How do you detect the largest set of parallel lines in an image?

Question

I have images with multiple line in them and I’m looking to detect the largest set of lines which are (approximately) parallel using Python and OpenCV. For example give:

The green lines are the best set:

Asked By: nickponline

||

Source

Answer 1

you can follow the following steps

Apply the Hough Line Transform to detect all line segments in the image.
Group the line segments based on their orientation using a clustering
Identify the largest cluster of lines. These will be the set of lines
that are approximately parallel.

import cv2
import numpy as np
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt


img = cv2.imread('UI5Mr.png')


gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)


edges = cv2.Canny(gray, 50, 150, apertureSize=3)


lines = cv2.HoughLinesP(edges, rho=1, theta=np.pi/180, threshold=100, minLineLength=100, maxLineGap=10)


X = np.array([[x1, y1, x2, y2] for [[x1, y1, x2, y2]] in lines])
kmeans = KMeans(n_clusters=2)
kmeans.fit(X[:, [2, 3]] - X[:, [0, 1]])
labels = kmeans.labels_
centers = kmeans.cluster_centers_


counts = np.bincount(labels)
largest_cluster_idx = np.argmax(counts)
largest_cluster_mask = (labels == largest_cluster_idx)
largest_cluster_lines = X[largest_cluster_mask]


for [x1, y1, x2, y2] in largest_cluster_lines:
    cv2.line(img, (x1, y1), (x2, y2), (0, 255, 0), 2)


plt.imshow(img)

Answered By: Basir Mahmood

How do you detect the largest set of parallel lines in an image?

Question:

Answers: