import networkx as nx
import matplotlib.pyplot as plt

n_clique, n_path = 10, 10
clique1 = nx.complete_graph(n_clique)
clique1_pos = nx.circular_layout(clique1)
clique2 = nx.complete_graph(n_clique)
clique2_mapping = {node: node + n_clique for node in clique2}
nx.relabel_nodes(clique2, clique2_mapping, copy=False) # avoids repeated nodes
x_diff, y_diff = 8, -1
clique2_pos = {node: clique1_pos[node-n_clique] + (x_diff, y_diff) for node in clique2}
path = nx.path_graph(n_path)
path_mapping = {node: node + 2 * n_clique for node in path}
nx.relabel_nodes(path, path_mapping, copy=False) # avoids repeated nodes
path_nodes = list(path.nodes)
path_half1_nodes = path_nodes[:n_path//2]
path_half2_nodes = path_nodes[n_path//2:]
path_dist = 0.9
clique2_entry = n_clique + n_clique // 2
path_half1_pos = {node: clique1_pos[0] + (path_dist + i * path_dist, 0) for i, node in enumerate(path_half1_nodes)}
path_half2_pos = {node: clique2_pos[clique2_entry] - (path_dist + i * path_dist, 0) for i, node in enumerate(path_half2_nodes[::-1])}
path_pos = {**path_half1_pos, **path_half2_pos}
barbell = nx.Graph()
barbell.add_edges_from(clique1.edges)
barbell.add_edges_from(clique2.edges)
barbell.add_edges_from(path.edges)
barbell.add_edges_from([(path_half1_nodes[0], 0), (path_half2_nodes[-1], clique2_entry)])
clique_pos = {**clique1_pos, **clique2_pos}
barbell_pos = {**clique_pos, **path_pos}
plt.figure(figsize=(20, 6))
nx.draw(barbell, pos=barbell_pos, with_labels=True)

import cv2
import numpy as np

# Input image
img = cv2.imread('cut.jpeg', cv2.IMREAD_GRAYSCALE)

# Needed due to JPG artifacts
_, temp = cv2.threshold(img, 128, 255, cv2.THRESH_BINARY)

# Dilate to better detect contours
temp = cv2.dilate(temp, cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3)))

# Find largest contour
_, cnts, _ = cv2.findContours(temp, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
largestCnt = []
for cnt in cnts:
    if len(cnt) > len(largestCnt):
        largestCnt = cnt

# Determine center of area of largest contour
M = cv2.moments(largestCnt)
x = int(M["m10"] / M["m00"])
y = int(M["m01"] / M["m00"])

# Initiale mask for flood filling
width, height = temp.shape
mask = img2 = np.ones((width + 2, height + 2), np.uint8) * 255
mask[1:width, 1:height] = 0

# Generate intermediate image, draw largest contour, flood filled
temp = np.zeros(temp.shape, np.uint8)
temp = cv2.drawContours(temp, largestCnt, -1, 255, cv2.FILLED)
_, temp, mask, _ = cv2.floodFill(temp, mask, (x, y), 255)
temp = cv2.morphologyEx(temp, cv2.MORPH_OPEN, cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3)))

# Count pixels in desired region
area = cv2.countNonZero(temp)

# Put result on original image
img = cv2.putText(img, str(area), (x, y), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, 255)

cv2.imshow('Input', img)
cv2.imshow('Temp image', temp)

cv2.waitKey(0)

{% endcodeblock %}

最后我们可以得到一个比较准确的轮廓：

面积如图中所示：

参考：
https://stackoverflow.com/questions/55467031/how-to-get-the-area-of-the-contours