OpenCV图像处理|OpenCV for Python之图像的开闭操作、顶帽黑帽、形态学梯度 OpenCV|顶帽黑帽|OpenCV形态学梯度

OpenCV for Python之图像的开闭操作

1 开闭操作
2 顶帽黑帽
3 形态学梯度

Opencv4 官方文档 : https://docs.opencv.org/4.2.0/
Opencv4 for Python中文文档点击下载:OpenCV4 for Python 中文文档
1 开闭操作

开运算:先腐蚀再膨胀.就叫做开运算,它被用来去除噪声。
闭运算:先膨胀再腐蚀。它经常被用来填充前景物体中的小洞，或者前景物体上的小黑点。
api:

cv.morphologyEx(src, op, kernel, dst=None, anchor=None, iterations=None, borderType=None, borderValue=https://www.it610.com/article/None)

开操作：
demo1：

def open_demo(image): print(image.shape) gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY) ret, binary = cv.threshold(gray, 0, 255, cv.THRESH_BINARY | cv.THRESH_OTSU) cv.imshow("binary", binary) kernel = cv.getStructuringElement(cv.MORPH_RECT, (5, 5)) dst = cv.morphologyEx(binary, cv.MORPH_OPEN, kernel=kernel) cv.imshow("open_demo", dst)

result1:

OpenCV图像处理|OpenCV for Python之图像的开闭操作、顶帽黑帽、形态学梯度

文章图片

demo2:

def open_line(image): print(image.shape) gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY) ret, binary = cv.threshold(gray, 0, 255, cv.THRESH_BINARY_INV | cv.THRESH_OTSU) cv.imshow("binary", binary) # kernel = cv.getStructuringElement(cv.MORPH_RECT, (15, 1))#去掉竖线 # kernel = cv.getStructuringElement(cv.MORPH_RECT, (15, 1))#去掉水平线 kernel = cv.getStructuringElement(cv.MORPH_RECT, (3, 3))#去掉背景干扰线 dst = cv.morphologyEx(binary, cv.MORPH_OPEN, kernel=kernel) cv.imshow("open_line", dst)

result2:

文章图片

闭操作：
demo:

def open_line(image): print(image.shape) gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY) ret, binary = cv.threshold(gray, 0, 255, cv.THRESH_BINARY_INV | cv.THRESH_OTSU) cv.imshow("binary", binary) # kernel = cv.getStructuringElement(cv.MORPH_RECT, (15, 1))#去掉竖线 # kernel = cv.getStructuringElement(cv.MORPH_RECT, (15, 1))#去掉水平线 kernel = cv.getStructuringElement(cv.MORPH_RECT, (3, 3))#去掉背景干扰线 dst = cv.morphologyEx(binary, cv.MORPH_OPEN, kernel=kernel) cv.imshow("open_line", dst)

result:

文章图片

2 顶帽黑帽黑帽:

文章图片

demo:

def black_hat_demo(image): gray=cv.cvtColor(image,cv.COLOR_BGR2GRAY) #构建形态学元素提高内核矩阵(10,10)可以提取更多元素 kernel=cv.getStructuringElement(cv.MORPH_RECT,(10,10)) #黑帽处理 dst=cv.morphologyEx(gray,cv.MORPH_BLACKHAT,kernel)#如果图像较黑可以用图像增强看看效果 cimage=np.array(gray.shape,np.uint8) cimage=50 dst=cv.add(dst,cimage)cv.imshow('black_hat',dst)

result:

文章图片

顶帽:

文章图片
demo:

def top_hat_demo(image): gray=cv.cvtColor(image,cv.COLOR_BGR2GRAY) #构建形态学元素提高内核矩阵(10,10)可以提取更多元素 kernel=cv.getStructuringElement(cv.MORPH_RECT,(10,10)) #黑帽处理 dst=cv.morphologyEx(gray,cv.MORPH_TOPHAT,kernel) #如果图像较黑可以用图像增强看看效果 cimage=np.array(gray.shape,np.uint8) cimage=50 dst=cv.add(dst,cimage) cv.imshow('top_hat',dst)

result:

文章图片

3 形态学梯度就是膨胀图像减去腐蚀图像的结果，,得到图像的轮廓。分为基本梯度，内、外梯度
demo1:基本梯度

def gradient_demo(image):#基本梯度 gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY) ret, binary = cv.threshold(gray, 0, 255, cv.THRESH_BINARY | cv.THRESH_OTSU) kernel = cv.getStructuringElement(cv.MORPH_RECT, (3, 3)) dst = cv.morphologyEx(binary, cv.MORPH_GRADIENT, kernel) cv.imshow("gradient", dst)

result:

文章图片

demo2:内外梯度

def gradient2_demo(image): kernel = cv.getStructuringElement(cv.MORPH_RECT, (3, 3)) dm = cv.dilate(image, kernel) em = cv.erode(image, kernel) dst1 = cv.subtract(image, em) # internal gradient dst2 = cv.subtract(dm, image) # external gradient cv.imshow("internal", dst1) cv.imshow("external", dst2)

result: