Created
February 27, 2020 10:44
-
-
Save devarshi16/f70acd7ccad8fd8f51135ffa846b8b00 to your computer and use it in GitHub Desktop.
Vectorly interview assignment, first round
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# This is the problem for First technical round for the role of Computer Vision Engineer at Vectorly | |
# More details at https://www.linkedin.com/jobs/view/1629909785/ | |
# | |
# Write a function which will segment and extract the text overlay "Bart & Homer's EXCELLENT Adventure" | |
# Input image is at https://vectorly.io/demo/simpsons_frame0.png | |
# Output : Image with only the overlay visible and everything else white | |
# | |
# Note that you don't need to extract the text, the output is an image with only | |
# the overlay visible and everything else (background) white | |
# | |
# You can use the snipped below (in python) to get started if you like | |
# Python is not required but is preferred. You are free to use any libraries or any language | |
##################### | |
import cv2 | |
import numpy as np | |
def getTextOverlay(input_image): | |
output = np.zeros(input_image.shape, dtype=np.uint8) | |
# Write your code here for output | |
img_gray = cv2.cvtColor(inp_img, cv2.COLOR_BGR2GRAY) | |
_,img_thresh = cv2.threshold(img_gray,5,255,cv2.THRESH_BINARY) | |
denoise1 = cv2.medianBlur(img_thresh,7) | |
output = cv2.GaussianBlur(denoise1,(5,5),0) | |
return output | |
if __name__ == '__main__': | |
image = cv2.imread('simpsons_frame0.png') | |
output = getTextOverlay(image) | |
cv2.imwrite('simpons_text.png', output) | |
##################### |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment