// Computes the noise_density_ by summing the number of elements in a
// neighbourhood of each grid cell.
void StrokeWidth::ComputeNoiseDensity(TO_BLOCK* block, TabFind* line_grid) {
// Run a preliminary strokewidth neighbour detection on the medium blobs.
line_grid->InsertBlobList(true, true, false, &block->blobs, false, this);
BLOBNBOX_IT blob_it(&block->blobs);
for (blob_it.mark_cycle_pt(); !blob_it.cycled_list(); blob_it.forward()) {
SetNeighbours(false, blob_it.data());
}
// Remove blobs with a good strokewidth neighbour from the grid.
for (blob_it.mark_cycle_pt(); !blob_it.cycled_list(); blob_it.forward()) {
BLOBNBOX* blob = blob_it.data();
if (blob->GoodTextBlob() > 0)
RemoveBBox(blob);
blob->ClearNeighbours();
}
// Insert the smaller blobs into the grid.
line_grid->InsertBlobList(true, true, false, &block->small_blobs,
false, this);
line_grid->InsertBlobList(true, true, false, &block->noise_blobs,
false, this);
if (noise_density_ != NULL)
delete noise_density_;
IntGrid* cell_counts = CountCellElements();
noise_density_ = cell_counts->NeighbourhoodSum();
delete cell_counts;
// Clear the grid as we don't want the small stuff hanging around in it.
Clear();
}
// Computes and returns the noise_density IntGrid, at the same gridsize as
// this by summing the number of small elements in a 3x3 neighbourhood of
// each grid cell. good_grid is filled with blobs that are considered most
// likely good text, and this is filled with small and medium blobs that are
// more likely non-text.
// The photo_map is used to bias the decision towards non-text, rather than
// supplying definite decision.
IntGrid* CCNonTextDetect::ComputeNoiseDensity(bool debug, Pix* photo_map,
BlobGrid* good_grid) {
IntGrid* noise_counts = CountCellElements();
IntGrid* noise_density = noise_counts->NeighbourhoodSum();
IntGrid* good_counts = good_grid->CountCellElements();
// Now increase noise density in photo areas, to bias the decision and
// minimize hallucinated text on image, but trim the noise_density where
// there are good blobs and the original count is low in non-photo areas,
// indicating that most of the result came from neighbouring cells.
int height = pixGetHeight(photo_map);
int photo_offset = IntCastRounded(max_noise_count_ * kPhotoOffsetFraction);
for (int y = 0; y < gridheight(); ++y) {
for (int x = 0; x < gridwidth(); ++x) {
int noise = noise_density->GridCellValue(x, y);
if (max_noise_count_ < noise + photo_offset &&
noise <= max_noise_count_) {
// Test for photo.
int left = x * gridsize();
int right = left + gridsize();
int bottom = height - y * gridsize();
int top = bottom - gridsize();
if (ImageFind::BoundsWithinRect(photo_map, &left, &top, &right,
&bottom)) {
noise_density->SetGridCell(x, y, noise + photo_offset);
}
}
if (debug && noise > max_noise_count_ &&
good_counts->GridCellValue(x, y) > 0) {
tprintf("At %d, %d, noise = %d, good=%d, orig=%d, thr=%d\n",
x * gridsize(), y * gridsize(),
noise_density->GridCellValue(x, y),
good_counts->GridCellValue(x, y),
noise_counts->GridCellValue(x, y), max_noise_count_);
}
if (noise > max_noise_count_ &&
good_counts->GridCellValue(x, y) > 0 &&
noise_counts->GridCellValue(x, y) * kOriginalNoiseMultiple <=
max_noise_count_) {
noise_density->SetGridCell(x, y, 0);
}
}
}
delete noise_counts;
delete good_counts;
return noise_density;
}
