0

I'm trying to detect background lines of a pre-processed binary image of a newspaper article using Hough lines transform.

The code I used is given below and it detects only one vertical background line, but I want to detect all the vertical background lines.

How can I improve my code to detect all the vertical background lines only as I marked in the expected output image?

import cv2 as cv
import numpy as np
import os
    
#binary image
image = cv.imread('../outputs/contour.jpg')
gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)  # convert2grayscale
(thresh, binary) = cv.threshold(gray, 150, 255, cv.THRESH_BINARY | cv.THRESH_OTSU)
#cv.imshow('binary',binary)
#cv.waitKey(0)
    
minLineLength = 10
maxLineGap = 40
lines=np.array([])
    
lines = cv.HoughLinesP(binary,rho=np.pi/180,theta=np.pi/180,threshold=10,lines=lines,minLineLength=minLineLength,maxLineGap=maxLineGap)

for x1,y1,x2,y2 in lines[0]:
   cv.line(image,(x1,y1),(x2,y2),(0,255,0),2)
    
cv.imshow('lines',image)
path='../outputs'
cv.imwrite(os.path.join(path , 'line.jpg'), image)
cv.waitKey(0)

The expected Output is like this:enter image description here

But the output I get from above code is this: enter image description here

The input image is: enter image description here

Jin Lee
  • 3,194
  • 12
  • 46
  • 86
Shashiwadana
  • 492
  • 1
  • 8
  • 16

1 Answers1

1

This is a brute-force solution, you might want to optimize the parameters to make it better:

result

#------------------#
# Import Libraries #
#------------------#
import matplotlib.pyplot as plt
import numpy as np
import cv2

# Read Image
image = cv2.imread('input.jpg', 0)
# Gaussian Blur 
blur = cv2.GaussianBlur(image,(13,13),5)
# Morphological opening
kernel = np.ones((11,11), dtype=np.uint8)
opening = cv2.morphologyEx(blur, cv2.MORPH_OPEN, kernel)

# Thresholding
(_, thresh) = cv2.threshold(opening, 150, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
(_, thresh2) = cv2.threshold(image, 150, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
# Stacking the image to draw lines in colour
image = np.stack([image, image, image], axis=2)

# Define Hough Parameters
minLineLength = 40
maxLineGap = 10
# Hough Lines Detection
lines1 = cv2.HoughLinesP(thresh,rho=np.pi/180,theta=np.pi/180,threshold=1,minLineLength=minLineLength,maxLineGap=maxLineGap)
lines2 = cv2.HoughLinesP(thresh,rho=np.pi/180,theta=np.pi/180,threshold=10,minLineLength=minLineLength,maxLineGap=maxLineGap)
lines3 = cv2.HoughLinesP(thresh2,rho=np.pi/180,theta=np.pi/180,threshold=10,minLineLength=minLineLength,maxLineGap=maxLineGap)

# Stack the detections
Lines = np.vstack([lines1[0], lines2[0], lines3[0]])

# Draw the Lines
for row in range(Lines.shape[0]):
    x1,y1,x2,y2 = Lines[row, 0], Lines[row, 1], Lines[row, 2], Lines[row, 3]
    cv2.line(image,(x1,y1),(x2,y2),(0,255,0),2)

# Visualize results
cv2.imshow('lines',image)
cv2.waitKey(0)
Bilal
  • 3,191
  • 4
  • 21
  • 49
  • Could you please explain this part of your code````# Stack the detections Lines = np.vstack([lines1[0], lines2[0], lines3[0]]) # Draw the Lines for row in range(Lines.shape[0]): x1,y1,x2,y2 = Lines[row, 0], Lines[row, 1], Lines[row, 2], Lines[row, 3] cv2.line(image,(x1,y1),(x2,y2),(0,255,0),2)```` – Shashiwadana Feb 27 '21 at 07:12
  • 1
    @Shashiwadana `Stack the detections` part to join the arrays which contain the detected lines all together in one array(vertically) instead of 3. # `Draw the Lines` part is for each row in the array get the 4 coordinates `x1, x2, y1, y2` and simply draw the line over the image, to understand it perfectly try to print the shape of the array before, and after stacking. – Bilal Feb 27 '21 at 07:18