Opencv: Remove background and draw bounding box around the ID Card

Question

I have some images from Google, where I want to remove the background from the images and draw the bounding box around the ID cards.

Here is the input image:

Here is my code:

import cv2
import numpy as np
import matplotlib.pyplot as plt

image = cv2.imread('/content/f6644ae09eb9acfc6a71f01115f917f9.jpg')
result = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
        cv2.drawContours(thresh, [c], -1, (255,255,255), 5)
plt.imshow(thresh,'gray')

This code is used to threshold the image. The output is like this:

How can I crop only the ID card and remove the background from the image?

Answer 1

You can crop out the ID in the following way. See inline comments for explanation

import cv2 as cv
import matplotlib.pyplot as plt
import numpy as np

gray = cv.cvtColor(img,cv.COLOR_BGR2GRAY)

## use cv.THRESH_BINARY instead of ..._INV
## this will set the background black instead of white
## and the foreground to white instead of black
thresh = cv.threshold(gray, 0, 255, cv.THRESH_BINARY + cv.THRESH_OTSU)[1]
##                                  ^^^^^^^^^^^^^^^^^

cnts,_ = cv.findContours(thresh, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)

## sort the contours from largest to smallest.
## the largest will contain your image
cnts = sorted(cnts, key=lambda x:-len(x))

## place a rectangle around the largest contour
rect = cv.boundingRect(cnts[0])
x = rect[1] # column coordinate of top left corner of rectangle
y = rect[0] # row coordinate of top left corner of rectangle
width = rect[2] # width of rectangle
height = rect[3] # height of rectangle
crop = img[y:y+height, x:x+width]
plt.imshow(crop)