首页 > 代码库 > OpenCV3 SVM ANN Adaboost KNN 随机森林等机器学习方法对OCR分类
OpenCV3 SVM ANN Adaboost KNN 随机森林等机器学习方法对OCR分类
转摘自http://www.cnblogs.com/denny402/p/5032839.html
opencv3中的ml类与opencv2中发生了变化,下面列举opencv3的机器学习类方法实例:
用途是opencv自带的ocr样本的分类功能,其中神经网络和adaboost训练速度很慢,效果还是knn的最好;
1 #include <opencv2/opencv.hpp> 2 #include <iostream> 3 using namespace std; 4 using namespace cv; 5 using namespace cv::ml; 6 7 // 读取文件数据 8 bool read_num_class_data(const string& filename, int var_count, Mat* _data, Mat* _responses) 9 { 10 const int M = 1024; 11 char buf[M + 2]; 12 13 Mat el_ptr(1, var_count, CV_32F); 14 int i; 15 vector<int> responses; 16 17 _data->release(); 18 _responses->release(); 19 FILE *f; 20 fopen_s(&f, filename.c_str(), "rt"); 21 if (!f) 22 { 23 cout << "Could not read the database " << filename << endl; 24 return false; 25 } 26 27 for (;;) 28 { 29 char* ptr; 30 if (!fgets(buf, M, f) || !strchr(buf, ‘,‘)) 31 break; 32 responses.push_back((int)buf[0]); 33 ptr = buf + 2; 34 for (i = 0; i < var_count; i++) 35 { 36 int n = 0; 37 sscanf_s(ptr, "%f%n", &el_ptr.at<float>(i), &n); 38 ptr += n + 1; 39 } 40 if (i < var_count) 41 break; 42 _data->push_back(el_ptr); 43 } 44 fclose(f); 45 Mat(responses).copyTo(*_responses); 46 return true; 47 } 48 49 50 //准备训练数据 51 Ptr<TrainData> prepare_train_data(const Mat& data, const Mat& responses, int ntrain_samples) 52 { 53 Mat sample_idx = Mat::zeros(1, data.rows, CV_8U); 54 Mat train_samples = sample_idx.colRange(0, ntrain_samples); 55 train_samples.setTo(Scalar::all(1)); 56 57 int nvars = data.cols; 58 Mat var_type(nvars + 1, 1, CV_8U); 59 var_type.setTo(Scalar::all(VAR_ORDERED)); 60 var_type.at<uchar>(nvars) = VAR_CATEGORICAL; 61 62 return TrainData::create(data, ROW_SAMPLE, responses, 63 noArray(), sample_idx, noArray(), var_type); 64 } 65 66 //设置迭代条件 67 inline TermCriteria TC(int iters, double eps) 68 { 69 return TermCriteria(TermCriteria::MAX_ITER + (eps > 0 ? TermCriteria::EPS : 0), iters, eps); 70 } 71 72 //分类预测 73 void test_and_save_classifier(const Ptr<StatModel>& model, const Mat& data, const Mat& responses, 74 int ntrain_samples, int rdelta) 75 { 76 int i, nsamples_all = data.rows; 77 double train_hr = 0, test_hr = 0; 78 79 // compute prediction error on train and test data 80 for (i = 0; i < nsamples_all; i++) 81 { 82 Mat sample = data.row(i); 83 84 float r = model->predict(sample); 85 r = std::abs(r + rdelta - responses.at<int>(i)) <= FLT_EPSILON ? 1.f : 0.f; 86 87 if (i < ntrain_samples) 88 train_hr += r; 89 else 90 test_hr += r; 91 } 92 93 test_hr /= nsamples_all - ntrain_samples; 94 train_hr = ntrain_samples > 0 ? train_hr / ntrain_samples : 1.; 95 96 printf("Recognition rate: train = %.1f%%, test = %.1f%%\n", 97 train_hr*100., test_hr*100.); 98 } 99 100 //随机树分类 101 bool build_rtrees_classifier(const string& data_filename) 102 { 103 Mat data; 104 Mat responses; 105 read_num_class_data(data_filename, 16, &data, &responses); 106 107 int nsamples_all = data.rows; 108 int ntrain_samples = (int)(nsamples_all*0.8); 109 110 Ptr<RTrees> model; 111 Ptr<TrainData> tdata =http://www.mamicode.com/ prepare_train_data(data, responses, ntrain_samples); 112 model = RTrees::create(); 113 model->setMaxDepth(10); 114 model->setMinSampleCount(10); 115 model->setRegressionAccuracy(0); 116 model->setUseSurrogates(false); 117 model->setMaxCategories(15); 118 model->setPriors(Mat()); 119 model->setCalculateVarImportance(true); 120 model->setActiveVarCount(4); 121 model->setTermCriteria(TC(100, 0.01f)); 122 model->train(tdata); 123 test_and_save_classifier(model, data, responses, ntrain_samples, 0); 124 cout << "Number of trees: " << model->getRoots().size() << endl; 125 126 // Print variable importance 127 Mat var_importance = model->getVarImportance(); 128 if (!var_importance.empty()) 129 { 130 double rt_imp_sum = sum(var_importance)[0]; 131 printf("var#\timportance (in %%):\n"); 132 int i, n = (int)var_importance.total(); 133 for (i = 0; i < n; i++) 134 printf("%-2d\t%-4.1f\n", i, 100.f*var_importance.at<float>(i) / rt_imp_sum); 135 } 136 137 return true; 138 } 139 140 //adaboost分类 141 bool build_boost_classifier(const string& data_filename) 142 { 143 const int class_count = 26; 144 Mat data; 145 Mat responses; 146 Mat weak_responses; 147 148 read_num_class_data(data_filename, 16, &data, &responses); 149 int i, j, k; 150 Ptr<Boost> model; 151 152 int nsamples_all = data.rows; 153 int ntrain_samples = (int)(nsamples_all*0.5); 154 int var_count = data.cols; 155 156 Mat new_data(ntrain_samples*class_count, var_count + 1, CV_32F); 157 Mat new_responses(ntrain_samples*class_count, 1, CV_32S); 158 159 for (i = 0; i < ntrain_samples; i++) 160 { 161 const float* data_row = data.ptr<float>(i); 162 for (j = 0; j < class_count; j++) 163 { 164 float* new_data_row = (float*)new_data.ptr<float>(i*class_count + j); 165 memcpy(new_data_row, data_row, var_count * sizeof(data_row[0])); 166 new_data_row[var_count] = (float)j; 167 new_responses.at<int>(i*class_count + j) = responses.at<int>(i) == j + ‘A‘; 168 } 169 } 170 171 Mat var_type(1, var_count + 2, CV_8U); 172 var_type.setTo(Scalar::all(VAR_ORDERED)); 173 var_type.at<uchar>(var_count) = var_type.at<uchar>(var_count + 1) = VAR_CATEGORICAL; 174 175 Ptr<TrainData> tdata =http://www.mamicode.com/ TrainData::create(new_data, ROW_SAMPLE, new_responses, 176 noArray(), noArray(), noArray(), var_type); 177 vector<double> priors(2); 178 priors[0] = 1; 179 priors[1] = 26; 180 181 model = Boost::create(); 182 model->setBoostType(Boost::GENTLE); 183 model->setWeakCount(100); 184 model->setWeightTrimRate(0.95); 185 model->setMaxDepth(5); 186 model->setUseSurrogates(false); 187 model->setPriors(Mat(priors)); 188 model->train(tdata); 189 Mat temp_sample(1, var_count + 1, CV_32F); 190 float* tptr = temp_sample.ptr<float>(); 191 192 // compute prediction error on train and test data 193 double train_hr = 0, test_hr = 0; 194 for (i = 0; i < nsamples_all; i++) 195 { 196 int best_class = 0; 197 double max_sum = -DBL_MAX; 198 const float* ptr = data.ptr<float>(i); 199 for (k = 0; k < var_count; k++) 200 tptr[k] = ptr[k]; 201 202 for (j = 0; j < class_count; j++) 203 { 204 tptr[var_count] = (float)j; 205 float s = model->predict(temp_sample, noArray(), StatModel::RAW_OUTPUT); 206 if (max_sum < s) 207 { 208 max_sum = s; 209 best_class = j + ‘A‘; 210 } 211 } 212 213 double r = std::abs(best_class - responses.at<int>(i)) < FLT_EPSILON ? 1 : 0; 214 if (i < ntrain_samples) 215 train_hr += r; 216 else 217 test_hr += r; 218 } 219 220 test_hr /= nsamples_all - ntrain_samples; 221 train_hr = ntrain_samples > 0 ? train_hr / ntrain_samples : 1.; 222 printf("Recognition rate: train = %.1f%%, test = %.1f%%\n", 223 train_hr*100., test_hr*100.); 224 225 cout << "Number of trees: " << model->getRoots().size() << endl; 226 return true; 227 } 228 229 //多层感知机分类(ANN) 230 bool build_mlp_classifier(const string& data_filename) 231 { 232 const int class_count = 26; 233 Mat data; 234 Mat responses; 235 236 read_num_class_data(data_filename, 16, &data, &responses); 237 Ptr<ANN_MLP> model; 238 239 int nsamples_all = data.rows; 240 int ntrain_samples = (int)(nsamples_all*0.8); 241 Mat train_data = http://www.mamicode.com/data.rowRange(0, ntrain_samples); 242 Mat train_responses = Mat::zeros(ntrain_samples, class_count, CV_32F); 243 244 // 1. unroll the responses 245 cout << "Unrolling the responses...\n"; 246 for (int i = 0; i < ntrain_samples; i++) 247 { 248 int cls_label = responses.at<int>(i) - ‘A‘; 249 train_responses.at<float>(i, cls_label) = 1.f; 250 } 251 252 // 2. train classifier 253 int layer_sz[] = { data.cols, 100, 100, class_count }; 254 int nlayers = (int)(sizeof(layer_sz) / sizeof(layer_sz[0])); 255 Mat layer_sizes(1, nlayers, CV_32S, layer_sz); 256 257 #if 1 258 int method = ANN_MLP::BACKPROP; 259 double method_param = 0.001; 260 int max_iter = 300; 261 #else 262 int method = ANN_MLP::RPROP; 263 double method_param = 0.1; 264 int max_iter = 1000; 265 #endif 266 267 Ptr<TrainData> tdata =http://www.mamicode.com/ TrainData::create(train_data, ROW_SAMPLE, train_responses); 268 model = ANN_MLP::create(); 269 model->setLayerSizes(layer_sizes); 270 model->setActivationFunction(ANN_MLP::SIGMOID_SYM, 0, 0); 271 model->setTermCriteria(TC(max_iter, 0)); 272 model->setTrainMethod(method, method_param); 273 model->train(tdata); 274 return true; 275 } 276 277 //K最近邻分类 278 bool build_knearest_classifier(const string& data_filename, int K) 279 { 280 Mat data; 281 Mat responses; 282 read_num_class_data(data_filename, 16, &data, &responses); 283 int nsamples_all = data.rows; 284 int ntrain_samples = (int)(nsamples_all*0.8); 285 286 Ptr<TrainData> tdata =http://www.mamicode.com/ prepare_train_data(data, responses, ntrain_samples); 287 Ptr<KNearest> model = KNearest::create(); 288 model->setDefaultK(K); 289 model->setIsClassifier(true); 290 model->train(tdata); 291 292 test_and_save_classifier(model, data, responses, ntrain_samples, 0); 293 return true; 294 } 295 296 //贝叶斯分类 297 bool build_nbayes_classifier(const string& data_filename) 298 { 299 Mat data; 300 Mat responses; 301 read_num_class_data(data_filename, 16, &data, &responses); 302 303 int nsamples_all = data.rows; 304 int ntrain_samples = (int)(nsamples_all*0.8); 305 306 Ptr<NormalBayesClassifier> model; 307 Ptr<TrainData> tdata =http://www.mamicode.com/ prepare_train_data(data, responses, ntrain_samples); 308 model = NormalBayesClassifier::create(); 309 model->train(tdata); 310 311 test_and_save_classifier(model, data, responses, ntrain_samples, 0); 312 return true; 313 } 314 315 316 //svm分类 317 bool build_svm_classifier(const string& data_filename) 318 { 319 Mat data; 320 Mat responses; 321 read_num_class_data(data_filename, 16, &data, &responses); 322 323 int nsamples_all = data.rows; 324 int ntrain_samples = (int)(nsamples_all*0.8); 325 326 Ptr<SVM> model; 327 Ptr<TrainData> tdata =http://www.mamicode.com/ prepare_train_data(data, responses, ntrain_samples); 328 model = SVM::create(); 329 model->setType(SVM::C_SVC); 330 model->setKernel(SVM::LINEAR); 331 model->setC(1); 332 model->train(tdata); 333 334 test_and_save_classifier(model, data, responses, ntrain_samples, 0); 335 return true; 336 } 337 338 int main() 339 { 340 string data_filename = "D:\\Program Files\\opencv\\sources\\samples\\data\\letter-recognition.data"; //字母数据 341 342 cout << "svm分类:" << endl; 343 build_svm_classifier(data_filename); 344 345 cout << "贝叶斯分类:" << endl; 346 build_nbayes_classifier(data_filename); 347 348 cout << "K最近邻分类:" << endl; 349 build_knearest_classifier(data_filename, 10); 350 351 cout << "随机树分类:" << endl; 352 build_rtrees_classifier(data_filename); 353 354 cout << "adaboost分类:" << endl; 355 build_boost_classifier(data_filename); 356 357 cout << "ANN(多层感知机)分类:" << endl; 358 build_mlp_classifier(data_filename); 359 360 system("pause"); 361 return 0; 362 }
OpenCV3 SVM ANN Adaboost KNN 随机森林等机器学习方法对OCR分类
声明:以上内容来自用户投稿及互联网公开渠道收集整理发布,本网站不拥有所有权,未作人工编辑处理,也不承担相关法律责任,若内容有误或涉及侵权可进行投诉: 投诉/举报 工作人员会在5个工作日内联系你,一经查实,本站将立刻删除涉嫌侵权内容。