void readTokenMatrix(Dataset& data, const char* filename) {
std::vector<string> lines;
loadFile(lines, filename);
assert(lines.size() > 1);
std::vector<int> counts(2);
tokenizeLineIntoIntVector(lines[1], counts);
assert(counts.size() == 2);
//cout << "Found: " << counts[0] << " and " << counts[1] << endl;
data.numDocs = counts[0];
data.numTokens = counts[1];
vec trainClasses(data.numDocs);
mat features(data.numDocs, data.numTokens);
rowvec row(data.numTokens);
for(uint i = 3; i < data.numDocs + 3; i++) {
std::vector<double> tokens(getNumTokens(lines[i]));
tokenizeLineIntoDoubleVector(lines[i], tokens);
trainClasses(i-3) = tokens[0];
//cout << "class[" << tokens[0] << "]";
row.zeros();
int cumsum = 0;
for(uint j = 1; j < tokens.size() - 1; j+=2) {
cumsum += tokens[j];
//cout << "cumsum[" << cumsum << "]token[" << tokens[j+1] << "]" << flush ;
row[cumsum] = tokens[j+1];
}
Matrix::setMatrixRowToVector(features, i-3 ,row);
}
data.classifications = trainClasses;
data.features = features;
}
Impl(const std::string& learnpath, const std::string& allchars)
{
std::set<char> goodChars(allchars.begin(), allchars.end());
std::ifstream train((learnpath + "/train.txt").c_str());
std::vector< std::pair<char, std::string> > samples;
char symbol;
std::string imageFile;
while (train >> symbol >> imageFile) {
if (goodChars.find(symbol) == goodChars.end()) continue;
samples.push_back(std::make_pair(symbol, imageFile));
}
cv::Mat trainData(samples.size(), FEATURE_COUNT, cv::DataType<float>::type);
cv::Mat trainClasses(samples.size(), 1, cv::DataType<float>::type);
for (size_t i = 0; i < samples.size(); ++i) {
std::string path = learnpath + samples[i].second;
cv::Mat inp = cv::imread(path, 0), out, canny;
if (inp.empty()) continue;
cv::Canny(inp, canny, 100, 50, 3);
std::vector< std::vector<cv::Point> > contours;
cv::findContours(canny, contours, CV_RETR_LIST, CV_CHAIN_APPROX_SIMPLE, cv::Point(0, 0));
int maxx = -1, maxy = -1, minx = 1e9, miny = 1e9;
for (size_t j = 0; j < contours.size(); ++j) {
cv::Rect r = cv::boundingRect(contours[j]);
if (r.x + r.width > maxx) maxx = r.x + r.width;
if (r.y + r.height > maxy) maxy = r.y + r.height;
if (r.x < minx) minx = r.x;
if (r.y < miny) miny = r.y;
}
cv::Rect bound(minx, miny, maxx - minx, maxy - miny);
cv::resize(cv::Mat(inp, bound), out, cv::Size(10, 16), 0, 0, cv::INTER_CUBIC);
for (int j = 0; j < FEATURE_COUNT; ++j) trainData.at<float>(i, j) = out.data[j];
trainClasses.at<float>(i, 0) = samples[i].first;
}
oracle.train(trainData, trainClasses);
}
