How to remove a watermark from an document image-CodePudding

The

Code

import numpy as np import cv2 # Load image, convert to HSV, then HSV color threshold image = cv2.imread('1.jpg') original = image.copy() hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV) lower = np.array([0, 0, 0]) upper = np.array([179, 255, 163]) mask = cv2.inRange(hsv, lower, upper) # Dilate to repair kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3)) dilate = cv2.dilate(mask, kernel, iterations=1) # Second pass of HSV to remove pink colored = cv2.bitwise_and(original, original, mask=dilate) colored_hsv = cv2.cvtColor(colored, cv2.COLOR_BGR2HSV) lower_two = np.array([96, 89, 161]) upper_two = np.array([179, 255, 255]) mask_two = cv2.inRange(colored_hsv, lower_two, upper_two) # Convert to grayscale then remove pink contours result = cv2.cvtColor(colored, cv2.COLOR_BGR2GRAY) result[result <= 10] = 255 cv2.imshow('result before removal', result) result[mask_two==255] = 255 cv2.imshow('dilate', dilate) cv2.imshow('colored', colored) cv2.imshow('mask_two', mask_two) cv2.imshow('result after removal', result) cv2.waitKey()

Depending on the image, you may need to adjust the lower/upper HSV ranges. To determine the HSV lower/upper ranges, you can use this HSV thresholder script with sliders so you don't need to guess and check. Just change the image path

import cv2 import numpy as np def nothing(x): pass # Load image image = cv2.imread('1.jpg') # Create a window cv2.namedWindow('image') # Create trackbars for color change # Hue is from 0-179 for Opencv cv2.createTrackbar('HMin', 'image', 0, 179, nothing) cv2.createTrackbar('SMin', 'image', 0, 255, nothing) cv2.createTrackbar('VMin', 'image', 0, 255, nothing) cv2.createTrackbar('HMax', 'image', 0, 179, nothing) cv2.createTrackbar('SMax', 'image', 0, 255, nothing) cv2.createTrackbar('VMax', 'image', 0, 255, nothing) # Set default value for Max HSV trackbars cv2.setTrackbarPos('HMax', 'image', 179) cv2.setTrackbarPos('SMax', 'image', 255) cv2.setTrackbarPos('VMax', 'image', 255) # Initialize HSV min/max values hMin = sMin = vMin = hMax = sMax = vMax = 0 phMin = psMin = pvMin = phMax = psMax = pvMax = 0 while(1): # Get current positions of all trackbars hMin = cv2.getTrackbarPos('HMin', 'image') sMin = cv2.getTrackbarPos('SMin', 'image') vMin = cv2.getTrackbarPos('VMin', 'image') hMax = cv2.getTrackbarPos('HMax', 'image') sMax = cv2.getTrackbarPos('SMax', 'image') vMax = cv2.getTrackbarPos('VMax', 'image') # Set minimum and maximum HSV values to display lower = np.array([hMin, sMin, vMin]) upper = np.array([hMax, sMax, vMax]) # Convert to HSV format and color threshold hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV) mask = cv2.inRange(hsv, lower, upper) result = cv2.bitwise_and(image, image, mask=mask) # Print if there is a change in HSV value if((phMin != hMin) | (psMin != sMin) | (pvMin != vMin) | (phMax != hMax) | (psMax != sMax) | (pvMax != vMax) ): print("(hMin = %d , sMin = %d, vMin = %d), (hMax = %d , sMax = %d, vMax = %d)" % (hMin , sMin , vMin, hMax, sMax , vMax)) phMin = hMin psMin = sMin pvMin = vMin phMax = hMax psMax = sMax pvMax = vMax # Display result image cv2.imshow('image', result) if cv2.waitKey(10) & 0xFF == ord('q'): break cv2.destroyAllWindows()

CodePudding user response：

The Concept

For this, I used two simple HSV masks; one to fade out the logo (using a simple formula), and one to finish off the masking by completely removing the logo.

Here is the original image, the pre-masked image, and the completely-masked image, in that order:

Here is what the two masks look like:

The Output

The Code

import cv2 import numpy as np def HSV_mask(img_hsv, lower): lower = np.array(lower) upper = np.array([255, 255, 255]) return cv2.inRange(img_hsv, lower, upper) img = cv2.imread("image.jpg") img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV) img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) img_gray[img_gray >= 235] = 255 mask1 = HSV_mask(img_hsv, [0, 0, 155])[..., None].astype(np.float32) mask2 = HSV_mask(img_hsv, [0, 20, 0]) masked = np.uint8((img mask1) / (1 mask1 / 255)) gray = cv2.cvtColor(masked, cv2.COLOR_BGR2GRAY) gray[gray >= 180] = 255 gray[mask2 == 0] = img_gray[mask2 == 0] cv2.imshow("result", gray) cv2.waitKey(0)

The Explanation

Import the necessary libraries:

import cv2 import numpy as np

Define a function, HSV_mask, that will take in an image (that has been converted to HSV color space), and the lower range for the HSV mask (the upper range will be 255, 255, 255), and return the HSV mask:

def HSV_mask(img_hsv, lower): lower = np.array(lower) upper = np.array([255, 255, 255]) return cv2.inRange(img_hsv, lower, upper)

Read in the image, image.jpg, and define two more variables that will hold the image converted to HSV and grayscale. For the grayscale image, replace all pixels of it that is greater or equal to 235 with 255; this will remove some noise from the white parts of the image:

img = cv2.imread("image.jpg") img_hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV) img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) img_gray[img_gray >= 235] = 255

Define 2 variables, mask1 and mask2, using the HSV_mask function defined before. mask1 will mask out everything but the text, and mask2 will mask out everything but the logo:

mask1 = HSV_mask(img_hsv, [0, 0, 155])[..., None].astype(np.float32) mask2 = HSV_mask(img_hsv, [0, 20, 0])

Mask the original image with mask1 and a formula that will fade out (but not remove) the logo. This is just a preprocessing step so that we can remove the logo cleanly later:

masked = np.uint8((img mask1) / (1 mask1 / 255))

Convert the image with the faded logo to grayscale, and apply mask2 so that all pixels masked out by the mask will be converted back to the original image:

gray = cv2.cvtColor(masked, cv2.COLOR_BGR2GRAY) gray[gray >= 180] = 255 gray[mask2 == 0] = img_gray[mask2 == 0]

Finally, show the result:

cv2.imshow("result", gray) cv2.waitKey(0)