分水岭算法

分水岭流程.png

import cv2 as cv
import numpy


def watershed_demo():
    # remove noise if any 消除噪声
    print(src.shape)
    # gray, binary image
    blurred = cv.pyrMeanShiftFiltering(src, 10, 100)
    gray = cv.cvtColor(blurred, cv.COLOR_BGR2GRAY)
    ret, binary = cv.threshold(gray, 0, 255, cv.THRESH_BINARY | cv.THRESH_OTSU)
    cv.imshow("binary image", binary)

    # morphology operation 开操作去除噪点
    kernel = cv.getStructuringElement(cv.MORPH_RECT, (3, 3))
    # morphology binary,2次开操作
    mb = cv.morphologyEx(binary, cv.MORPH_OPEN, kernel, iterations=2)
    sure_bg = cv.dilate(mb, kernel, iterations=3)  # 3次膨胀
    cv.imshow("mor-opt", sure_bg)

    # distance transform
    # distance transform
    # DIST_L1:曼哈顿距离，DIST_L2：欧氏距离, masksize:跟卷积一样
    # 这是我们获取的字段距离数值，对应每个像素都有，所以数组结构和图像数组一致
    dist = cv.distanceTransform(mb, cv.DIST_L2, 3)
    dist_output = cv.normalize(dist, 0, 1.0, cv.NORM_MINMAX)  # 归一化的距离图像数组 0-1之间标准化
    # cv.imshow("distance-t", dist_output*50)    # 这行代码运行不了

    ret, surface = cv.threshold(dist, dist.max()*0.5, 255, cv.THRESH_BINARY)
    # cv.imshow("surface_bin", surface)   # 个人运行不了
    # 计算marker
    surface_fg = numpy.uint8(surface)  # 计算前景
    unknown = cv.subtract(sure_bg, surface_fg)  # 计算未知区域
    ret, markers = cv.connectedComponents(surface_fg)
    print(ret)

    # watershed transform 分水岭变换
    markers = markers + 1   # 用label进行控制
    markers[unknown == 255] = 0
    markers = cv.watershed(src, markers=markers)  # 分水岭的地方就编程-1
    src[markers == -1] = [0, 0, 255]
    cv.imshow("result_image", src)


src = cv.imread("./data/coins.png", cv.IMREAD_COLOR)
cv.namedWindow("girl", cv.WINDOW_AUTOSIZE)
cv.imshow("girl", src)
watershed_demo()

cv.waitKey(0)
cv.destroyAllWindows()

运行结果

分水岭.png