原图像与开运算图的区别(差值),突出原图像中比周围亮的区域
闭操作图像 - 原图像,突出原图像中比周围暗的区域
基础梯度:基础梯度是用膨胀后的图像减去腐蚀后的图像得到差值图像,称为梯度图像也是opencv中支持的计算形态学梯度的方法,而此方法得到梯度有称为基本梯度。
内部梯度:是用原图像减去腐蚀之后的图像得到差值图像,称为图像的内部梯度。
外部梯度:图像膨胀之后再减去原来的图像得到的差值图像,称为图像的外部梯度。
import cv2
import numpy as np
from matplotlib import pyplot as plt
__author__ = "zxsuperstar"
__email__ = "[email protected]"
"""
顶帽、黑帽、形态学梯度
"""
def top_hat_demo(image): #顶帽
cv2.imshow("image", image)
gray = cv2.cvtColor(image, cv2.COLOR_BGRA2GRAY)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
dst = cv2.morphologyEx(gray, cv2.MORPH_TOPHAT, kernel)
# 增加亮度
cimage = np.array(gray.shape, np.uint8)
cimage = 100
dst = cv2.add(dst,cimage)
cv2.imshow("dst", dst)
def black_hat_demo(image): #黑帽
cv2.imshow("image", image)
gray = cv2.cvtColor(image, cv2.COLOR_BGRA2GRAY)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
dst = cv2.morphologyEx(gray, cv2.MORPH_BLACKHAT, kernel)
# 增加亮度
cimage = np.array(gray.shape, np.uint8)
cimage = 100
dst = cv2.add(dst,cimage)
cv2.imshow("dst", dst)
def threshold_top_hat_demo(image):#顶帽 二值图像
cv2.imshow("image", image)
gray = cv2.cvtColor(image, cv2.COLOR_BGRA2GRAY)
ret, binary = cv2.threshold(gray, 0 ,255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
dst = cv2.morphologyEx(binary, cv2.MORPH_TOPHAT, kernel)
cv2.imshow("dst", dst)
def threshold_black_hat_demo(image):#黑帽 二值图像
cv2.imshow("image", image)
gray = cv2.cvtColor(image, cv2.COLOR_BGRA2GRAY)
ret, binary = cv2.threshold(gray, 0 ,255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
dst = cv2.morphologyEx(binary, cv2.MORPH_BLACKHAT, kernel)
cv2.imshow("dst", dst)
def gradient_threshold_hat_demo(image):
cv2.imshow("image", image)
gray = cv2.cvtColor(image, cv2.COLOR_BGRA2GRAY)
ret, binary = cv2.threshold(gray, 0 ,255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
dst = cv2.morphologyEx(binary, cv2.MORPH_GRADIENT, kernel) #基本梯度
cv2.imshow("dst", dst)
def gradients_threshold_hat_demo(image):
cv2.imshow("image", image)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
dm = cv2.dilate(image, kernel)
em = cv2.erode(image, kernel)
dst1 = cv2.subtract(image, em) #内部梯度
dst2 = cv2.subtract(image, dm) # 外部梯度
cv2.imshow("internal", dst1)
cv2.imshow("external", dst2)
if __name__ == "__main__":
image = cv2.imread("slant1.jpg") #blue green red
image = cv2.resize(image, (0, 0), fx=0.5, fy=0.5, interpolation=cv2.INTER_NEAREST)
# top_hat_demo(image)
black_hat_demo(image)
# threshold_top_hat_demo(image)
# threshold_black_hat_demo(image)
# gradient_threshold_hat_demo(image)
# gradients_threshold_hat_demo(image)
cv2.waitKey(0)
cv2.destroyAllWindows()
顶帽 黑帽
cv2.morphologyEx()
看前三个参数就行了,后面的就用默认值
第一个参数 输入
第二个参数 操作类型
MORTH_OPEN 函数做开运算
MORTH_CLOSE 函数做闭运算
MORTH_GRADIENT 函数做形态学梯度运算
MORTH_TOPHAT 函数做顶帽运算
MORTH_BLACKHAT 函数做黑帽运算
MORTH_DILATE 函数做膨胀运算
MORTH_ERODE 函数做腐蚀运算
第三个参数 内核类型 用getStructuringElement函数得到