图像分割：分水岭分割算法--python实现

直接上代码，原理大家都可以查到

注意：以下img自己加载即可，我是事先把图片转换成了单通道的Array形式，并且我的img是归一化后在0-1的。

import cv2
import numpy as np
import copy
def watershed(img):

    gray = img
    ret0, thresh0 = cv2.threshold(gray,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)

    kernel = np.ones((3,3),np.uint8)
    opening = cv2.morphologyEx(thresh0,cv2.MORPH_OPEN,kernel, iterations = 2)

    # 确定背景区域
    sure_bg = cv2.dilate(opening,kernel,iterations=3)

    # 确定前景区域
    dist_transform = cv2.distanceTransform(opening,cv2.DIST_L2,5)
    ret1, sure_fg = cv2.threshold(dist_transform,0.7*dist_transform.max(),255,0)

    # 查找未知区域
    sure_fg = np.uint8(sure_fg)
    unknown = cv2.subtract(sure_bg,sure_fg)

    # 标记标签
    ret2, markers1 = cv2.connectedComponents(sure_fg)
    markers = markers1+1
    markers[unknown==255] = 0

    markers3 = cv2.watershed(img,markers)
    img[markers3 == -1] = [0,255,0]
    return thresh0,sure_bg,sure_fg,img

imgc = copy.deepcopy(img)
gray = copy.deepcopy(img)
ret, thresh = cv.threshold(gray, 0, 255, cv.THRESH_BINARY_INV + cv.THRESH_OTSU)
# noise removal
kernel = np.ones((3, 3), np.uint8)
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=2)

# sure background area
sure_bg = cv2.dilate(opening, kernel, iterations=3)

# Finding sure foreground area
# 距离变换的基本含义是计算一个图像中非零像素点到最近的零像素点的距离，也就是到零像素点的最短距离
# 最常见的距离变换算法就是通过连续的腐蚀操作来实现，腐蚀操作的停止条件是所有前景像素都被完全
# 腐蚀。这样根据腐蚀的先后顺序，我们就得到各个前景像素点到前景中心骨架像素点的距离。
# 根据各个像素点的距离值，设置为不同的灰度值。这样就完成了二值图像的距离变换
# cv2.distanceTransform(src, distanceType, maskSize)
# 第二个参数 0,1,2 分别表示 CV_DIST_L1, CV_DIST_L2 , CV_DIST_C
dist_transform = cv2.distanceTransform(opening, 1, 5)
ret, sure_fg = cv2.threshold(dist_transform, 0.7 * dist_transform.max(), 255, 0)

# Finding unknown region
sure_fg = np.uint8(sure_fg)
unknown = cv2.subtract(sure_bg, sure_fg)
# Marker labelling
ret, markers = cv.connectedComponents(sure_fg)

# Add one to all labels so that sure background is not 0, but 1
markers = markers + 1

# Now, mark the region of unknown with zero
markers[unknown == 255] = 0

imgc = cv.cvtColor(img, cv.COLOR_GRAY2BGR)
markers = cv.watershed(imgc, markers)

imgc[markers == -1] = [255,0,0]
label = imgc