// Given an initial estimate of line spacing (m_in) and the positions of each
// baseline, computes the line spacing of the block more accurately in m_out,
// and the corresponding intercept in c_out, and the number of spacings seen
// in index_delta. Returns the error of fit to the line spacing model.
// Uses a simple linear regression, but optimized the offset using the median.
double BaselineBlock::FitLineSpacingModel(
const GenericVector<double>& positions, double m_in,
double* m_out, double* c_out, int* index_delta) {
if (m_in == 0.0f || positions.size() < 2) {
*m_out = m_in;
*c_out = 0.0;
if (index_delta != NULL) *index_delta = 0;
return 0.0;
}
GenericVector<double> offsets;
// Get the offset (remainder) linespacing for each line and choose the median.
for (int i = 0; i < positions.size(); ++i)
offsets.push_back(fmod(positions[i], m_in));
// Get the median offset.
double median_offset = MedianOfCircularValues(m_in, &offsets);
// Now fit a line to quantized line number and offset.
LLSQ llsq;
int min_index = MAX_INT32;
int max_index = -MAX_INT32;
for (int i = 0; i < positions.size(); ++i) {
double y_pos = positions[i];
int row_index = IntCastRounded((y_pos - median_offset) / m_in);
UpdateRange(row_index, &min_index, &max_index);
llsq.add(row_index, y_pos);
}
// Get the refined line spacing.
*m_out = llsq.m();
// Use the median offset rather than the mean.
offsets.truncate(0);
for (int i = 0; i < positions.size(); ++i)
offsets.push_back(fmod(positions[i], *m_out));
// Get the median offset.
if (debug_level_ > 2) {
for (int i = 0; i < offsets.size(); ++i)
tprintf("%d: %g\n", i, offsets[i]);
}
*c_out = MedianOfCircularValues(*m_out, &offsets);
if (debug_level_ > 1) {
tprintf("Median offset = %g, compared to mean of %g.\n",
*c_out, llsq.c(*m_out));
}
// Index_delta is the number of hypothesized line gaps present.
if (index_delta != NULL)
*index_delta = max_index - min_index;
// Use the regression model's intercept to compute the error, as it may be
// a full line-spacing in disagreement with the median.
double rms_error = llsq.rms(*m_out, llsq.c(*m_out));
if (debug_level_ > 1) {
tprintf("Linespacing of y=%g x + %g improved to %g x + %g, rms=%g\n",
m_in, median_offset, *m_out, *c_out, rms_error);
}
return rms_error;
}
void ResultIterator::CalculateTextlineOrder(
bool paragraph_is_ltr,
const LTRResultIterator &resit,
GenericVector<StrongScriptDirection> *dirs_arg,
GenericVectorEqEq<int> *word_indices) const {
GenericVector<StrongScriptDirection> dirs;
GenericVector<StrongScriptDirection> *directions;
directions = (dirs_arg != NULL) ? dirs_arg : &dirs;
directions->truncate(0);
// A LTRResultIterator goes strictly left-to-right word order.
LTRResultIterator ltr_it(resit);
ltr_it.RestartRow();
if (ltr_it.Empty(RIL_WORD)) return;
do {
directions->push_back(ltr_it.WordDirection());
} while (ltr_it.Next(RIL_WORD) && !ltr_it.IsAtBeginningOf(RIL_TEXTLINE));
word_indices->truncate(0);
CalculateTextlineOrder(paragraph_is_ltr, *directions, word_indices);
}