OCR of Hand-written Data using SVM

在kNN中，我们直接使用像素强度作为特征向量。 这次我们将使用方向梯度直方图（HOG）作为特征向量。在计算HOG之前，使用其二阶矩来校正图像：

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

接下来，我们必须找到每个单元格的HOG描述符，为此，我们在X和Y方向上找到每个单元的Sobel导数，然后在每个像素处找到它们的大小和梯度方向，该梯度量化为16个整数值，将此图像分为四个子方块，对于每个子平方，计算方向的直方图（16个区间），用它们的大小加权，因此每个子方格都会为您提供一个包含16个值的向量，四个这样的矢量（四个子方块）一起给出了包含64个值的特征向量，这是我们用来训练数据的特征向量。

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

最后，与前一种情况一样，我们首先将大数据集拆分为单个单元格，对于每个数字，保留250个单元用于训练数据，剩余的250个数据保留用于测试。

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


SZ=20
bin_n = 16 # Number of bins


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)
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 = 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, 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)

输出：93.8