我正在尝试使用OpenCV和C++创建神经网络，目的是识别道路标志。我按照以下方式创建了网络，但预测效果很差，因为它返回奇怪的结果：
。训练样本图片如下所示：
。请问有人能帮忙吗？
奇怪的结果：对于这个输入
，答案是3（因为我只有4个类别-限速50、60、70、80）。对于限速80标志来说是正确的。
但是对于其他输入，结果是不正确的。它们对于50、60、70限速标志是相同的。max1 = min1 = 1.02631...（如第一张图片所示）。这很奇怪。
。训练样本图片如下所示：。请问有人能帮忙吗？ trainNN() {
char* templates_directory[] = {
"speed50ver1\\",
"speed60ver1\\",
"speed70ver1\\",
"speed80ver1\\"
};
int const numFilesChars[]={ 213, 100, 385, 163};
char const strCharacters[] = { '5', '6', '7', '8' };
Mat trainingData;
Mat trainingLabels(0, 0, CV_32S);
int const numCharacters = 4;
// load images from directory
for (int i = 0; i != numCharacters; ++i) {
int numFiles = numFilesChars[i];
DIR *dir;
struct dirent *ent;
char* s1 = templates_directory[i];
if ((dir = opendir (s1)) != NULL) {
Size size(80, 80);
while ((ent = readdir (dir)) != NULL) {
string s = s1;
s.append(ent->d_name);
if(s.substr(s.find_last_of(".") + 1) == "jpg") {
Mat img = imread(s,0);
Mat img_mat;
resize(img, img_mat, size);
Mat new_img = img_mat.reshape(1, 1);
trainingData.push_back(new_img);
trainingLabels.push_back(i);
}
}
int b = 0;
closedir (dir);
} else {
/* could not open directory */
perror ("");
}
}
trainingData.convertTo(trainingData, CV_32FC1);
Mat trainClasses(trainingData.rows, numCharacters, CV_32FC1);
for( int i = 0; i != trainClasses.rows; ++i){
int const labels = *trainingLabels.ptr<int>(i);
auto train_ptr = trainClasses.ptr<float>(i);
for(int k = 0; k != trainClasses.cols; ++k){
*train_ptr = k != labels ? 0 : 1;
++train_ptr;
}
}
int layers_d[] = { trainingData.cols, 10, numCharacters};
Mat layers(1, 3, CV_32SC1, layers_d);
ann.create(layers, CvANN_MLP::SIGMOID_SYM, 1, 1);
CvANN_MLP_TrainParams params = CvANN_MLP_TrainParams(
// terminate the training after either 1000
// iterations or a very small change in the
// network wieghts below the specified value
cvTermCriteria(CV_TERMCRIT_ITER+CV_TERMCRIT_EPS, 1000, 0.000001),
// use backpropogation for training
CvANN_MLP_TrainParams::BACKPROP,
// co-efficents for backpropogation training
// (refer to manual)
0.1,
0.1);
int iterations = ann.train(trainingData, trainClasses, cv::Mat(), cv::Mat(), params);
CvFileStorage* storage = cvOpenFileStorage( "neural_network_2.xml", 0, CV_STORAGE_WRITE );
ann.write(storage,"digit_recognition");
cvReleaseFileStorage(&storage);
}
void analysis(char* file, bool a) {
//trainNN(a);
read_nn();
// load image
Mat img = imread(file, 0);
Size my_size(80,80);
resize(img, img, my_size);
Mat r_img = img.reshape(1,1);
r_img.convertTo(r_img, CV_32FC1);
Mat classOut(1,4,CV_32FC1);
ann.predict(r_img, classOut);
double min1, max1;
cv::Point min_loc, max_loc;
minMaxLoc(classOut, &min1, &max1, &min_loc, &max_loc);
int x = max_loc.x;
//create windows
namedWindow("Original Image", CV_WINDOW_AUTOSIZE);
imshow("Original Image", img);
waitKey(0); //wait for key press
img.release();
rr.release();
destroyAllWindows(); //destroy all open windows
}
奇怪的结果：对于这个输入
，答案是3（因为我只有4个类别-限速50、60、70、80）。对于限速80标志来说是正确的。
但是对于其他输入，结果是不正确的。它们对于50、60、70限速标志是相同的。max1 = min1 = 1.02631...（如第一张图片所示）。这很奇怪。