这是使用 OpenCV 2.4 用 python 2.7.x 编写的完整解决方案。
它在这个线程中使用了来自alkasm 的解决方案，这是不完整的。 HoughLines() 的返回值和 kmeans() 的语法也从 OpenCV 2.x 更改为 3.x
结果 1：桌子上的一张纸
https://i.ibb.co/VBSY7V7/paper-on-desk-intersection-points.jpg
这回答了最初的问题，但是使用 k = 2,3,4 的 k-means 聚类不会分割纸张。您需要一种不同的方法来找到纸的角落
例如过滤平行线。
结果 2：数独网格
https://i.ibb.co/b6thfgr/sudoku-intersection-points.jpg
代码： https://pastiebin.com/5f36425b7ae3d
"""
Find the intersection points of lines.
"""
import numpy as np
import cv2
from collections import defaultdict
import sys
img = cv2.imread("paper_on_desk.jpg")
#img = cv2.imread("sudoku.jpg")
def segment_by_angle_kmeans(lines, k=2, **kwargs):
"""
Group lines by their angle using k-means clustering.
Code from here:
https://stackoverflow.com/a/46572063/1755401
"""
# Define criteria = (type, max_iter, epsilon)
default_criteria_type = cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER
criteria = kwargs.get('criteria', (default_criteria_type, 10, 1.0))
flags = kwargs.get('flags', cv2.KMEANS_RANDOM_CENTERS)
attempts = kwargs.get('attempts', 10)
# Get angles in [0, pi] radians
angles = np.array([line[0][1] for line in lines])
# Multiply the angles by two and find coordinates of that angle on the Unit Circle
pts = np.array([[np.cos(2*angle), np.sin(2*angle)] for angle in angles], dtype=np.float32)
# Run k-means
if sys.version_info[0] == 2:
# python 2.x
ret, labels, centers = cv2.kmeans(pts, k, criteria, attempts, flags)
else:
# python 3.x, syntax has changed.
labels, centers = cv2.kmeans(pts, k, None, criteria, attempts, flags)[1:]
labels = labels.reshape(-1) # Transpose to row vector
# Segment lines based on their label of 0 or 1
segmented = defaultdict(list)
for i, line in zip(range(len(lines)), lines):
segmented[labels[i]].append(line)
segmented = list(segmented.values())
print("Segmented lines into two groups: %d, %d" % (len(segmented[0]), len(segmented[1])))
return segmented
def intersection(line1, line2):
"""
Find the intersection of two lines
specified in Hesse normal form.
Returns closest integer pixel locations.
See here:
https://stackoverflow.com/a/383527/5087436
"""
rho1, theta1 = line1[0]
rho2, theta2 = line2[0]
A = np.array([[np.cos(theta1), np.sin(theta1)],
[np.cos(theta2), np.sin(theta2)]])
b = np.array([[rho1], [rho2]])
x0, y0 = np.linalg.solve(A, b)
x0, y0 = int(np.round(x0)), int(np.round(y0))
return [[x0, y0]]
def segmented_intersections(lines):
"""
Find the intersection between groups of lines.
"""
intersections = []
for i, group in enumerate(lines[:-1]):
for next_group in lines[i+1:]:
for line1 in group:
for line2 in next_group:
intersections.append(intersection(line1, line2))
return intersections
def drawLines(img, lines, color=(0,0,255)):
"""
Draw lines on an image
"""
for line in lines:
for rho,theta in line:
a = np.cos(theta)
b = np.sin(theta)
x0 = a*rho
y0 = b*rho
x1 = int(x0 + 1000*(-b))
y1 = int(y0 + 1000*(a))
x2 = int(x0 - 1000*(-b))
y2 = int(y0 - 1000*(a))
cv2.line(img, (x1,y1), (x2,y2), color, 1)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
blur = cv2.medianBlur(gray, 5)
# Make binary image
adapt_type = cv2.ADAPTIVE_THRESH_GAUSSIAN_C
thresh_type = cv2.THRESH_BINARY_INV
bin_img = cv2.adaptiveThreshold(blur, 255, adapt_type, thresh_type, 11, 2)
cv2.imshow("binary", bin_img)
cv2.waitKey()
# Detect lines
rho = 2
theta = np.pi/180
thresh = 350
lines = cv2.HoughLines(bin_img, rho, theta, thresh)
if sys.version_info[0] == 2:
# python 2.x
# Re-shape from 1xNx2 to Nx1x2
temp_lines = []
N = lines.shape[1]
for i in range(N):
rho = lines[0,i,0]
theta = lines[0,i,1]
temp_lines.append( np.array([[rho,theta]]) )
lines = temp_lines
print("Found lines: %d" % (len(lines)))
# Draw all Hough lines in red
img_with_all_lines = np.copy(img)
drawLines(img_with_all_lines, lines)
cv2.imshow("Hough lines", img_with_all_lines)
cv2.waitKey()
cv2.imwrite("all_lines.jpg", img_with_all_lines)
# Cluster line angles into 2 groups (vertical and horizontal)
segmented = segment_by_angle_kmeans(lines, 2)
# Find the intersections of each vertical line with each horizontal line
intersections = segmented_intersections(segmented)
img_with_segmented_lines = np.copy(img)
# Draw vertical lines in green
vertical_lines = segmented[1]
img_with_vertical_lines = np.copy(img)
drawLines(img_with_segmented_lines, vertical_lines, (0,255,0))
# Draw horizontal lines in yellow
horizontal_lines = segmented[0]
img_with_horizontal_lines = np.copy(img)
drawLines(img_with_segmented_lines, horizontal_lines, (0,255,255))
# Draw intersection points in magenta
for point in intersections:
pt = (point[0][0], point[0][1])
length = 5
cv2.line(img_with_segmented_lines, (pt[0], pt[1]-length), (pt[0], pt[1]+length), (255, 0, 255), 1) # vertical line
cv2.line(img_with_segmented_lines, (pt[0]-length, pt[1]), (pt[0]+length, pt[1]), (255, 0, 255), 1)
cv2.imshow("Segmented lines", img_with_segmented_lines)
cv2.waitKey()
cv2.imwrite("intersection_points.jpg", img_with_segmented_lines)