer 1 · answered Sep 24 '18 at 19:57

1

I would suggest a simple pipeline for removing your edge noise:

import numpy as np
import cv2

gray = cv2.imread("t1yfp.jpg", cv2.IMREAD_GRAYSCALE)

#  eliminate white blobs
kernel = np.ones((5, 5), np.float32)/25
processedImage = cv2.filter2D(gray, -1, kernel)
gray[processedImage > 100] = 0

#  eliminate pixels with very large value
gray[gray > 230] = 0

#  eliminate last remeaning outlier white pixels
gray = cv2.medianBlur(gray, 5)



#  display result
cv2.imshow("res", gray)
cv2.waitKey(0)

After last step, white pixels inside your image mask is also will get eliminated. You can maybe use an averaging filter for recovering them. Here is the result:

answered Sep 24 '18 at 19:57

unlut

3,525
2
14
23

Although it does in fact remove the white outline, it also removes all of the detail from the shirt. – Alistair Carscadden Sep 25 '18 at 03:51
Please explain what you mean by removing all detail. – unlut Sep 25 '18 at 15:13
I mean, the original has detailed sparkes over the front of the shirt. In your output the image is blurred. – Alistair Carscadden Sep 25 '18 at 16:06
Thanks unlut, but the details is needed – cz1980 Sep 26 '18 at 01:30

score 1 · Accepted Answer · answered Sep 25 '18 at 04:18

By dilating the threshold image I was able to take a slightly larger bite out of the image and remove all of the white, but a 1px edge was removed from some innocent areas.

Here is the result:

enter image description here

And here is the code, based on this answer:

import cv2
import numpy as np

# Create binary threshold
img = cv2.imread('shirt.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
_, gray = cv2.threshold(gray, 220, 255, cv2.THRESH_BINARY)

# Dilate the image to join small pieces to the larger white sections
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
gray = cv2.dilate(gray, kernel)

# Create the mask by filling in all the contours of the dilated edges
mask = np.zeros(gray.shape, np.uint8)
_, contours, _ = cv2.findContours(gray, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
for cnt in contours:
    if 10 < cv2.contourArea(cnt) < 5000:
        #  cv2.drawContours(img, [cnt], 0, (0, 255, 0), 2)
        cv2.drawContours(mask, [cnt], 0, 255, -1)

# Erode the edges back to their orig. size
# Leaving this out creates a more greedy bite of the edges, removing the single strands
#  mask = cv2.erode(mask, kernel)

cv2.imwrite('im.png', img)
cv2.imwrite('ma.png', mask)

mask = cv2.cvtColor(255 - mask, cv2.COLOR_GRAY2BGR)
img = img & mask
cv2.imwrite('fi.png', img)

This answer has the benefit of the contours part allowing you to keep white areas of smaller sizes if you mess around with the magic number 10 (I'm assuming this may not be the only image you want to run this code over.) If that is not necessary, then the code could be a lot simpler, by just 1) taking the original threshold, 2) dilating it 3) masking it out on the original image.

Thanks, yes I need to process images with different colours. I tried your code and it works well for dark colour images, but for light colour images the magic "10" parameter tends to generate holes in the clothes. I also tried tuning that parameter, however it is hard to get a "perfect" parameter for both dark and light images. — cz1980, Sep 26 '18 at 03:04

How to remove edge noises from an object in an image

2 Answers2