How can I detect only vertical lines in an image?

Question

I have this image:

From that I want to detect only vertical lines, and don't want horizontal lines anyway.

I have written the following code which gives me this result with horizontal lines, too:

That's my code:

import sys
import math
import cv2 as cv
import numpy as np


def main(argv):
    default_file = 'C:/Users/Rizwan/Desktop/amy_images/image2_43WqE0i.png'
    filename = argv[0] if len(argv) > 0 else default_file
    # Loads an image
    src = cv.imread(cv.samples.findFile(filename), cv.IMREAD_GRAYSCALE)
    img = cv.resize(src, (100, 40))
    src = cv.medianBlur(img, 5)
    # Check if image is loaded fine
    if src is None:
        print('Error opening image!')
        print('Usage: hough_lines.py [image_name -- default ' + default_file + '] \n')
        return -1

    dst = cv.Canny(src, 10, 40, None, 3)

    # Copy edges to the images that will display the results in BGR
    cdst = cv.cvtColor(dst, cv.COLOR_GRAY2BGR)
    cdstP = np.copy(cdst)

    lines = cv.HoughLines(dst, 1, np.pi / 180, 150, None, 0, 0)

    if lines is not None:
        for i in range(0, len(lines)):
            rho = lines[i][0][0]
            theta = lines[i][0][1]
            a = math.cos(theta)
            b = math.sin(theta)
            x0 = a * rho
            y0 = b * rho
            pt1 = (int(x0 + 1000 * (-b)), int(y0 + 1000 * (a)))
            pt2 = (int(x0 - 1000 * (-b)), int(y0 - 1000 * (a)))
            cv.line(cdst, pt1, pt2, (0, 0, 255), 3, cv.LINE_AA)

    linesP = cv.HoughLinesP(dst, 1, np.pi / 180, 50, None, 50, 10)

    if linesP is not None:
        for i in range(0, len(linesP)):
            l = linesP[i][0]
            cv.line(cdstP, (l[0], l[1]), (l[2], l[3]), (0, 0, 255), 3, cv.LINE_AA)

    cv.imshow("Source", src)
    cv.imshow("Detected Lines (in red) - Standard Hough Line Transform", cdst)
    cv.imwrite("Source.png", cdst)
    cv.imwrite("Source1.png", src)
    # cv.imshow("Detected Lines (in red) - Probabilistic Line Transform", cdstP)

    cv.waitKey()
    return 0


if __name__ == "__main__":
    main(sys.argv[1:])

And one thing more that this gives me two lines in first-line and two lines in the second line as in original image there are only two thick lines but in the second image it giving me 4 vertical lines.

Any help would be highly appreciated.

Community · Accepted Answer · 2020-06-20 09:12:55Z

3

The (intensity) difference between the lighter stripe and the background is just around 10. The best idea here would be to use cv2.adaptiveThreshold and morphological opening with some vertical line kernel afterwards, cf. cv2.morphologyEx.

Here's some code:

import cv2
import numpy as np
from skimage import io      # Only needed for web grabbing images, use cv2.imread for local images

# Read image from web (is already grayscale)
image = io.imread('https://i.sstatic.net/FVrCN.png')

# Apply adaptive threshold
image_thr = cv2.adaptiveThreshold(image, 255, cv2.THRESH_BINARY_INV, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, 51, 0)

# Apply morphological opening with vertical line kernel
kernel = np.ones((image.shape[0], 1), dtype=np.uint8) * 255
image_mop = cv2.morphologyEx(image_thr, cv2.MORPH_OPEN, kernel)

# Canny edge detection
image_canny = cv2.Canny(image_mop, 1, 3)

# Get pixel values from the input image (force RGB/BGR on given input) within stripes
image_bgr = cv2.cvtColor(image, cv2.COLOR_GRAY2BGR)
pixels = image_bgr[image_mop > 0, :]
print(pixels)

# (Visualization) Output
cv2.imshow('image', image)
cv2.imshow('image_thr', image_thr)
cv2.imshow('image_mop', image_mop)
cv2.imshow('image_canny', image_canny)
cv2.waitKey(0)
cv2.destroyAllWindows()

Result of adaptive thresholding:

After morphological opening:

After Canny edge detection:

You can play around with the parameters. Maybe the "shape" of the lines can be improved.

Hope that helps!

edited Jun 20, 2020 at 9:12

CommunityBot

11 silver badge

answered Dec 3, 2019 at 12:16

HansHirse

19k10 gold badges48 silver badges78 bronze badges

Sign up to request clarification or add additional context in comments.

10 Comments

Loïc Over a year ago

Those cv2 skills :o

rizwan Over a year ago

Thanks HansHirse for your reply, here is the error i get when running your code: ---> image_thr = cv2.adaptiveThreshold(image, 255, cv2.THRESH_BINARY_INV, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, 51, 0) cv2.error: OpenCV(4.1.1) C:\projects\opencv-python\opencv\modules\imgproc\src\thresh.cpp:1645: error: (-215:Assertion failed) src.type() == CV_8UC1 in function 'cv::adaptiveThreshold'

HansHirse Over a year ago

@rizwan Make sure, that image is a uint8 grayscale image, i.e. image.shape should be (height, width). Most likely, you tried to pass a color image, i.e. image.shape is (height, width, 3). Try image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) before passing the image to cv2.adaptiveThreshold.

rizwan Over a year ago

Yes, It solved. And the results are now even better than before. I am really thankful to you @HansHirse :) You really deserve more respect in the field :)

rizwan Over a year ago

@HansHirse how can I get the original image's RGB values for the detect lines?

|

Collectives™ on Stack Overflow

How can I detect only vertical lines in an image?

1 Answer 1

10 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

10 Comments

Your Answer

Sign up or log in

Post as a guest

Related