基于qt和opencv3实现机器学习之：对OCR进行分类

OCR （Optical Character Recognition，光学字符识别），我们这个练习就是对OCR英文字母进行识别。得到一张OCR图片后，提取出字符相关的ROI图像，并且大小归一化，整个图像的像素值序列可以直接作为特征。但直接将整个图像作为特征数据维度太高，计算量太大，所以也可以进行一些降维处理，减少输入的数据量。

处理过程一般这样：先对原图像进行裁剪，得到字符的ROI图像，二值化。然后将图像分块，统计每个小块中非0像素的个数，这样就形成了一个较小的矩阵，这矩阵就是新的特征了。opencv为我们提供了一些这样的数据，放在

\opencv\sources\samples\data\letter-recognition.data

这个文件里，打开看看：

#include "opencv2/core.hpp"#include "opencv2/ml.hpp"#include <cstdio>#include <vector>#include <iostream>using namespace std;using namespace cv;using namespace cv::ml;static void help(){    printf("\nThe sample demonstrates how to train Random Trees classifier\n"    "(or Boosting classifier, or MLP, or Knearest, or Nbayes, or Support Vector Machines - see main()) using the provided dataset.\n"    "\n"    "We use the sample database letter-recognition.data\n"    "from UCI Repository, here is the link:\n"    "\n"    "Newman, D.J. & Hettich, S. & Blake, C.L. & Merz, C.J. (1998).\n"    "UCI Repository of machine learning databases\n"    "[http://www.ics.uci.edu/~mlearn/MLRepository.html].\n"    "Irvine, CA: University of California, Department of Information and Computer Science.\n"    "\n"    "The dataset consists of 20000 feature vectors along with the\n"    "responses - capital latin letters A..Z.\n"    "The first 16000 (10000 for boosting)) samples are used for training\n"    "and the remaining 4000 (10000 for boosting) - to test the classifier.\n"    "======================================================\n");}// 读取文件数据bool read_num_class_data(const string& filename, int var_count,Mat* _data, Mat* _responses){    const int M = 1024;    char buf[M + 2];    Mat el_ptr(1, var_count, CV_32F);    int i;    vector<int> responses;    _data->release();    _responses->release();    FILE* f = fopen( filename.c_str(), "rt" );    if (!f)    {        cout << "Could not read the database " << filename << endl;        return false;    }    for (;;)    {        char* ptr;        if (!fgets(buf, M, f) || !strchr(buf, ','))            break;        responses.push_back((int)buf[0]);        ptr = buf + 2;        for (i = 0; i < var_count; i++)        {            int n = 0;            sscanf( ptr, "%f%n", &el_ptr.at<float>(i), &n );            ptr += n + 1;        }        if (i < var_count)            break;        _data->push_back(el_ptr);    }    fclose(f);    Mat(responses).copyTo(*_responses);    return true;}//准备训练数据Ptr<TrainData> prepare_train_data(const Mat& data, const Mat& responses, int ntrain_samples){    Mat sample_idx = Mat::zeros(1, data.rows, CV_8U);    Mat train_samples = sample_idx.colRange(0, ntrain_samples);    train_samples.setTo(Scalar::all(1));    int nvars = data.cols;    Mat var_type(nvars + 1, 1, CV_8U);    var_type.setTo(Scalar::all(VAR_ORDERED));    var_type.at<uchar>(nvars) = VAR_CATEGORICAL;    return TrainData::create(data, ROW_SAMPLE, responses,        noArray(), sample_idx, noArray(), var_type);}//设置迭代条件inline TermCriteria TC(int iters, double eps){    return TermCriteria(TermCriteria::MAX_ITER + (eps > 0 ? TermCriteria::EPS : 0), iters, eps);}//分类预测void test_and_save_classifier(const Ptr<StatModel>& model,    const Mat& data, const Mat& responses,    int ntrain_samples, int rdelta){    int i, nsamples_all = data.rows;    double train_hr = 0, test_hr = 0;    // compute prediction error on train and test data    for (i = 0; i < nsamples_all; i++)    {        Mat sample = data.row(i);        float r = model->predict(sample);        r = std::abs(r + rdelta - responses.at<int>(i)) <= FLT_EPSILON ? 1.f : 0.f;        if (i < ntrain_samples)            train_hr += r;        else            test_hr += r;    }    test_hr /= nsamples_all - ntrain_samples;    train_hr = ntrain_samples > 0 ? train_hr / ntrain_samples : 1.;    printf("Recognition rate: train = %.1f%%, test = %.1f%%\n",        train_hr*100., test_hr*100.);}//随机树分类bool build_rtrees_classifier(const string& data_filename){    Mat data;    Mat responses;    read_num_class_data(data_filename, 16, &data, &responses);    int nsamples_all = data.rows;    int ntrain_samples = (int)(nsamples_all*0.8);    Ptr<RTrees> model;    Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples);    model = RTrees::create();    model->setMaxDepth(10);    model->setMinSampleCount(10);    model->setRegressionAccuracy(0);    model->setUseSurrogates(false);    model->setMaxCategories(15);    model->setPriors(Mat());    model->setCalculateVarImportance(true);    model->setActiveVarCount(4);    model->setTermCriteria(TC(100, 0.01f));    model->train(tdata);    test_and_save_classifier(model, data, responses, ntrain_samples, 0);    cout << "Number of trees: " << model->getRoots().size() << endl;    // Print variable importance    Mat var_importance = model->getVarImportance();    if (!var_importance.empty())    {        double rt_imp_sum = sum(var_importance)[0];        printf("var#\timportance (in %%):\n");        int i, n = (int)var_importance.total();        for (i = 0; i < n; i++)            printf("%-2d\t%-4.1f\n", i, 100.f*var_importance.at<float>(i) / rt_imp_sum);    }    return true;}//adaboost分类bool build_boost_classifier(const string& data_filename){    const int class_count = 26;    Mat data;    Mat responses;    Mat weak_responses;    read_num_class_data(data_filename, 16, &data, &responses);    int i, j, k;    Ptr<Boost> model;    int nsamples_all = data.rows;    int ntrain_samples = (int)(nsamples_all*0.5);    int var_count = data.cols;    Mat new_data(ntrain_samples*class_count, var_count + 1, CV_32F);    Mat new_responses(ntrain_samples*class_count, 1, CV_32S);    for (i = 0; i < ntrain_samples; i++)    {        const float* data_row = data.ptr<float>(i);        for (j = 0; j < class_count; j++)        {            float* new_data_row = (float*)new_data.ptr<float>(i*class_count + j);            memcpy(new_data_row, data_row, var_count*sizeof(data_row[0]));            new_data_row[var_count] = (float)j;            new_responses.at<int>(i*class_count + j) = responses.at<int>(i) == j + 'A';        }    }    Mat var_type(1, var_count + 2, CV_8U);    var_type.setTo(Scalar::all(VAR_ORDERED));    var_type.at<uchar>(var_count) = var_type.at<uchar>(var_count + 1) = VAR_CATEGORICAL;    Ptr<TrainData> tdata = TrainData::create(new_data, ROW_SAMPLE, new_responses,        noArray(), noArray(), noArray(), var_type);    vector<double> priors(2);    priors[0] = 1;    priors[1] = 26;    model = Boost::create();    model->setBoostType(Boost::GENTLE);    model->setWeakCount(100);    model->setWeightTrimRate(0.95);    model->setMaxDepth(5);    model->setUseSurrogates(false);    model->setPriors(Mat(priors));    model->train(tdata);    Mat temp_sample(1, var_count + 1, CV_32F);    float* tptr = temp_sample.ptr<float>();    // compute prediction error on train and test data    double train_hr = 0, test_hr = 0;    for (i = 0; i < nsamples_all; i++)    {        int best_class = 0;        double max_sum = -DBL_MAX;        const float* ptr = data.ptr<float>(i);        for (k = 0; k < var_count; k++)            tptr[k] = ptr[k];        for (j = 0; j < class_count; j++)        {            tptr[var_count] = (float)j;            float s = model->predict(temp_sample, noArray(), StatModel::RAW_OUTPUT);            if (max_sum < s)            {                max_sum = s;                best_class = j + 'A';            }        }        double r = std::abs(best_class - responses.at<int>(i)) < FLT_EPSILON ? 1 : 0;        if (i < ntrain_samples)            train_hr += r;        else            test_hr += r;    }    test_hr /= nsamples_all - ntrain_samples;    train_hr = ntrain_samples > 0 ? train_hr / ntrain_samples : 1.;    printf("Recognition rate: train = %.1f%%, test = %.1f%%\n",        train_hr*100., test_hr*100.);    cout << "Number of trees: " << model->getRoots().size() << endl;    return true;}//K最近邻分类bool build_knearest_classifier(const string& data_filename, int K){    Mat data;    Mat responses;    read_num_class_data(data_filename, 16, &data, &responses);    int nsamples_all = data.rows;    int ntrain_samples = (int)(nsamples_all*0.8);    Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples);    Ptr<KNearest> model = KNearest::create();    model->setDefaultK(K);    model->setIsClassifier(true);    model->train(tdata);    test_and_save_classifier(model, data, responses, ntrain_samples, 0);    return true;}//贝叶斯分类bool build_nbayes_classifier(const string& data_filename){    Mat data;    Mat responses;    read_num_class_data(data_filename, 16, &data, &responses);    int nsamples_all = data.rows;    int ntrain_samples = (int)(nsamples_all*0.8);    Ptr<NormalBayesClassifier> model;    Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples);    model = NormalBayesClassifier::create();    model->train(tdata);    test_and_save_classifier(model, data, responses, ntrain_samples, 0);    return true;}//svm分类bool build_svm_classifier(const string& data_filename){    Mat data;    Mat responses;    read_num_class_data(data_filename, 16, &data, &responses);    int nsamples_all = data.rows;    int ntrain_samples = (int)(nsamples_all*0.8);    Ptr<SVM> model;    Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples);    model = SVM::create();    model->setType(SVM::C_SVC);    model->setKernel(SVM::LINEAR);    model->setC(1);    model->train(tdata);    test_and_save_classifier(model, data, responses, ntrain_samples, 0);    return true;}int main(){    help();    string data_filename = "/home/xyl/opencv/samples/data/letter-recognition.data";  //字母数据    cout << "svm分类：" << endl;    build_svm_classifier(data_filename);    cout << "贝叶斯分类：" << endl;    build_nbayes_classifier(data_filename);    cout << "K最近邻分类：" << endl;    build_knearest_classifier(data_filename,10);    cout << "随机树分类：" << endl;    build_rtrees_classifier(data_filename);    cout << "adaboost分类：" << endl;    build_boost_classifier(data_filename);}

运行出现的效果：