CODEWITHSUNDEEP
pythonopencvimage-processingcomputer-visionpanoramas
Ankit Kumar
Ankit Kumar

Reputation: 1281

Trim image during Stitching

I am stitching multiple images into one. In an intermediate step, I get an image like:

enter image description here

It isn't necessary at all that the image starts from left and has black region in the right. I want to obtain a rectangular image from this one that doesn't contain the black region. That is, something like:

enter image description here

Can someone please suggest me a way to do that?

Upvotes: 0

Views: 929

Answers (1)

fmw42
fmw42

Reputation: 53089

Here is one way to crop out the excess black on the right side of the image:

Read the image

Convert to grayscale

Threshold

Apply closing and opening morphology to remove small black and white spots.

Get the surrounding contour

Crop the contour

Save the result


Input:

enter image description here

import cv2
import numpy as np

# read image
img = cv2.imread('road.jpg')

# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

# threshold
_,thresh = cv2.threshold(gray,5,255,cv2.THRESH_BINARY)

# apply close and open morphology to fill tiny black and white holes
kernel = np.ones((5,5), np.uint8)
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
thresh = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)

# get contours (presumably just one around the nonzero pixels) 
# then crop it to bounding rectangle
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for cntr in contours:
    x,y,w,h = cv2.boundingRect(cntr)
    crop = img[y:y+h,x:x+w]
    # show cropped image
    cv2.imshow("CROP", crop)

cv2.waitKey(0)
cv2.destroyAllWindows()

# save cropped image
cv2.imwrite('road_crop.png',crop)


enter image description here

Upvotes: 1

Related Questions