Python+OpenCV之形态学操作详解

一、 腐蚀与膨胀

1.1 腐蚀操作

import cv2
import numpy as np

img = cv2.imread('DataPreprocessing/img/dige.png')

cv2.imshow("img", img)
cv2.waitKey(0)
cv2.destroyAllWindows()

dige.png原图1展示(注: 没有原图的可以截图下来保存本地。):

腐蚀1轮次之后~ (iterations = 1)

kernel = np.ones((3, 3), np.uint8)
erosion = cv2.erode(img, kernel, iterations=1)

cv2.imshow('erosion', erosion)
cv2.waitKey(0)
cv2.destroyAllWindows()

腐蚀结果展示图2：

腐蚀圆多次的效果，以及腐蚀原理

pie = cv2.imread('DataPreprocessing/img/pie.png')

cv2.imshow('pie', pie)
cv2.waitKey(0)
cv2.destroyAllWindows()

pie.png原图3:

腐蚀原理, 其中滤波器的大小越大腐蚀的程度越大 图4:

kernel = np.ones((30, 30), np.uint8)
erosion_1 = cv2.erode(pie, kernel, iterations=1)
erosion_2 = cv2.erode(pie, kernel, iterations=2)
erosion_3 = cv2.erode(pie, kernel, iterations=3)
res = np.hstack((erosion_1, erosion_2, erosion_3))
cv2.imshow('res', res)
cv2.waitKey(0)
cv2.destroyAllWindows()

圆腐蚀三次结果展示图5:

1.2 膨胀操作

kernel = np.ones((3, 3), np.uint8)
dige_dilate = erosion
dige_dilate = cv2.dilate(erosion, kernel, iterations=1)

cv2.imshow('dilate', dige_dilate)
cv2.waitKey(0)
cv2.destroyAllWindows()

膨胀之前图2,发现线条变粗，跟原图对比的线条相差无几，但是没了那些长须装的噪音，图6:

膨胀圆多次的效果，以及膨胀原理与腐蚀相反，有白色点的滤波器则滤波器内数据全变为白色。

pie = cv2.imread('DataPreprocessing/img/pie.png')

kernel = np.ones((30, 30), np.uint8)
dilate_1 = cv2.dilate(pie, kernel, iterations=1)
dilate_2 = cv2.dilate(pie, kernel, iterations=2)
dilate_3 = cv2.dilate(pie, kernel, iterations=3)
res = np.hstack((dilate_1, dilate_2, dilate_3))
cv2.imshow('res', res)
cv2.waitKey(0)
cv2.destroyAllWindows()

膨胀圆3次的结果展示,图7:

二、 开运算与闭运算

2.1 开运算

# 开：先腐蚀，再膨胀
img = cv2.imread('DataPreprocessing/img/dige.png')

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

cv2.imshow('opening', opening)
cv2.waitKey(0)
cv2.destroyAllWindows()

将原图1，先腐蚀，再膨胀，得到开运算结果图8:

2.2 闭运算

# 闭：先膨胀，再腐蚀
img = cv2.imread('DataPreprocessing/img/dige.png')

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

cv2.imshow('closing', closing)
cv2.waitKey(0)
cv2.destroyAllWindows()

将原图1，先膨胀，再腐蚀，得到开运算结果图9:

三、梯度运算

拿原图3的圆，做5次膨胀，5次腐蚀，相减得到其轮廓。

# 梯度=膨胀-腐蚀
pie = cv2.imread('DataPreprocessing/img/pie.png')
kernel = np.ones((7, 7), np.uint8)
dilate = cv2.dilate(pie, kernel, iterations=5)
erosion = cv2.erode(pie, kernel, iterations=5)

res = np.hstack((dilate, erosion))

cv2.imshow('res', res)
cv2.waitKey(0)
cv2.destroyAllWindows()

gradient = cv2.morphologyEx(pie, cv2.MORPH_GRADIENT, kernel)

cv2.imshow('gradient', gradient)
cv2.waitKey(0)
cv2.destroyAllWindows()

得到梯度运算结果图10:

四、礼帽与黑帽

4.1 礼帽

礼帽 = 原始输入-开运算结果

# 礼帽
img = cv2.imread('DataPreprocessing/img/dige.png')
tophat = cv2.morphologyEx(img, cv2.MORPH_TOPHAT, kernel)
cv2.imshow('tophat', tophat)
cv2.waitKey(0)
cv2.destroyAllWindows()

得到礼帽结果图11:

4.2 黑帽

黑帽 = 闭运算-原始输入

# 黑帽
img = cv2.imread('DataPreprocessing/img/dige.png')
blackhat = cv2.morphologyEx(img, cv2.MORPH_BLACKHAT, kernel)
cv2.imshow('blackhat ', blackhat)
cv2.waitKey(0)
cv2.destroyAllWindows()

得到礼帽结果图12:

来源：https://blog.csdn.net/qq_37700257/article/details/127039846