1 K近邻

1.1 理解K近邻

重要函数

knn = cv.ml.KNearest_create()
knn.train(trainData, cv.ml.ROW_SAMPLE, responses)
ret, results, neighbours ,dist = knn.findNearest(newcomer, 3)

https://docs.opencv.org/3.4/d5/d26/tutorial_py_knn_understanding.html

1.2 例子：使用K近邻对手写数字OCR识别

import numpy as np
import cv2 as cv
img = cv.imread('digits.png')
gray = cv.cvtColor(img,cv.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 = cv.ml.KNearest_create()
knn.train(train, cv.ml.ROW_SAMPLE, train_labels)
ret,result,neighbours,dist = knn.findNearest(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 )

1.3 例子：使用K近邻对手写字母OCR识别

import cv2 as cv
import numpy as np
# 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 = cv.ml.KNearest_create()
knn.train(trainData, cv.ml.ROW_SAMPLE, responses)
ret, result, neighbours, dist = knn.findNearest(testData, k=5)
correct = np.count_nonzero(result == labels)
accuracy = correct*100.0/10000
print( accuracy )

https://docs.opencv.org/3.4/d8/d4b/tutorial_py_knn_opencv.html

2 SVM支持向量机

2.1 理解SVM

此前我有对机器学习相关算法进行归纳，可以看我机器学习的专栏
在这里插入图片描述

2.2 例子:使用SVM对手写字母OCR识别

核心函数

svm = cv.ml.SVM_create()
svm.setKernel(cv.ml.SVM_LINEAR)
svm.setType(cv.ml.SVM_C_SVC)
svm.setC(2.67)
svm.setGamma(5.383)

#!/usr/bin/env python
import cv2 as cv
import numpy as np
SZ=20
bin_n = 16 # Number of bins
affine_flags = cv.WARP_INVERSE_MAP|cv.INTER_LINEAR
def deskew(img):
    m = cv.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 = cv.warpAffine(img,M,(SZ, SZ),flags=affine_flags)
    return img
def hog(img):
    gx = cv.Sobel(img, cv.CV_32F, 1, 0)
    gy = cv.Sobel(img, cv.CV_32F, 0, 1)
    mag, ang = cv.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 = cv.imread('digits.png',0)
if img is None:
    raise Exception("we need the digits.png image from samples/data here !")
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]
deskewed = [list(map(deskew,row)) for row in train_cells]
hogdata = [list(map(hog,row)) for row in deskewed]
trainData = np.float32(hogdata).reshape(-1,64)
responses = np.repeat(np.arange(10),250)[:,np.newaxis]
svm = cv.ml.SVM_create()
svm.setKernel(cv.ml.SVM_LINEAR)
svm.setType(cv.ml.SVM_C_SVC)
svm.setC(2.67)
svm.setGamma(5.383)
svm.train(trainData, cv.ml.ROW_SAMPLE, responses)
svm.save('svm_data.dat')
deskewed = [list(map(deskew,row)) for row in test_cells]
hogdata = [list(map(hog,row)) for row in deskewed]
testData = np.float32(hogdata).reshape(-1,bin_n*4)
result = svm.predict(testData)[1]
mask = result==responses
correct = np.count_nonzero(mask)
print(correct*100.0/result.size)

https://docs.opencv.org/3.4/dd/d3b/tutorial_py_svm_opencv.html

3 K均值聚类

3.1 例子——多特征数据

核心函数


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

import numpy as np
import cv2 as cv
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 = (cv.TERM_CRITERIA_EPS + cv.TERM_CRITERIA_MAX_ITER, 10, 1.0)
ret,label,center=cv.kmeans(Z,2,None,criteria,10,cv.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()

在这里插入图片描述

3.2 颜色量化

核心函数

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

import numpy as np
import cv2 as cv
img = cv.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 = (cv.TERM_CRITERIA_EPS + cv.TERM_CRITERIA_MAX_ITER, 10, 1.0)
K = 8
ret,label,center=cv.kmeans(Z,K,None,criteria,10,cv.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))
cv.imshow('res2',res2)
cv.waitKey(0)
cv.destroyAllWindows()