OpenCV与图像处理（八）

# encoding:utf-8
import cv2
import numpy as np

SZ = 20
bin_n = 16
affine_flags = cv2.WARP_INVERSE_MAP | cv2.INTER_LINEAR

def deskew(img):
    # 计算图像中的中心矩(最高到三阶)
    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]])
    # 图像的平移，参数:输入图像、变换矩阵、变换后的大小
    img = cv2.warpAffine(img, M, (SZ, SZ), flags=affine_flags)
    return img

# 使用方向梯度直方图HOG作为特征向量，计算图像的 X 方向和 Y 方向的 Sobel 导数
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)  # 笛卡尔坐标转换为极坐标, → magnitude, angle
    bins = np.int32(bin_n * ang / (2 * np.pi))
    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

# 将大图分割为小图，使用每个数字的前250个作为训练数据，后250个作为测试数据
img = cv2.imread('./digits.png', 0)
cells = [np.hsplit(row, 100) for row in np.vsplit(img, 50)]

# 第一部分是训练数据，剩下的是测试数据
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]
print(hogdata)

trainData = np.float32(hogdata).reshape(-1, 64)
labels = np.repeat(np.arange(10), 250)[:, np.newaxis]

svm = cv2.ml.SVM_create()
svm.setKernel(cv2.ml.SVM_LINEAR)
svm.setType(cv2.ml.SVM_C_SVC)
svm.setC(2.67)
svm.setGamma(5.383)
svm.train(trainData, cv2.ml.ROW_SAMPLE, labels)
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)

ret, result = svm.predict(testData)
mask = result == labels
correct = np.count_nonzero(mask)
print(correct * 100.0 / len(result),'%')

# encoding:utf-8
import cv2 as cv
import numpy as np

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

# 将图像分割为5000个单元格，每个单元格为20x20
cells = [np.hsplit(row,100) for row in np.vsplit(gray,50)]

# 使其成为一个Numpy数组,大小将是（50,100,20,20）
x = np.array(cells)

# 准备train_data和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)

# 为训练和测试数据创建标签
k = np.arange(10)
train_labels = np.repeat(k,250)[:,np.newaxis]
test_labels = train_labels.copy()

# 初始化kNN，训练数据，然后使用k=5的测试数据对其进行测试
knn = cv.ml.KNearest_create()
knn.train(train, cv.ml.ROW_SAMPLE, train_labels)
knn.save('knn_data.dat')
ret,result,neighbours,dist = knn.findNearest(test, k=5)
print( test )
print( result )

# 检查分类的准确性，将结果与test_labels进行比较
matches = result == test_labels
correct = np.count_nonzero(matches)
accuracy = correct*100.0/result.size
print( accuracy,'%' )

# encoding:utf-8
import cv2 as cv
import numpy as np

# 加载数据，转换器将字母转换为数字
data= np.loadtxt('letter-recognition.data',
      dtype= 'float32', 
      delimiter = ',',
            converters= {0: lambda ch: ord(ch)-ord('A')})

# 将数据分为训练数据和测试数据
train, test = np.vsplit(data,2)

# 将训练数据和测试数据分别拆分为特征和标签
train_labels, trainData = np.hsplit(train,[1])
test_labels, testData = np.hsplit(test,[1])

# 初始化KNN, 记性训练测试
knn = cv.ml.KNearest_create()
knn.train(trainData, cv.ml.ROW_SAMPLE, train_labels)
knn.save('knn_english.dat')

ret, result, neighbours, dist = knn.findNearest(testData, k=5)
print( testData )
print( result )

correct = np.count_nonzero(result == test_labels)
accuracy = correct*100.0/10000
print( accuracy,'%')