How to remove all the detected lines from the original image using Python?

Question

I am trying to remove all the lines present in the image. I am able to detect the lines but when I am trying to remove the lines, I am still getting few small lines in the final image. I have used cv2.getStructuringElement to get both the horizontal and vertical lines. In some cases, the final image is getting completely distorted and I am not able to move forward

The image is taken from google

    res = verticle_lines_img + horizontal_lines_img 
    res = cv2.bitwise_not(res)
    fin=cv2.bitwise_or(img_bin, res,mask =cv2.bitwise_not(res))
    fin= cv2.bitwise_not(fin)
    exp =255-res
    final = cv2.bitwise_and(exp,img_bin)
    final = cv2.bitwise_not(final)
    exp = ~exp
    finalised = cv2.bitwise_and(img_bin,final)
    finalised = cv2.bitwise_not(finalised)

Please help! Thanks

score 5 · Accepted Answer · answered Sep 16 '19 at 20:04

Here's an approach

Convert image to grayscale
Otsu's threshold to obtain binary image
Remove horizontal lines
Remove vertical lines

After converting to grayscale, we Otsu's threshold to get a binary image

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

From here we construct a special horizontal kernel to detect horizontal lines. Once the lines are detected, we fill in the lines to effectively remove the line

# Remove horizontal
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (10,1))
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts = cv2.findContours(detected_lines, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    cv2.drawContours(image, [c], -1, (255,255,255), 2)

Similarly, to remove vertical lines, we construct a special vertical kernel

# Remove vertical
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,10))
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
cnts = cv2.findContours(detected_lines, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    cv2.drawContours(image, [c], -1, (255,255,255), 2)

Here's the detected lines in green

Result

You can fine tune the results by adjusting the kernel size. For instance, changing (10,1) to say (15,1) will tighten the line detection while lowering it to (5,1) will loosen the detection

Full Code

import cv2

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

# Remove horizontal
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (10,1))
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts = cv2.findContours(detected_lines, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    cv2.drawContours(image, [c], -1, (255,255,255), 2)

# Remove vertical
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,10))
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
cnts = cv2.findContours(detected_lines, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    cv2.drawContours(image, [c], -1, (255,255,255), 2)

cv2.imshow('thresh', thresh)
cv2.imshow('image', image)
cv2.waitKey()

Thanks @nathancy, the output image that I am getting now is better than what I was getting earlier. Although there are still long horizontal lines that are present in the image. Any advice on how to get them removed? — not_yet_a_fds, Sep 16 '19 at 20:23
Try like `(20,1)` or `(50,1)`, its experimental. There is a tradeoff, you don't want a too small kernel which takes away the text but you also dont want a too big kernel where it doesnt detect anything. You can try also modifying the "line width" by increasing the other parameter such as `(20, 2)` — nathancy, Sep 16 '19 at 20:29
For me changing the width of the contours to 3 did the job. Thank you @nathancy — not_yet_a_fds, Sep 16 '19 at 20:43

How to remove all the detected lines from the original image using Python?

1 Answers1

Linked