9形态学图像处理

9.2腐蚀与膨胀

9.2.1腐蚀

img=cv2.imread('dige.png',0)
kernel = np.ones((3,3),np.uint8) 
num=[[]]*6
for i in range(6):
    num[i] = cv2.erode(img,kernel,iterations = i)
plt_show(num[0],num[1],num[2],num[3],num[4],num[5])

可看出腐蚀操作使得线条变细直至消失

9.2.2膨胀

img=cv2.imread('dige.png',0)
kernel = np.ones((3,3),np.uint8) 
num=[[]]*6
for i in range(6):
    num[i] = cv2.dilate(img,kernel,iterations = i)
plt_show(num[0],num[1],num[2],num[3],num[4],num[5])

可看出线条不断变粗

9.3开操作和闭操作

• 开运算：先腐蚀，后膨胀
• 闭运算：先膨胀，后腐蚀

kernel = np.ones((5,5),np.uint8) 
opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)
closing = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel)
plt_show(img,opening,closing)

9.5一些基本形态学方法

9.3.1边界提取

$$\beta \left(A\right)=A-\left(A\ominus B\right)$$

# 原图-腐蚀
a=cv2.imread('am.png',0)
kernel = np.ones((3,3),np.uint8) 
a2=cv2.erode(a,kernel,iterations = 1)
plt_show(a,a2,a-a2)

9.6灰度级形态学

9.6.3一些基本的形态学算法

形态学梯度：膨胀-腐蚀

img=cv2.imread('am.png',0)
kernel = np.ones((3,3),np.uint8) 
dilate = cv2.dilate(img,kernel,iterations = 1)
erosion = cv2.erode(img,kernel,iterations = 1)
img2=dilate-erosion
plt_show(img,dilate,erosion,img2)

上图中，(膨胀-腐蚀)可得出梯度（最后一幅图）

礼帽与黑帽

• 礼帽 = 原始输入-开运算结果(取’刺’)
• 黑帽 = 闭运算-原始输入(取’整体’)

img = cv2.imread('dige.png')
tophat = cv2.morphologyEx(img, cv2.MORPH_TOPHAT, np.ones((7,7),np.uint8) )
blackhat  = cv2.morphologyEx(img,cv2.MORPH_BLACKHAT, np.ones((15,15),np.uint8) )
plt_show(img,tophat,blackhat)