腐蚀
通常对二值图片进行腐蚀操作
kernel = np.ones((3, 3), np.uint8) # 定义核
erosion = cv2.erode(img, kernel, iteratoons= )去毛刺、使线条变细

膨胀
腐蚀的逆运算
例子:腐蚀去掉毛刺了,但是让图片线条变细了,这时候再膨胀图片
kernel = np.ones((30, 30), np.uint8)
dilation = cv2.dilate(img, kernel, iterations= )
运算
开运算:先腐蚀再膨胀
kernel = np.ones((3, 3), np.uint8)
opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)E.g. 去毛刺
闭运算:先膨胀再腐蚀
kernel = np.ones((3, 3), np.uint8)
closing = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel)E.g. 补全空缺
梯度运算:膨胀-腐蚀
kernel = np.ones((3, 3), np.uint8)
gradient = cv2.morphologyEx(img, cv2.MORPH_GRADIENT, kernel)
礼帽与黑帽
礼帽:原始输入-开运算
tophat = cv2.morphologyEx(img, cv2.MORPH_TOPHAT, kernel)剩下毛刺

黑帽:闭运算-原始输入
blackhat = cv2.morphologyEx(img, cv2.MORPH_BLACKHAT, kernel)剩下原始轮廓
