Morphological operation of OpenCV image processing

Opencv Morphological operation of image processing

Morphological operation ： corrosion , inflation , Open close operation , Top hat and black hat , And the relationship between different operations

Connectivity
Binary figure ：

Pixels 4 Neighborhood ,D Neighborhood ,8 Neighborhood

Connectivity , Meet specific similarity criteria
4 connected ,8 connected

M connected
Same value , Four connections have no intersection

Corrosion and expansion

corrosion ：

Use structure B Every pixel and structure in the element A Covered pixels do “ And ” operation , If it's all for 1, Then the pixel is 1, Otherwise 0. As shown in the figure below , structure A Quilt structure B After corrosion ：
Corrosion results
API：

cv.erode(img,kernel,iterations)
Parameters ：

img: The image to be processed
kernel: Nuclear structure
iterations: The number of corrosions , The default is 1

inflation
Scan each pixel in the image with a structural element , Use each pixel in the structure element and the pixel it covers “ And ” operation , If it's all for 0, Then the pixel is 0, Otherwise 1

API：

cv.dilate(img,kernel,iterations)
Parameters ：

img: The image to be processed

kernel: Nuclear structure

iterations: The number of corrosions , The default is 1

import numpy as np
import cv2 as cv
import matplotlib.pyplot as plt
# 1  Read images 
img = cv.imread("./shouxieshuzi001.jpg")
# 2  Create core structure 
kernel = np.ones((5, 5), np.uint8)

# 3  Image corrosion and expansion 
erosion = cv.erode(img, kernel) #  corrosion 
dilate = cv.dilate(img,kernel) #  inflation 

# 4  Image display 
fig,axes=plt.subplots(nrows=1,ncols=3,figsize=(10,8),dpi=100)
axes[0].imshow(img)
axes[0].set_title(" Original picture ")
axes[1].imshow(erosion)
axes[1].set_title(" Results after corrosion ")
axes[2].imshow(dilate)
axes[2].set_title(" The result of expansion ")
plt.show()

Open close operation
Open and close operations are to treat corrosion and expansion in a certain order .

Open operation , It is considered as corrosion before expansion , Eliminate noise , Does not affect the original image .

Eliminate external noise
Closed operation , Expand first and then corrode , The function is to eliminate /“ closed ” Holes in objects

Eliminate internal holes

cv.morphologyEx(img, op, kernel)
Parameters ：

img: The image to be processed
op: Processing mode ： If you do an open operation , Set to cv.MORPH_OPEN, If you do a closed operation , Set to cv.MORPH_CLOSE
Kernel： Nuclear structure

import numpy as np
import cv2 as cv
import matplotlib.pyplot as plt
# 1  Read images 
img1 = cv.imread("./shouxieshuzi002.jpg")
img2 = cv.imread("./shouxieshuzi002.jpg")
# 2  Create core structure 
kernel = np.ones((10, 10), np.uint8)
# 3  Image opening and closing operation 
cvOpen = cv.morphologyEx(img1,cv.MORPH_OPEN,kernel) #  Open operation 
cvClose = cv.morphologyEx(img2,cv.MORPH_CLOSE,kernel)#  Closed operation 
# 4  Image display 
fig,axes=plt.subplots(nrows=2,ncols=2,figsize=(10,8))
axes[0,0].imshow(img1)
axes[0,0].set_title(" Original picture ")
axes[0,1].imshow(cvOpen)
axes[0,1].set_title(" The result of the open operation is ")
axes[1,0].imshow(img2)
axes[1,0].set_title(" Original picture ")
axes[1,1].imshow(cvClose)
axes[1,1].set_title(" Closed operation result ")
plt.show()

Top hat and black hat
Top hat arithmetic

The original image and “ Open operation “ The difference between the results of

Black hat operation

by ” Closed operation “ The difference between the result image and the original image

cv.morphologyEx(img, op, kernel)
Parameters ：

img: The image to be processed

op: Processing mode ：

import numpy as np
import cv2 as cv
import matplotlib.pyplot as plt
# 1  Read images 
img1 = cv.imread("./0055.png")
img2 = cv.imread("./0055.png")
# 2  Create core structure 
kernel = np.ones((10, 10), np.uint8)
# 3  Top hat and black hat operation of image 
cvOpen = cv.morphologyEx(img1,cv.MORPH_TOPHAT,kernel) #  Top hat arithmetic 
cvClose = cv.morphologyEx(img2,cv.MORPH_BLACKHAT,kernel)#  Black hat operation 
# 4  Image display 
fig,axes=plt.subplots(nrows=2,ncols=2,figsize=(10,8))
axes[0,0].imshow(img1)
axes[0,0].set_title(" Original picture ")
axes[0,1].imshow(cvOpen)
axes[0,1].set_title(" Top hat calculation result ")
axes[1,0].imshow(img2)
axes[1,0].set_title(" Original picture ")
axes[1,1].imshow(cvClose)
axes[1,1].set_title(" Black hat operation result ")
plt.show()