Create a mask from outer contour to remove image background

Question

I have image of a single object (specimen) which is uncontrollable background color. The problem has been solved by suggestions from this post . If image was taken from perpendicular angle, that code work nicely.

However, I have another problem. Some images were taken from uncontrollable angle. The existing code in the post i mentioned above returned unexpected result. For example, given the original image

The result is .

My idea to modify that code is to make a mask from the outer contour then apply bitwise between original and mask. But i have no idea how to make a mask from the outer contour. May i have your suggestions?

score 2 · Accepted Answer · answered Feb 20 '20 at 17:52

You may use the following solution (although it's not separating the specimen so nicely):

Use cv2.floodFill do replace the colored background with black background.
Use "close" morphological operation for removing some unwanted artifacts that got left after the floodFill.
Threshold the result, and find the largest contour.
Smooth the contour using the code in following post
Build a mask from the "smoothened" contour, and apply the mask.

Here is the code:

import numpy as np
import cv2
from scipy.interpolate import splprep, splev

orig_im = cv2.imread("specimen1.jpg")

im = orig_im.copy()

h, w = im.shape[0], im.shape[1]

# Seed points for floodFill (use two points at each corner for improving robustness)
seedPoints = ((0, 0), (10, 10), (w-1, 0), (w-1, 10), (0, h-1), (10, h-1), (w-1, h-1), (w-10, h-10))

# Fill background with black color
for seed in seedPoints:
    cv2.floodFill(im, None, seedPoint=seed, newVal=(0, 0, 0), loDiff=(5, 5, 5), upDiff=(5, 5, 5))

# Use "close" morphological operation
im = cv2.morphologyEx(im, cv2.MORPH_OPEN, cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (10,10)));

#Convert to Grayscale, and then to binary image.
gray = cv2.cvtColor(im, cv2.COLOR_RGB2GRAY)
ret, thresh_gray = cv2.threshold(gray, 5, 255, cv2.THRESH_BINARY)

#Find contours
_, contours, _ = cv2.findContours(thresh_gray, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
c = max(contours, key=cv2.contourArea) # Get the largest contour

# Smooth contour
# https://agniva.me/scipy/2016/10/25/contour-smoothing.html
x,y = c.T
x = x.tolist()[0]
y = y.tolist()[0]
tck, u = splprep([x,y], u=None, s=1.0, per=1)
u_new = np.linspace(u.min(), u.max(), 20)
x_new, y_new = splev(u_new, tck, der=0)
res_array = [[[int(i[0]), int(i[1])]] for i in zip(x_new,y_new)]
smoothened = np.asarray(res_array, dtype=np.int32)

# For testing
test_im = orig_im.copy()
cv2.drawContours(test_im, [smoothened], 0, (0, 255, 0), 1)

# Build a mask
mask = np.zeros_like(thresh_gray)
cv2.drawContours(mask, [smoothened], -1, 255, -1)

# Apply mask
res = np.zeros_like(orig_im)
res[(mask > 0)] = orig_im[(mask > 0)]

# Show images for testing
cv2.imshow('test_im', test_im)
cv2.imshow('res', res)
cv2.imshow('mask', mask)
cv2.waitKey(0)
cv2.destroyAllWindows()

Remark:
I don't think the solution is very robust.
You may need to use iterative approaches (like gradually increasing loDiff and hiDiff parameters for matching the best parameters for a given image).

Results:

First specimen:

test_im:

mask:

res:

Second specimen:

test_im:

mask:

res:

Third specimen:

res:

Create a mask from outer contour to remove image background

1 Answers1

Linked