Method ExtractFeatures

deps/tesseract/classify/intfx.cpp:445–487

Extracts sets of 3-D features of length kStandardFeatureLength (=12.8), as (x,y) position and angle as measured counterclockwise from the vector <-1, 0>, from blob using two normalizations defined by bl_denorm and cn_denorm. See SetpuBLCNDenorms for definitions. If outline_cn_counts is not NULL, on return it contains the cumulative number of cn features generated for each outline in the blob (in o

// Thus after the first outline, there were (*outline_cn_counts)[0] features,
// after the second outline, there were (*outline_cn_counts)[1] features etc.
void Classify::ExtractFeatures(const TBLOB& blob,
                               bool nonlinear_norm,
                               GenericVector<INT_FEATURE_STRUCT>* bl_features,
                               GenericVector<INT_FEATURE_STRUCT>* cn_features,
                               INT_FX_RESULT_STRUCT* results,
                               GenericVector<int>* outline_cn_counts) {
  DENORM bl_denorm, cn_denorm;
  tesseract::Classify::SetupBLCNDenorms(blob, nonlinear_norm,
                                        &bl_denorm, &cn_denorm, results);
  if (outline_cn_counts != NULL)
    outline_cn_counts->truncate(0);
  // Iterate the outlines.
  for (TESSLINE* ol = blob.outlines; ol != NULL; ol = ol->next) {
    // Iterate the polygon.
    EDGEPT* loop_pt = ol->FindBestStartPt();
    EDGEPT* pt = loop_pt;
    if (pt == NULL) continue;
    do {
      if (pt->IsHidden()) continue;
      // Find a run of equal src_outline.
      EDGEPT* last_pt = pt;
      do {
        last_pt = last_pt->next;
      } while (last_pt != loop_pt && !last_pt->IsHidden() &&
               last_pt->src_outline == pt->src_outline);
      last_pt = last_pt->prev;
      // Until the adaptive classifier can be weaned off polygon segments,
      // we have to force extraction from the polygon for the bl_features.
      ExtractFeaturesFromRun(pt, last_pt, bl_denorm, kStandardFeatureLength,
                             true, bl_features);
      ExtractFeaturesFromRun(pt, last_pt, cn_denorm, kStandardFeatureLength,
                             false, cn_features);
      pt = last_pt;
    } while ((pt = pt->next) != loop_pt);
    if (outline_cn_counts != NULL)
      outline_cn_counts->push_back(cn_features->size());
  }
  results->NumBL = bl_features->size();
  results->NumCN = cn_features->size();
  results->YBottom = blob.bounding_box().bottom();
  results->YTop = blob.bounding_box().top();
  results->Width = blob.bounding_box().width();
}

}  // namespace tesseract