我已经使用 opencv 来读取图像，将其转换为灰度，并使用 canny、kernel、thesh、erode 等找到边缘，并且我已经使用 HooughLineP() 检测到图像中的所有线条，并且我已经检测到时间和分针，但我还需要找到秒针，这是我使用过的代码
import cv2
import math
import numpy as np
from matplotlib import pyplot as plt
from math import sqrt
from math import acos, degrees
kernel = np.ones((5,5),np.uint8)
img1 = cv2.imread('input1.jpg')
img = cv2.imread('input1.jpg',0)
gray = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 50, 255, cv2.THRESH_BINARY)
# Create mask
height,width = img.shape
#height=height-10
#width=width-10
mask = np.zeros((height,width), np.uint8)
edges = cv2.Canny(thresh, 100, 200)
#cv2.imshow('detected ',gray)
cimg=cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 1.2, 100)
#circles = cv2.HoughCircles(edges, cv2.HOUGH_GRADIENT, 1.2, 1000, param1 = 50, param2 = 30, minRadius = 20, maxRadius = 0)
for i in circles[0,:]:
i[2]=i[2]+4
# Draw on mask
cv2.circle(mask,(i[0],i[1]),i[2],(255,255,255),thickness=-1)
# Copy that image using that mask
masked_data = cv2.bitwise_and(img1, img1, mask=mask)
# Apply Threshold
_,thresh = cv2.threshold(mask,1,255,cv2.THRESH_BINARY)
# Find Contour
contours = cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
x,y,w,h = cv2.boundingRect(contours[0])
# Crop masked_data
crop = masked_data[y+30:y+h-30,x+30:x+w-30]
i=crop
height, width, channels = i.shape
print (width, height, channels)
#########################################################################
ret, mask = cv2.threshold(i, 10, 255, cv2.THRESH_BINARY)
edges = cv2.Canny(i,100,200)
kernel = np.ones((11,11),np.uint8)
kernel2 = np.ones((13,13),np.uint8)
edges = cv2.dilate(edges,kernel,iterations = 1)
edges = cv2.erode(edges,kernel2,iterations = 1)
minLineLength = 1000
maxLineGap = 10
lines = cv2.HoughLinesP(edges,1,np.pi/180,15,minLineLength,maxLineGap)
h=[]
xmax1=0
xmax2=0
ymax1=0
ymax2=0
xs1=0
xs2=0
ys1=0
ys2=0
for line in lines:
x1, y1, x2, y2 = line[0]
#cv2.line(i, (x1, y1), (x2, y2), (0, 255, 0), 1)
dx=x2-x1
if(dx<0):
dx=dx*-1
dy=y2-y1
if(dy<0):
dy=dy*-1
hypo=sqrt(dx**2 + dy**2)
#print("dx=",dx," dy=",dy)
h.append(hypo)
#print(h)
print(len(h))
a=len(h)
h.sort(reverse=True)
#print(h)
m=0
k=0
for f in range(a):
for line in lines:
x1, y1, x2, y2 = line[0]
#cv2.line(i, (x1, y1), (x2, y2), (0, 255, 0), 3)
dx=x2-x1
if(dx<0):
dx=dx*-1
dy=y2-y1
if(dy<0):
dy=dy*-1
hypo2=sqrt(dx**2 + dy**2)
if(hypo2==h[0]):
m=hypo2
xmax1=x1
xmax2=x2
ymax1=y1
ymax2=y2
cv2.line(crop, (xmax1, ymax1), (xmax2, ymax2), (255, 0, 0), 3)
#print("xmax1=",xmax1," ymax1=",ymax1," xmax2=",xmax2," ymax2=",ymax2)
if(m==h[0]):
if(hypo2==h[f]):
if((sqrt((xmax2-x2)**2 + (ymax2-y2)**2))>20):
if((sqrt((xmax1-x1)**2 + (ymax1-y1)**2))>20):
xs1=x1
xs2=x2
ys1=y1
ys2=y2
cv2.line(crop, (xs1, ys1), (xs2, ys2), (0, 255, 0), 3)
print("xs1=",xs1," ys1=",ys1," xs2=",xs2," ys2=",ys2)
k=1
break
if(k==1):
break
print("xmax1=",xmax1," ymax1=",ymax1," xmax2=",xmax2," ymax2=",ymax2)
我在上面的代码行中将分针和时针分开，但我也需要分开秒针，请任何人帮助我！
基于这篇文章：OpenCV中如何检测线条？我已经适应了您的图像和裁剪方法，它给出了给定图像的有效输出：
import cv2
import numpy as np
from matplotlib import pyplot as plt
kernel = np.ones((5,5),np.uint8)
img1 = cv2.imread('clock.jpg')
img = cv2.imread('clock.jpg',0)
gray = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 50, 255, cv2.THRESH_BINARY)
# Create mask
height,width = img.shape
mask = np.zeros((height,width), np.uint8)
edges = cv2.Canny(thresh, 100, 200)
#cv2.imshow('detected ',gray)
cimg=cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 1.2, 100)
for i in circles[0,:]:
i[2]=i[2]+4
# Draw on mask
cv2.circle(mask,(i[0],i[1]),i[2],(255,255,255),thickness=-1)
# Copy that image using that mask
masked_data = cv2.bitwise_and(img1, img1, mask=mask)
# Apply Threshold
_,thresh = cv2.threshold(mask,1,255,cv2.THRESH_BINARY)
# Find Contour
contours, hierarchy =
cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
x,y,w,h = cv2.boundingRect(contours[0])
# Crop masked_data
crop = masked_data[y+30:y+h-30,x+30:x+w-30]
################################
kernel_size = 5
blur_crop = cv2.GaussianBlur(crop,(kernel_size, kernel_size),0)
low_threshold = 50
high_threshold = 150
edges = cv2.Canny(blur_crop, low_threshold, high_threshold)
rho = 1 # distance resolution in pixels
theta = np.pi / 180 # angular resolution in radians
threshold = 15 # minimum number of votes
min_line_length = 100 # minimum number of pixels making up a line
max_line_gap = 10 # maximum gap in pixels between connectable
line segments
line_image = np.copy(crop) * 0
# Run Hough on edge detected image
# Output "lines" is an array containing endpoints of detected line
lines = cv2.HoughLinesP(edges, rho, theta, threshold, np.array([]),
min_line_length, max_line_gap)
for line in lines:
for x1,y1,x2,y2 in line:
cv2.line(line_image,(x1,y1),(x2,y2),(255,0,0),5)
# Draw the lines on the image
lines_edges = cv2.addWeighted(crop, 0.8, line_image, 1, 0)
cv2.imshow('line_image', line_image)
cv2.imshow('crop', crop)
With some parameter tweaking on the Hough detection you should be able to reduce the results to 3 nice lines.
