opencv python 基於SVM的手寫體識別

sakurala發表於2019-02-16
OpenCVPython

OCR of Hand-written Data using SVM

在kNN中，我們直接使用畫素強度作為特徵向量。 這次我們將使用方向梯度直方圖（HOG）作為特徵向量。在計算HOG之前，使用其二階矩來校正影像：

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

接下來，我們必須找到每個單元格的HOG描述符，為此，我們在X和Y方向上找到每個單元的Sobel導數，然後在每個畫素處找到它們的大小和梯度方向，該梯度量化為16個整數值，將此影像分為四個子方塊，對於每個子平方，計算方向的直方圖（16個區間），用它們的大小加權，因此每個子方格都會為您提供一個包含16個值的向量，四個這樣的向量（四個子方塊）一起給出了包含64個值的特徵向量，這是我們用來訓練資料的特徵向量。

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

最後，與前一種情況一樣，我們首先將大資料集拆分為單個單元格，對於每個數字，保留250個單元用於訓練資料，剩餘的250個資料保留用於測試。

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)

輸出：93.8

相關文章