Python中的最大似然像素分类opencv

Question

我想根据给定数量的类的输入训练样本对RGB图像执行像素分类。所以我有4个类包含像素（r，g，b），因此目标是将图像分为四个阶段。

我发现python opencv2具有可以完成这项工作的期望最大化算法。但不幸的是，我没有找到任何教程或材料可以解释我（因为我是初学者）如何使用该算法。

你能否提出任何一种可以作为出发点的教程？

更新...的另一种方法为以下代码：

**def getsamples(img): 
    x, y, z = img.shape 
    samples = np.empty([x * y, z]) 
    index = 0 
    for i in range(x): 
     for j in range(y): 
      samples[index] = img[i, j] 
      index += 1 
    return samples 
def EMSegmentation(img, no_of_clusters=2): 
    output = img.copy() 
    colors = np.array([[0, 11, 111], [22, 22, 22]]) 
    samples = getsamples(img) 
    #em = cv2.ml.EM_create() 
    em = cv2.EM(no_of_clusters) 
    #em.setClustersNumber(no_of_clusters) 
    #em.trainEM(samples) 
    em.train(samples) 
    x, y, z = img.shape 
    index = 0 
    for i in range(x): 
     for j in range(y): 

      result = em.predict(samples[index])[0][1] 
      #print(result) 
      output[i][j] = colors[result] 
      index = index + 1 
    return output 
img = cv2.imread('00.jpg') 
smallImg = small = cv2.resize(img, (0,0), fx=0.5, fy=0.5) 
output = EMSegmentation(img) 
smallOutput = cv2.resize(output, (0,0), fx=0.5, fy=0.5) 
cv2.imshow('image', smallImg) 
cv2.imshow('EM', smallOutput) 
cv2.waitKey(0) 
cv2.destroyAllWindows()** 

Answer 1

转换C++到Python source

import cv2 
import numpy as np 


def getsamples(img): 
    x, y, z = img.shape 
    samples = np.empty([x * y, z]) 
    index = 0 
    for i in range(x): 
     for j in range(y): 
      samples[index] = img[i, j] 
      index += 1 
    return samples 


def EMSegmentation(img, no_of_clusters=2): 
    output = img.copy() 
    colors = np.array([[0, 11, 111], [22, 22, 22]]) 
    samples = getsamples(img) 
    em = cv2.ml.EM_create() 
    em.setClustersNumber(no_of_clusters) 
    em.trainEM(samples) 
    means = em.getMeans() 
    covs = em.getCovs() # Known bug: https://github.com/opencv/opencv/pull/4232 
    x, y, z = img.shape 
    distance = [0] * no_of_clusters 
    for i in range(x): 
     for j in range(y): 
      for k in range(no_of_clusters): 
       diff = img[i, j] - means[k] 
       distance[k] = abs(np.dot(np.dot(diff, covs[k]), diff.T)) 
      output[i][j] = colors[distance.index(max(distance))] 
    return output 


img = cv2.imread('dinosaur.jpg') 
output = EMSegmentation(img) 
cv2.imshow('image', img) 
cv2.imshow('EM', output) 
cv2.waitKey(0) 
cv2.destroyAllWindows()