如何使用随机森林与python进行图像分割

Question

我目前开始从事一个对图像类别进行分类的研究项目。研究的第一部分是使用随机森林算法进行图像分割。我在用这种算法分割图像时遇到了巨大的困难。有人可以帮助我了解如何使用 随机森林 算法使用 Python 分割图像吗？

我已经尝试过使用 K-means 聚类。但我需要随机森林的方式来做到这一点。

---

import time

import numpy as np
import scipy as sp
import matplotlib.pyplot as plt

from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_extraction import image
from sklearn.cluster import spectral_clustering
from sklearn.utils.testing import SkipTest
from sklearn.utils.fixes import sp_version

if sp_version < (0, 12):
    raise SkipTest("Skipping because SciPy version earlier than 0.12.0 and "
                   "thus does not include the scipy.misc.face() image.")


# load the raccoon face as a numpy array
try:
    face = sp.face(gray=True)  
except AttributeError:
    # Newer versions of scipy have face in misc
    from scipy import misc
    face = misc.face(gray=True)

# Resize it to 10% of the original size to speed up the processing
face = sp.misc.imresize(face, 0.10) / 255.

rm = RandomForestClassifier

# Convert the image into a graph with the value of the gradient on the
# edges.
graph = image.img_to_graph(face)

# Take a decreasing function of the gradient: an exponential
# The smaller beta is, the more independent the segmentation is of the
# actual image. For beta=1, the segmentation is close to a voronoi
beta = 5
eps = 1e-6
graph.data = np.exp(-beta * graph.data / graph.data.std()) + eps

# Apply spectral clustering (this step goes much faster if you have pyamg
# installed)
N_REGIONS = 25

#############################################################################
# Visualize the resulting regions

for assign_labels in ('kmeans', 'discretize'):
    t0 = time.time()
    labels = spectral_clustering(graph, n_clusters=N_REGIONS,
                                 assign_labels=assign_labels, random_state=1)
    t1 = time.time()
    labels = labels.reshape(face.shape)

    plt.figure(figsize=(5, 5))
    plt.imshow(face, cmap=plt.cm.gray)
    for l in range(N_REGIONS):
        plt.contour(labels == l, contours=1,
                    colors=[plt.cm.spectral(l / float(N_REGIONS))])

    plt.xticks(())
    plt.yticks(())
    title = 'Spectral clustering: %s, %.2fs' % (assign_labels, (t1 - t0))
    print(title)
    plt.title(title)
plt.show()

Answer 1

这是python中的随机森林实现。

如果您需要它进行图像分割，我建议您使用 ITKsnap，监督学习，使用随机森林并在 python 中实现的分割包。 这很容易，您可以插入或定义标签并训练数据。您可以调整您的学习参数，例如树的数量或深度。 这是分割如何对大脑数据起作用的示例：

import numpy as np
import csv as csv
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.cross_validation import StratifiedKFold # Add important libs

# Training:
train=[]
test=[]         #Array Definition
path1 =  r'D:\random forest\data set\train.csv'     #Address Definition
path2 =  r'D:\random forest\data set\test.csv'
with open(path1, 'r') as f1:    #Open File as read by 'r'
    reader = csv.reader(f1)     
    next(reader, None)          #Skip header because file header is not needed
    for row in reader:          #fill array by file info by for loop
        train.append(row)
    train = np.array(train)         

with open(path2, 'r') as f2:
    reader2 = csv.reader(f2)
    next(reader2, None)  
    for row2 in  reader2:
        test.append(row2)
    test = np.array(test)

train = np.delete(train,[0],1) 
test = np.delete(test,[0],1)


# Optimization
parameter_gridsearch = {
                 'max_depth' : [3, 4],  #depth of each decision tree
                 'n_estimators': [50, 20],  #count of decision tree
                 'max_features': ['sqrt', 'auto', 'log2'],      
                 'min_samples_split': [2],      
                 'min_samples_leaf': [1, 3, 4],
                 'bootstrap': [True, False],
                 }
# RF classification

randomForestClassifier()
crossvalidation = StratifiedKFold(train[0::,0] , n_folds=5)

gridsearch = GridSearchCV(randomforest,             #grid search for algorithm optimization
                               scoring='accuracy',
                               param_grid=parameter_gridsearch,
                               cv=crossvalidation)


gridsearch.fit(train[0::,1::], train[0::,0])    #train[0::,0] is as target
model = gridsearch
parameters = gridsearch.best_params_