视觉/图像重磅干货，第一时间送达
下面实例核心步骤或者算法：
- 二值化 形态学预处理
- 距离变换
- 分水岭算法
实例一：硬币分割计数
上代码：
代码语言：javascript复制# import the necessary packages
from skimage.feature import peak_local_max
from skimage.morphology import watershed
from scipy import ndimage
import numpy as np
import argparse
import imutils
import cv2
# load the image and perform pyramid mean shift filtering
# to aid the thresholding step
image = cv2.imread("1.jpg")
shifted = cv2.pyrMeanShiftFiltering(image, 21, 51)
cv2.imshow("Input", image)
# convert the mean shift image to grayscale, then apply
# Otsu's thresholding
gray = cv2.cvtColor(shifted, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
cv2.imshow("Thresh", thresh)
# compute the exact Euclidean distance from every binary
# pixel to the nearest zero pixel, then find peaks in this
# distance map
D = ndimage.distance_transform_edt(thresh)
localMax = peak_local_max(D, indices=False, min_distance=10,
labels=thresh)
# perform a connected component analysis on the local peaks,
# using 8-connectivity, then appy the Watershed algorithm
markers = ndimage.label(localMax, structure=np.ones((3, 3)))[0]
labels = watershed(-D, markers, mask=thresh)
print("[INFO] {} unique segments found".format(len(np.unique(labels)) - 1))
# loop over the unique labels returned by the Watershed
# algorithm
for label in np.unique(labels):
# if the label is zero, we are examining the 'background'
# so simply ignore it
if label == 0:
continue
# otherwise, allocate memory for the label region and draw
# it on the mask
mask = np.zeros(gray.shape, dtype="uint8")
mask[labels == label] = 255
# detect contours in the mask and grab the largest one
cnts = cv2.findContours(mask.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
c = max(cnts, key=cv2.contourArea)
# draw a circle enclosing the object
((x, y), r) = cv2.minEnclosingCircle(c)
cv2.circle(image, (int(x), int(y)), int(r), (0, 255, 0), 2)
cv2.putText(image, "{}".format(label), (int(x) - 10, int(y)),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
# show the output image
cv2.imshow("Output", image)
cv2.waitKey(0)
cv2.destroyAllWindows()分割计数结果：
实例二：药片分割计数
代码同上，可能参数需略微调整，上效果：
实例三：玉米粒分割计数
上代码：
代码语言：javascript复制import numpy as np
import cv2
from matplotlib import pyplot as plt
font=cv2.FONT_HERSHEY_SIMPLEX
img = cv2.imread('5.jpg')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray,245,255,cv2.THRESH_BINARY)
cv2.imshow("threshold", thresh)
k = cv2.getStructuringElement(cv2.MORPH_RECT,(13,13))
dilate = cv2.dilate(thresh,k,iterations=3)
cv2.imshow("dilate", dilate)
cv2.bitwise_not(dilate, dilate)
dist_transform = cv2.distanceTransform(dilate,cv2.DIST_L2,3)
dist = cv2.normalize(dist_transform,dist_transform,0,1.0,cv2.NORM_MINMAX)
cv2.imshow("distance", dist)
cv2.imwrite("dis.jpg", dist)
#dist = np.uint8(dist)
dist = cv2.convertScaleAbs(dist)
ret2,morph = cv2.threshold(dist,0.99,255,cv2.THRESH_BINARY cv2.THRESH_OTSU)
#ret2, morph = cv2.threshold(dist,0,255,cv2.THRESH_BINARY_INV)
cv2.imshow("morph", morph)
k2 = cv2.getStructuringElement(cv2.MORPH_RECT,(11,5))
sure_fg = cv2.morphologyEx(morph,cv2.MORPH_OPEN,k2, iterations = 1) # 形态开运算
cv2.imshow("result", sure_fg)
thresh,contours,hierarchy = cv2.findContours(sure_fg, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
for i in range(0,len(contours)):
(x, y, w, h) = cv2.boundingRect(contours[i])
#cv2.drawContours(img,contours,i,(0,255,0),5)
cv2.circle(img,(x int(w/2),y int(h/2)),20,(0,0,255),-1, cv2.LINE_AA)
cv2.putText(img,str(i 1),(x int(w/2)-15,y int(h/2) 5),font,0.8,(0,255,0),2)
cv2.imshow('img',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
分割计数效果：
中间执行结果略去，大家可以复制源码和图片自己运行，查看中间结果，简单来做个总结：
- 预处理---基本就是二值化和形态学操作
- 粘连分割---距离变换少不了
- 分水岭算法---根据实际情况使用，有时候分割不太可控，慎用
参考资料：
https://www.pyimagesearch.com/2015/11/02/watershed-opencv/
https://www.itread01.com/content/1545201032.html
