I tried to digitize the stamp stamped on paper using OpenCV

Motive There is a place to stamp your seal on an Excel sheet or word. If it is a little important document, I sometimes want to use the same seal certificate registered in the city hall, but before, I printed the paper at a convenience store once, stamped it, scanned it again and submitted it as pdf. was doing.

I was doing a lot of analog processing, but I thought that if I could image the seal and paste it on the sheet, I wouldn't have to go to a convenience store.

At first I took a picture of the seal and tried to make the background color transparent using PowerPoint or a free image editing tool, but I gave up because I could not convert everything depending on the paper quality.

So, after trial and error, I wrote a few lines of image processing with OpenCV and solved the problem, so I will leave it as a memorandum.

Dataset I used the seal stamp sample from Akusea.

Method

Binarization + image inversion
Masking with original image and 1 image
Transparent background image (α value 100%)

Development

import cv2
import sys
import numpy as np

if __name__ == '__main__':

	if len(sys.argv) != 2:
		sys.exit()

	window_name = "sample"
	img_path = sys.argv[1]

	mat = cv2.imread(img_path)
	gray = cv2.cvtColor(mat, cv2.COLOR_BGR2GRAY)
	cv2.imwrite("gray.png ", gray)

	#Binarization
	ret2, mono = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU + cv2.THRESH_BINARY_INV) 
	cv2.imwrite("mono.png ", mono)

	#Masking process
	dst = cv2.bitwise_and(mat,mat,mask=mono)
	cv2.imwrite("dst.png ", dst)

	#channel 3->Change to 4
	alpha = cv2.cvtColor(dst, cv2.COLOR_BGR2BGRA)

	#Only the black background is transparent
	for i,col in enumerate(dst):
		for j,row in enumerate(col):
			color = dst[i][j]
			if (color == np.array([0,0,0])).all():
				alpha[i][j][3] = 0

	cv2.imshow(window_name, alpha)
	cv2.imwrite("out.png ", alpha)
	cv2.waitKey(0)
	cv2.destroyWindow(window_name)

This time, the image data processed halfway is also output.

Result

Processing flow	output
raw data
Black and white
Binarization+Invert
masking
Background color transparent (Processing Exit)

Future Background transparency can be easily created by using cv2.bitwise_and. If it seems that it will take time to use the tool, this one seems to be better.

Reference -Image processing with python + Opencv 5 (image combination and mask) -Alpha blending and masking of images with Python, OpenCV, NumPy -Akusea --Original data set used for seal