[FIXED] How to change the background to white using OpenCV

Issue

Image

I want to change the background of the image to white for OCR.

Result

image = cv2.imread('./screenshot_2.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
threshold_value = 150
_, image = cv2.threshold(gray, threshold_value, 255, cv2.THRESH_BINARY_INV)
contours, _ = cv2.findContours(image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
largest_contour = max(contours, key=cv2.contourArea)
height, width = image.shape
image = np.ones((height, width), np.uint8) * 255 
cv2.drawContours(image, [largest_contour], -1, 0, -1)

Expecting

I want the image to change like this.

Solution

You can do that in Python/OpenCV by flood filling with white.

Input:

import cv2
import numpy as np

# read the input as grayscale
img = cv2.imread('tentagruel.png', cv2.IMREAD_GRAYSCALE)
hh, ww = img.shape[:2]

# add black border to ensure black all around
img2 = cv2.copyMakeBorder(img, 5, 5, 5, 5, borderType=cv2.BORDER_CONSTANT, value=(0,0,0))
hh2 = hh+10
ww2 = ww+10 

# create mask image for floodfill
# create zeros mask 2 pixels larger in each dimension
mask = np.zeros([hh2 + 2, ww2 + 2], np.uint8)

# apply floodfill from top-left corner
result = img2.copy()
cv2.floodFill(result, mask, (0,0), 255, 0, 200, flags=8)[1]

# save the result
cv2.imwrite('tentagruel_proc.png', result)

# show result
cv2.imshow('result', result)
cv2.waitKey(0)

Result:

Answered By - fmw42