opencv Scharr、Canny、LOG边缘提取效果对比

# -*- coding: utf-8 -*-
import cv2 as cv
import numpy as np  
import matplotlib.pyplot as plt

#读取图像
img = cv.imread('d:/paojie.png')
img1 = cv.cvtColor(img, cv.COLOR_BGR2RGB)

#转换为灰度图像
grayImage = cv.cvtColor(img, cv.COLOR_BGR2GRAY)

#高斯滤波
gaussianBlur = cv.GaussianBlur(grayImage, (3,3), 0)

#自适应阈值处理
ret, binary = cv.threshold(gaussianBlur, 0, 255, cv.THRESH_BINARY+cv.THRESH_OTSU)

#Scharr算子
x = cv.Scharr(grayImage, cv.CV_32F, 1, 0) #X方向
y = cv.Scharr(grayImage, cv.CV_32F, 0, 1) #Y方向
absX = cv.convertScaleAbs(x)       
absY = cv.convertScaleAbs(y)
Scharr = cv.addWeighted(absX, 0.5, absY, 0.5, 0)

#Canny算子
gaussian = cv.GaussianBlur(grayImage, (3,3), 0) #高斯滤波降噪
Canny = cv.Canny(gaussian, 50, 150) 

#LOG算子
gaussian = cv.GaussianBlur(grayImage, (3,3), 0) #先通过高斯滤波降噪
dst = cv.Laplacian(gaussian, cv.CV_16S, ksize = 3) #再通过拉普拉斯算子做边缘检测
LOG = cv.convertScaleAbs(dst)

#效果图
titles = ['Source Image', 'Gray Image', 'Binary Image',
          'Scharr Image','Canny Image', 'LOG Image']  
images = [img1, grayImage, binary, Scharr, Canny, LOG]  
for i in np.arange(6):  
   plt.subplot(2,3,i+1),plt.imshow(images[i],'gray')  
   plt.title(titles[i])  
   plt.xticks([]),plt.yticks([])  
plt.show()  
实验输出

你可能感兴趣的:(opencv Scharr、Canny、LOG边缘提取效果对比)