python 各种边缘检测方法效果比对

效果展示

python代码

#encoding:utf-8
import cv2  
import numpy as np  
import matplotlib.pyplot as plt

#读取图像
img = cv2.imread('1.bmp',cv2.IMREAD_GRAYSCALE)
lenna_img = img #cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

#灰度化处理图像
grayImage = img #cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#高斯滤波
gaussianBlur = cv2.GaussianBlur(grayImage, (3,3), 0)

#阈值处理
#ret, binary = cv2.threshold(gaussianBlur, 150, 255, cv2.THRESH_BINARY)
#自适应阈值处理
binary = cv2.adaptiveThreshold(src=gaussianBlur,maxValue=255,adaptiveMethod=cv2.ADAPTIVE_THRESH_MEAN_C,thresholdType=cv2.THRESH_BINARY,blockSize=11,C=1)  


#Roberts算子
kernelx = np.array([[-1,0],[0,1]], dtype=int)
kernely = np.array([[0,-1],[1,0]], dtype=int)
x = cv2.filter2D(binary, cv2.CV_16S, kernelx)
y = cv2.filter2D(binary, cv2.CV_16S, kernely)
absX = cv2.convertScaleAbs(x)     
absY = cv2.convertScaleAbs(y)    
Roberts = cv2.addWeighted(absX, 0.5, absY, 0.5, 0)

#Prewitt算子
kernelx = np.array([[1,1,1],[0,0,0],[-1,-1,-1]], dtype=int)
kernely = np.array([[-1,0,1],[-1,0,1],[-1,0,1]], dtype=int)
x = cv2.filter2D(binary, cv2.CV_16S, kernelx)
y = cv2.filter2D(binary, cv2.CV_16S, kernely)
absX = cv2.convertScaleAbs(x)  
absY = cv2.convertScaleAbs(y)    
Prewitt = cv2.addWeighted(absX,0.5,absY,0.5,0)

#Sobel算子
x = cv2.Sobel(binary, cv2.CV_16S, 1, 0)
y = cv2.Sobel(binary, cv2.CV_16S, 0, 1)    
absX = cv2.convertScaleAbs(x)   
absY = cv2.convertScaleAbs(y)    
Sobel = cv2.addWeighted(absX, 0.5, absY, 0.5, 0)

#拉普拉斯算法
dst = cv2.Laplacian(binary, cv2.CV_16S, ksize = 3)
Laplacian = cv2.convertScaleAbs(dst)

# Scharr算子
x = cv2.Scharr(gaussianBlur, cv2.CV_32F, 1, 0) #X方向
y = cv2.Scharr(gaussianBlur, cv2.CV_32F, 0, 1) #Y方向
absX = cv2.convertScaleAbs(x)       
absY = cv2.convertScaleAbs(y)
Scharr = cv2.addWeighted(absX, 0.5, absY, 0.5, 0)

#Canny算子
Canny = cv2.Canny(gaussianBlur, 20, 30)

#先通过高斯滤波降噪
gaussian = cv2.GaussianBlur(grayImage, (3,3), 0)
 
#再通过拉普拉斯算子做边缘检测
dst = cv2.Laplacian(gaussian, cv2.CV_16S, ksize = 3)
LOG = cv2.convertScaleAbs(dst)

#效果图
fig = plt.figure(figsize=(10, 10))#设置大小
titles = ['Source Image', 'Binary Image', 'Roberts Image',
          'Prewitt Image','Sobel Image', 'Laplacian Image',
          'Scharr Image', 'Canny Image', 'LOG Image']  
images = [lenna_img, binary, Roberts,
          Prewitt, Sobel, Laplacian,
          Scharr, Canny, LOG]  
for i in np.arange(9):  
   plt.subplot(3,3,i+1),plt.imshow(images[i],'gray')  
   plt.title(titles[i])  
   plt.xticks([]),plt.yticks([])  
plt.show()  
fig.savefig('fig-sharp.jpg',bbox_inches='tight')

具体原理等描述见Python图像锐化及边缘检测(RobertsPrewittSobelLapllacianCannyLOG)