opencv-机器学习

参考：

1、http://docs.opencv.org/3.3.0/  官方文档api

2、http://docs.opencv.org/3.3.0/d6/d00/tutorial_py_root.html 官方英文教程

3、https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_tutorials.html

4、https://github.com/makelove/OpenCV-Python-Tutorial# 进阶教程

5、https://docs.opencv.org/3.3.0/index.html  官方英文教程

6、https://github.com/abidrahmank/OpenCV2-Python-Tutorials

7、https://www.learnopencv.com/

8、http://answers.opencv.org/questions/ OpenCV论坛

9、https://github.com/opencv/opencv   官方github

10、https://github.com/abidrahmank/OpenCV2-Python-Tutorials

注：安装的版本 opencv_python-3.3.0-cp36-cp36m-win_amd64.whl

参考：https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_tutorials.html

K-Nearest Neighbour

Understanding k-Nearest Neighbour

kNN in OpenCV

我们将在这里做一个简单的例子，有两个家庭（类），就像上面一样。 然后在下一章中，我们将做更多更好的例子。

所以在这里，我们将Red系列标记为Class-0（由0表示）和Blue系列作为Class 1（由1表示）。 我们创建25个类别或25个训练数据，并将其标记为class-0或class-1。 我们在Numpy的随机数生成器的帮助下完成所有这些。

然后我们在Matplotlib的帮助下绘制它。 红色类别显示为红色三角形，蓝色类别显示为蓝色正方形。

import cv2
import numpy as np
import matplotlib.pyplot as plt

# Feature set containing (x,y) values of 25 known/training data
trainData = np.random.randint(0,100,(25,2)).astype(np.float32)

# Labels each one either Red or Blue with numbers 0 and 1
responses = np.random.randint(0,2,(25,1)).astype(np.float32)

# Take Red families and plot them
red = trainData[responses.ravel()==0]
plt.scatter(red[:,0],red[:,1],80,'r','^')

# Take Blue families and plot them
blue = trainData[responses.ravel()==1]
plt.scatter(blue[:,0],blue[:,1],80,'b','s')

plt.show()

import cv2
import numpy as np
import matplotlib.pyplot as plt

newcomer = np.random.randint(0,100,(1,2)).astype(np.float32)
plt.scatter(newcomer[:,0],newcomer[:,1],80,'g','o')

knn = cv2.KNearest()
knn.train(trainData,responses)
ret, results, neighbours ,dist = knn.find_nearest(newcomer, 3)

print ("result: ", results,"\n")
print ("neighbours: ", neighbours,"\n")
print ("distance: ", dist)

plt.show()

使用kNN的手写数据的OCR

手写数字的OCR

import numpy as np
import cv2
from matplotlib import pyplot as plt

img = cv2.imread('digits.png')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

# Now we split the image to 5000 cells, each 20x20 size
cells = [np.hsplit(row,100) for row in np.vsplit(gray,50)]

# Make it into a Numpy array. It size will be (50,100,20,20)
x = np.array(cells)

# Now we prepare train_data and test_data.
train = x[:,:50].reshape(-1,400).astype(np.float32) # Size = (2500,400)
test = x[:,50:100].reshape(-1,400).astype(np.float32) # Size = (2500,400)

# Create labels for train and test data
k = np.arange(10)
train_labels = np.repeat(k,250)[:,np.newaxis]
test_labels = train_labels.copy()

# Initiate kNN, train the data, then test it with test data for k=1
knn = cv2.KNearest()
knn.train(train,train_labels)
ret,result,neighbours,dist = knn.find_nearest(test,k=5)

# Now we check the accuracy of classification
# For that, compare the result with test_labels and check which are wrong
matches = result==test_labels
correct = np.count_nonzero(matches)
accuracy = correct*100.0/result.size
print accuracy

# save the data
np.savez('knn_data.npz',train=train, train_labels=train_labels)

# Now load the data
with np.load('knn_data.npz') as data:
    print data.files
    train = data['train']
    train_labels = data['train_labels']

英文字母OCR

import cv2
import numpy as np
import matplotlib.pyplot as plt

# Load the data, converters convert the letter to a number
data= np.loadtxt('letter-recognition.data', dtype= 'float32', delimiter = ',',
                    converters= {
   0: lambda ch: ord(ch)-ord('A')})

# split the data to two, 10000 each for train and test
train, test = np.vsplit(data,2)

# split trainData and testData to features and responses
responses, trainData = np.hsplit(train,[1])
labels, testData = np.hsplit(test,[1])

# Initiate the kNN, classify, measure accuracy.
knn = cv2.KNearest()
knn.train(trainData, responses)
ret, result, neighbours, dist = knn.find_nearest(testData, k=5)

correct = np.count_nonzero(result == labels)
accuracy = correct*100.0/10000
print accuracy

Support Vector Machines (SVM)

使用SVM的手写数据的OCR

手写数字的OCR

这里，在找到HOG之前，我们会用其二阶时间去掉图像。 因此，我们首先定义一个可以使用数字图像并进行deskew()的函数。 以下是deskew()函数：

def deskew(img):
    m = cv2.moments(img)
    if abs(m['mu02']) < 1e-2:
        return img.copy()
    skew = m['mu11']/m['mu02']
    M = np.float32([[1, skew, -0.5*SZ*skew], [0, 1, 0]])
    img = cv2.warpAffine(img,M,(SZ, SZ),flags=affine_flags)
    return img

def hog(img):
    gx = cv2.Sobel(img, cv2.CV_32F, 1, 0)
    gy = cv2.Sobel(img, cv2.CV_32F, 0, 1)
    mag, ang = cv2.cartToPolar(gx, gy)

    # quantizing binvalues in (0...16)
    bins = np.int32(bin_n*ang/(2*np.pi))

    # Divide to 4 sub-squares
    bin_cells = bins[:10,:10], bins[10:,:10], bins[:10,10:], bins[10:,10:]
    mag_cells = mag[:10,:10], mag[10:,:10], mag[:10,10:], mag[10:,10:]
    hists = [np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells)]
    hist = np.hstack(hists)
    return hist

最后，像以前的情况一样，我们首先将我们的大数据集分成单独的单元格。 对于每个数字，250个单元被保留用于训练数据，剩余的250个数据被保留用于测试。 完整代码如下：

import cv2
import numpy as np

SZ=20
bin_n = 16 # Number of bins

svm_params = dict( kernel_type = cv2.SVM_LINEAR,
                    svm_type = cv2.SVM_C_SVC,
                    C=2.67, gamma=5.383 )

affine_flags = cv2.WARP_INVERSE_MAP|cv2.INTER_LINEAR

def deskew(img):
    m = cv2.moments(img)
    if abs(m['mu02']) < 1e-2:
        return img.copy()
    skew = m['mu11']/m['mu02']
    M = np.float32([[1, skew, -0.5*SZ*skew], [0, 1, 0]])
    img = cv2.warpAffine(img,M,(SZ, SZ),flags=affine_flags)
    return img

def hog(img):
    gx = cv2.Sobel(img, cv2.CV_32F, 1, 0)
    gy = cv2.Sobel(img, cv2.CV_32F, 0, 1)
    mag, ang = cv2.cartToPolar(gx, gy)
    bins = np.int32(bin_n*ang/(2*np.pi))    # quantizing binvalues in (0...16)
    bin_cells = bins[:10,:10], bins[10:,:10], bins[:10,10:], bins[10:,10:]
    mag_cells = mag[:10,:10], mag[10:,:10], mag[:10,10:], mag[10:,10:]
    hists = [np.bincount(b.ravel(), m.ravel(), bin_n) for b, m in zip(bin_cells, mag_cells)]
    hist = np.hstack(hists)     # hist is a 64 bit vector
    return hist

img = cv2.imread('digits.png',0)

cells = [np.hsplit(row,100) for row in np.vsplit(img,50)]

# First half is trainData, remaining is testData
train_cells = [ i[:50] for i in cells ]
test_cells = [ i[50:] for i in cells]

######     Now training      ########################

deskewed = [map(deskew,row) for row in train_cells]
hogdata = [map(hog,row) for row in deskewed]
trainData = np.float32(hogdata).reshape(-1,64)
responses = np.float32(np.repeat(np.arange(10),250)[:,np.newaxis])

svm = cv2.SVM()
svm.train(trainData,responses, params=svm_params)
svm.save('svm_data.dat')

######     Now testing      ########################

deskewed = [map(deskew,row) for row in test_cells]
hogdata = [map(hog,row) for row in deskewed]
testData = np.float32(hogdata).reshape(-1,bin_n*4)
result = svm.predict_all(testData)

#######   Check Accuracy   ########################
mask = result==responses
correct = np.count_nonzero(mask)
print correct*100.0/result.size

K均值聚类

K-Means Clustering in OpenCV

1. 只有一个特征的数据

import numpy as np
import cv2
from matplotlib import pyplot as plt

x = np.random.randint(25,100,25)
y = np.random.randint(175,255,25)
z = np.hstack((x,y))
z = z.reshape((50,1))
z = np.float32(z)
plt.hist(z,256,[0,256]),plt.show()

# Define criteria = ( type, max_iter = 10 , epsilon = 1.0 )
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)

# Set flags (Just to avoid line break in the code)
flags = cv2.KMEANS_RANDOM_CENTERS

# Apply KMeans
compactness,labels,centers = cv2.kmeans(z,2,None,criteria,10,flags)

A = z[labels==0]
B = z[labels==1]

# Now plot 'A' in red, 'B' in blue, 'centers' in yellow
plt.hist(A,256,[0,256],color = 'r')
plt.hist(B,256,[0,256],color = 'b')
plt.hist(centers,32,[0,256],color = 'y')
plt.show()

2. 多个特征的数据

import numpy as np
import cv2
from matplotlib import pyplot as plt

X = np.random.randint(25,50,(25,2))
Y = np.random.randint(60,85,(25,2))
Z = np.vstack((X,Y))

# convert to np.float32
Z = np.float32(Z)

# define criteria and apply kmeans()
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)
ret,label,center=cv2.kmeans(Z,2,None,criteria,10,cv2.KMEANS_RANDOM_CENTERS)

# Now separate the data, Note the flatten()
A = Z[label.ravel()==0]
B = Z[label.ravel()==1]

# Plot the data
plt.scatter(A[:,0],A[:,1])
plt.scatter(B[:,0],B[:,1],c = 'r')
plt.scatter(center[:,0],center[:,1],s = 80,c = 'y', marker = 's')
plt.xlabel('Height'),plt.ylabel('Weight')
plt.show()

3. 颜色量化

import numpy as np
import cv2

img = cv2.imread('home.jpg')
Z = img.reshape((-1,3))

# convert to np.float32
Z = np.float32(Z)

# define criteria, number of clusters(K) and apply kmeans()
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)
K = 8
ret,label,center=cv2.kmeans(Z,K,None,criteria,10,cv2.KMEANS_RANDOM_CENTERS)

# Now convert back into uint8, and make original image
center = np.uint8(center)
res = center[label.flatten()]
res2 = res.reshape((img.shape))

cv2.imshow('res2',res2)
cv2.waitKey(0)
cv2.destroyAllWindows()