Прямоугольная кластеризация

Вы ищете что-то вроде этого

from PIL import Image, ImageDraw
import matplotlib.pyplot as plt
import numpy as np
from sklearn.cluster import KMeans

width = 1024
height = 768
im = Image.new('RGBA', (width, height), (255, 255, 255))
draw = ImageDraw.Draw(im)

im2 = Image.new('RGBA', (width, height), (255, 255, 255))
draw2 = ImageDraw.Draw(im2)

im3 = Image.new('RGBA', (width, height), (255, 255, 255))
draw3 = ImageDraw.Draw(im3)

im4 = Image.new('RGBA', (width, height), (255, 255, 255))
draw4 = ImageDraw.Draw(im4)


coords = [[392, 0, 441, 62], [889, 106, 958, 146], [144, 215, 184, 299], [224, 44, 288, 62], [219, 243, 243, 277], [760, 450, 847, 547], [390, 311, 399, 351], [439, 232, 520, 274], [72, 438, 129, 506], [64, 177, 151, 207], [758, 160, 828, 228], [310, 543, 314, 587], [300, 215, 310, 271], [787, 310, 850, 332], [63, 198, 86, 276], [372, 432, 409, 448], [235, 121, 302, 217], [140, 614, 216, 643], [160, 203, 168, 244], [364, 645, 394, 708], [294, 219, 299, 294], [101, 215, 119, 251], [776, 65, 792, 151], [421, 608, 447, 659], [127, 183, 189, 196], [350, 114, 439, 140], [134, 600, 207, 686], [55, 126, 148, 224], [159, 130, 239, 219], [705, 114, 743, 164], [824, 601, 893, 620], [916, 541, 966, 557], [82, 251, 178, 324], [216, 317, 235, 349], [806, 443, 898, 483], [297, 618, 320, 659], [887, 213, 929, 256], [17, 117, 109, 182], [755, 233, 818, 287], [165, 392, 215, 463], [202, 256, 248, 308], [61, 499, 103, 595], [163, 182, 200, 268], [167, 143, 257, 243], [3, 468, 99, 549], [126, 51, 129, 112], [24, 63, 113, 67], [830, 555, 924, 585], [881, 297, 918, 356], [917, 226, 998, 295], [59, 148, 59, 156], [56, 16, 82, 113]]

centers = []

for coord in coords:
    x1, y1, x2, y2 = coord
    draw.rectangle((x1, y1, x2, y2), fill=(192, 192, 192), outline=(122, 122, 122))
    draw = ImageDraw.Draw(im)
    c = [(x1+x2)/2, (y1+y2)/2]
    centers.append(c)
    draw2.point((c[0], c[1]), fill = 0)
    draw2.ellipse((c[0]-2, c[1]-2, c[0]+2, c[1]+2), outline=(255, 0 , 0))

im.save('./1.png',)
im2.save('./2.png',)

x = np.array(centers)

kmeans = KMeans(n_clusters=3)
kmeans.fit(x)

print(kmeans.cluster_centers_)

print(kmeans.labels_)

for c,label, cord in zip(centers, kmeans.labels_, coords):
    draw3.point((c[0], c[1]), fill = 0)
    if label==0:
        draw3.ellipse((c[0]-5, c[1]-5, c[0]+5, c[1]+5), outline=(255, 0 , 0))
        draw4.rectangle((cord[0], cord[1], cord[2], cord[3]), fill=(255, 0, 0), outline=(122, 122, 122))
    elif label==1:
        draw3.ellipse((c[0]-5, c[1]-5, c[0]+5, c[1]+5), outline=(0, 255 , 0))
        draw4.rectangle((cord[0], cord[1], cord[2], cord[3]), fill=(0, 255, 0), outline=(122, 122, 122))
    else:
        draw3.ellipse((c[0]-5, c[1]-5, c[0]+5, c[1]+5), outline=(0, 0 , 255))
        draw4.rectangle((cord[0], cord[1], cord[2], cord[3]), fill=(0, 0, 255), outline=(122, 122, 122))

im3.save("./3.png")
im4.save("./4.png")

Я нашел центральную точку прямоугольников и использовал центры в качестве позиций прямоугольников, а затем kmeans, чтобы сгруппировать их, используя то же самое, что вы даже можете раскрасить прямоугольники.

В kmeans вы можете установить количество создаваемых кластеров.

Он также содержит код для изображений представления центральной точки, которые также не прикреплены.

[Обновление] Добавлена ​​оценка силуэта в качестве метрики для оптимизации количества кластеров

Я добавил расчет Silhouette Score, он будет работать с несколькими номерами кластеров и даст значение от 0 до 1, описывающее, насколько хорошо различаются наши кластеры.

import numpy as np
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score

coords = [[392, 0, 441, 62], [889, 106, 958, 146], [144, 215, 184, 299], [224, 44, 288, 62], [219, 243, 243, 277], [760, 450, 847, 547], [390, 311, 399, 351], [439, 232, 520, 274], [72, 438, 129, 506], [64, 177, 151, 207], [758, 160, 828, 228], [310, 543, 314, 587], [300, 215, 310, 271], [787, 310, 850, 332], [63, 198, 86, 276], [372, 432, 409, 448], [235, 121, 302, 217], [140, 614, 216, 643], [160, 203, 168, 244], [364, 645, 394, 708], [294, 219, 299, 294], [101, 215, 119, 251], [776, 65, 792, 151], [421, 608, 447, 659], [127, 183, 189, 196], [350, 114, 439, 140], [134, 600, 207, 686], [55, 126, 148, 224], [159, 130, 239, 219], [705, 114, 743, 164], [824, 601, 893, 620], [916, 541, 966, 557], [82, 251, 178, 324], [216, 317, 235, 349], [806, 443, 898, 483], [297, 618, 320, 659], [887, 213, 929, 256], [17, 117, 109, 182], [755, 233, 818, 287], [165, 392, 215, 463], [202, 256, 248, 308], [61, 499, 103, 595], [163, 182, 200, 268], [167, 143, 257, 243], [3, 468, 99, 549], [126, 51, 129, 112], [24, 63, 113, 67], [830, 555, 924, 585], [881, 297, 918, 356], [917, 226, 998, 295], [59, 148, 59, 156], [56, 16, 82, 113]]
centers = []

for coord in coords:
    x1, y1, x2, y2 = coord
    c = [(x1+x2)/2, (y1+y2)/2]
    centers.append(c)

# Vector with center coordinates
x = np.array(centers)

bestScore = -1
idx=-1

for i in range (2, 10):
    kmeans = KMeans(n_clusters=i, random_state=10)
    kmeans.fit(x)
    silhouette_avg = silhouette_score(x, kmeans.labels_)
    print("For n_clusters =", i,
          "The average silhouette_score is :", silhouette_avg)
    if silhouette_avg > bestScore:
        bestScore=silhouette_avg
        idx=i

print("Best score :", bestScore, " Number Of Clusters:", idx)

Выход:

For n_clusters = 2 The average silhouette_score is : 0.5998398985890973
For n_clusters = 3 The average silhouette_score is : 0.5537982490021037
For n_clusters = 4 The average silhouette_score is : 0.533919415288406
For n_clusters = 5 The average silhouette_score is : 0.460641507207192
For n_clusters = 6 The average silhouette_score is : 0.4685516097102802
For n_clusters = 7 The average silhouette_score is : 0.42313268667935106
For n_clusters = 8 The average silhouette_score is : 0.43283812579237735
For n_clusters = 9 The average silhouette_score is : 0.41602365463779123
Best score : 0.5998398985890973  Number Of Clusters: 2