Draw grid on a gridless (fully or partially) table image

Question

I have an image that contains a table, the table can be in many sizes and the image too, and the table can be fully gridded (with only some blank spot that needs to be filled), it can be with only vertical grid lines and can be only with horizontal grid lines.

I've searched the web for a long time and found no solution that worked for me.

I found the following questions that seem to be suitable for me:

• Python & OpenCV: How to add lines to the gridless table
• Draw a line on a gridless image Python Opencv
• How to repair incomplete grid cells and fix missing sections in image
• Python & OpenCV: How to crop half-formed bounding boxes

My code is taken from the answers to the above questions and the "best" result I got from the above question codes is that it drew 2 lines one at the rightmost part and one on the leftmost part.

I'm kind of new to OpenCV and the image processing field so I am not sure how can I fix the above questions codes to suit my needs or how to accomplish my needs exactly, I would appreciate any help you can provide.

Example of an image table:

Update:

To remove the horizontal lines I use exactly the code you can find in here, but the result I get on the example image is this:

as you can see it removed most of them but not all of them, and then when I try to apply the same for the vertical ones (I tried the same code with rotation, or flipping the kernel) it does not work at all...

I also tried this code but it didn't work at all also.

Update 2:

I was able to remove the lines using this code:

def removeLines(result, axis) -> np.ndarray:
    img = result.copy()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
    if axis == "horizontal":
        kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, 25))
    elif axis == "vertical":
        kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (25, 1))
    else:
        raise ValueError("Axis must be either 'horizontal' or 'vertical'")
    detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, 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]
    result = img.copy()
    for c in cnts:
        cv2.drawContours(result, [c], -1, (255, 255, 255), 2)
    return result

gridless = removeLines(removeLines(cv2.imread(image_path), 'horizontal'), 'vertical')

Result:

Problem: After I remove lines, when I try to draw the vertical lines using this code:

# read image
img = old_image.copy() # cv2.imread(image_path1)
hh, ww = img.shape[:2]
# convert to grayscale 
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# average gray image to one column
column = cv2.resize(gray, (ww,1), interpolation = cv2.INTER_AREA)
# threshold on white
thresh = cv2.threshold(column, 248, 255, cv2.THRESH_BINARY)[1]
# get contours
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# Draw vertical
for cntr in contours_v:
    x,y,w,h = cv2.boundingRect(cntr)
    xcenter = x+w//2
    cv2.line(original_image, (xcenter,0), (xcenter,hh-1), (0, 0, 0), 1)

I get this result:

Update 3:

when I try even thresh = cv2.threshold(column, 254, 255, cv2.THRESH_BINARY)[1] (I tried lowering it 1 by 1 until 245, for both the max value and the threshold value, each time I get a different or similar result but always too much lines or too less lines) I get the following:

Input:

Output:

It's putting too many lines instead of just 1 line in each column

Code:

# read image
img = old_image.copy() # cv2.imread(image_path1)
hh, ww = img.shape[:2]
# convert to grayscale 
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# average gray image to one column
column = cv2.resize(gray, (ww, 1), interpolation = cv2.INTER_AREA)
# threshold on white
thresh = cv2.threshold(column, 254, 255, cv2.THRESH_BINARY)[1]
# get contours
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
for cntr in contours:
    x, y, w, h = cv2.boundingRect(cntr)
    xcenter = x + w // 2
    cv2.line(original_image, (xcenter,0), (xcenter, hh_-1), (0, 0, 0), 1)

Answer 1

Here is one way to get the lines in Python/OpenCV. Average the image down to 1 column. Then threshold and get the contours. Then get the bounding boxes and find the vertical centers. Draw lines at those places.

If you do not want the extra lines, crop your image first to get the inside of the table.

Input:

import cv2
import numpy as np

# read image
img = cv2.imread("table4.png")
hh, ww = img.shape[:2]

# convert to grayscale 
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# average gray image to one column
column = cv2.resize(gray, (1,hh), interpolation = cv2.INTER_AREA)

# threshold on white
thresh = cv2.threshold(column, 248, 255, cv2.THRESH_BINARY)[1]

# get contours
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]

# loop over contours and get bounding boxes and ycenter and draw horizontal line at ycenter
result = img.copy()
for cntr in contours:
    x,y,w,h = cv2.boundingRect(cntr)
    ycenter = y+h//2
    cv2.line(result, (0,ycenter), (ww-1,ycenter), (0, 0, 255), 1)

# write results
cv2.imwrite("table4_lines3.png", result)

# display results
cv2.imshow("RESULT", result)
cv2.waitKey(0)

Result:

Answer 2

You wrote that you tried to remove the lines using the code, but it did not work.

It works fine for me in Python/OpenCV.

• Read the input
• Convert to grayscale
• Threshold to show the horizontal lines
• Apply morphology open with a horizontal kernel to isolate the horizontal lines
• Get their contours
• Draw the contours on a copy of the input as white to cover over the black horizontal lines
• Save the results

Input:

import cv2
import numpy as np

# read the input 
img = cv2.imread('table4.png')

# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

# threshold
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

# do morphology to detect lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (25,1))
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)

# get contours
cnts = cv2.findContours(detected_lines, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]

# draw contours as white on copy of input
result = img.copy()
for c in cnts:
    cv2.drawContours(result, [c], -1, (255,255,255), 2)

# save results
cv2.imwrite('table4_horizontal_lines_threshold.png', thresh)
cv2.imwrite('table4_horizontal_lines_detected.png', detected_lines)
cv2.imwrite('table4_horizontal_lines_removed.png', result)

# show results
cv2.imshow('thresh', thresh)
cv2.imshow('morphology', detected_lines)
cv2.imshow('result', result)
cv2.waitKey(0)

Threshold Image:

Morphology Detected Lines Image:

Result: