tesseract/wordrec/segsearch.cpp

///////////////////////////////////////////////////////////////////////
// File:        segsearch.h
// Description: Segmentation search functions.
// Author:      Daria Antonova
// Created:     Mon Jun 23 11:26:43 PDT 2008
//
// (C) Copyright 2009, Google Inc.
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
// http://www.apache.org/licenses/LICENSE-2.0
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
///////////////////////////////////////////////////////////////////////

#include "wordrec.h"

#include "associate.h"
#include "baseline.h"
#include "language_model.h"
#include "matrix.h"
#include "oldheap.h"
#include "params.h"
#include "ratngs.h"
#include "states.h"

ELISTIZE(SEG_SEARCH_PENDING);

namespace tesseract {

void Wordrec::SegSearch(CHUNKS_RECORD *chunks_record,
                        WERD_CHOICE *best_choice,
                        BLOB_CHOICE_LIST_VECTOR *best_char_choices,
                        WERD_CHOICE *raw_choice,
                        STATE *output_best_state) {
  int row, col = 0;
  if (segsearch_debug_level > 0) {
    tprintf("Starting SegSearch on ratings matrix:\n");
    chunks_record->ratings->print(getDict().getUnicharset());
  }
  // Start with a fresh best_choice since rating adjustments
  // used by the chopper and the new segmentation search are not compatible.
  best_choice->set_rating(WERD_CHOICE::kBadRating);
  // Clear best choice accumulator (that is used for adaption), so that
  // choices adjusted by chopper do not interfere with the results from the
  // segmentation search.
  getDict().ClearBestChoiceAccum();

  MATRIX *ratings = chunks_record->ratings;
  // Priority queue containing pain points generated by the language model
  // The priority is set by the language model components, adjustments like
  // seam cost and width priority are factored into the priority.
  HEAP *pain_points = MakeHeap(segsearch_max_pain_points);

  // best_path_by_column records the lowest cost path found so far for each
  // column of the chunks_record->ratings matrix over all the rows.
  BestPathByColumn *best_path_by_column =
    new BestPathByColumn[ratings->dimension()];
  for (col = 0; col < ratings->dimension(); ++col) {
    best_path_by_column[col].avg_cost = WERD_CHOICE::kBadRating;
    best_path_by_column[col].best_vse = NULL;
  }

  language_model_->InitForWord(prev_word_best_choice_, &denorm_,
                               assume_fixed_pitch_char_segment,
                               best_choice->certainty(),
                               segsearch_max_char_wh_ratio,
                               pain_points, chunks_record);

  MATRIX_COORD *pain_point;
  float pain_point_priority;
  BestChoiceBundle best_choice_bundle(
      output_best_state, best_choice, raw_choice, best_char_choices);

  // pending[i] stores a list of the parent/child pair of BLOB_CHOICE_LISTs,
  // where i is the column of the child. Initially all the classified entries
  // in the ratings matrix from column 0 (with parent NULL) are inserted into
  // pending[0]. As the language model state is updated, new child/parent
  // pairs are inserted into the lists. Next, the entries in pending[1] are
  // considered, and so on. It is important that during the update the
  // children are considered in the non-decreasing order of their column, since
  // this guarantess that all the parents would be up to date before an update
  // of a child is done.
  SEG_SEARCH_PENDING_LIST *pending =
    new SEG_SEARCH_PENDING_LIST[ratings->dimension()];

  // Search for the ratings matrix for the initial best path.
  for (row = 0; row < ratings->dimension(); ++row) {
    if (ratings->get(0, row) != NOT_CLASSIFIED) {
      pending[0].add_sorted(
          SEG_SEARCH_PENDING::compare, true,
          new SEG_SEARCH_PENDING(row, NULL, LanguageModel::kAllChangedFlag));
    }
  }
  UpdateSegSearchNodes(0, &pending, &best_path_by_column, chunks_record,
                       pain_points, &best_choice_bundle);

  // Keep trying to find a better path by fixing the "pain points".
  int num_futile_classifications = 0;
  while (!(language_model_->AcceptableChoiceFound() ||
           num_futile_classifications >=
           segsearch_max_futile_classifications)) {
    // Get the next valid "pain point".
    int pop;
    while (true) {
      pop = HeapPop(pain_points, &pain_point_priority, &pain_point);
      if (pop == EMPTY) break;
      if (pain_point->Valid(*ratings) &&
        ratings->get(pain_point->col, pain_point->row) == NOT_CLASSIFIED) {
        break;
      } else {
        delete pain_point;
      }
    }
    if (pop == EMPTY) {
      if (segsearch_debug_level > 0) tprintf("Pain points queue is empty\n");
      break;
    }
    if (segsearch_debug_level > 0) {
      tprintf("Classifying pain point priority=%.4f, col=%d, row=%d\n",
              pain_point_priority, pain_point->col, pain_point->row);
    }
    BLOB_CHOICE_LIST *classified = classify_piece(
        chunks_record->chunks, chunks_record->splits,
        pain_point->col, pain_point->row);
    ratings->put(pain_point->col, pain_point->row, classified);

    if (segsearch_debug_level > 0) {
      print_ratings_list("Updated ratings matrix with a new entry:",
                         ratings->get(pain_point->col, pain_point->row),
                         getDict().getUnicharset());
      chunks_record->ratings->print(getDict().getUnicharset());
    }

    // Insert initial "pain points" to join the newly classified blob
    // with its left and right neighbors.
    if (!classified->empty()) {
      float worst_piece_cert;
      bool fragmented;
      if (pain_point->col > 0) {
        language_model_->GetWorstPieceCertainty(
            pain_point->col-1, pain_point->row, chunks_record->ratings,
            &worst_piece_cert, &fragmented);
        language_model_->GeneratePainPoint(
            pain_point->col-1, pain_point->row, false,
            LanguageModel::kInitialPainPointPriorityAdjustment,
            worst_piece_cert, fragmented, best_choice->certainty(),
            segsearch_max_char_wh_ratio, NULL, NULL,
            chunks_record, pain_points);
      }
      if (pain_point->row+1 < ratings->dimension()) {
        language_model_->GetWorstPieceCertainty(
            pain_point->col, pain_point->row+1, chunks_record->ratings,
            &worst_piece_cert, &fragmented);
        language_model_->GeneratePainPoint(
            pain_point->col, pain_point->row+1, true,
            LanguageModel::kInitialPainPointPriorityAdjustment,
            worst_piece_cert, fragmented, best_choice->certainty(),
            segsearch_max_char_wh_ratio, NULL, NULL,
            chunks_record, pain_points);
      }
    }

    // Record a pending entry with the pain_point and each of its parents.
    int parent_row = pain_point->col - 1;
    if (parent_row < 0) {  // this node has no parents
      pending[pain_point->col].add_sorted(
          SEG_SEARCH_PENDING::compare, true,
          new SEG_SEARCH_PENDING(pain_point->row, NULL,
                                 LanguageModel::kAllChangedFlag));
    } else {
      for (int parent_col = 0; parent_col < pain_point->col; ++parent_col) {
        if (ratings->get(parent_col, parent_row) != NOT_CLASSIFIED) {
          pending[pain_point->col].add_sorted(
              SEG_SEARCH_PENDING::compare, true,
              new SEG_SEARCH_PENDING(pain_point->row,
                                     ratings->get(parent_col, parent_row),
                                     LanguageModel::kAllChangedFlag));
        }
      }
    }
    UpdateSegSearchNodes(pain_point->col, &pending, &best_path_by_column,
                         chunks_record, pain_points, &best_choice_bundle);
    if (!best_choice_bundle.updated) ++num_futile_classifications;

    if (segsearch_debug_level > 0) {
      tprintf("num_futile_classifications %d\n", num_futile_classifications);
    }

    // Clean up
    best_choice_bundle.updated = false;
    delete pain_point;  // done using this pain point
  }

  if (segsearch_debug_level > 0) {
    tprintf("Done with SegSearch (AcceptableChoiceFound: %d\n",
            language_model_->AcceptableChoiceFound());
  }

  // Clean up.
  FreeHeapData(pain_points, MATRIX_COORD::Delete);
  delete[] best_path_by_column;
  delete[] pending;
  for (row = 0; row < ratings->dimension(); ++row) {
    for (col = 0; col <= row; ++col) {
      BLOB_CHOICE_LIST *rating = ratings->get(col, row);
      if (rating != NOT_CLASSIFIED) language_model_->DeleteState(rating);
    }
  }
}

void Wordrec::UpdateSegSearchNodes(
    int starting_col,
    SEG_SEARCH_PENDING_LIST *pending[],
    BestPathByColumn *best_path_by_column[],
    CHUNKS_RECORD *chunks_record,
    HEAP *pain_points,
    BestChoiceBundle *best_choice_bundle) {
  MATRIX *ratings = chunks_record->ratings;
  for (int col = starting_col; col < ratings->dimension(); ++col) {
    if (segsearch_debug_level > 0) {
      tprintf("\n\nUpdateSegSearchNodes: evaluate children in col=%d\n", col);
    }
    // Iterate over the pending list for this column.
    SEG_SEARCH_PENDING_LIST *pending_list = &((*pending)[col]);
    SEG_SEARCH_PENDING_IT pending_it(pending_list);
    GenericVector<int> non_empty_rows;
    while (!pending_it.empty()) {
      // Update language model state of this child+parent pair.
      SEG_SEARCH_PENDING *p = pending_it.extract();
      if (non_empty_rows.length() == 0 ||
          non_empty_rows[non_empty_rows.length()-1] != p->child_row) {
        non_empty_rows.push_back(p->child_row);
      }
      BLOB_CHOICE_LIST *current_node = ratings->get(col, p->child_row);
      LanguageModelFlagsType new_changed =
        language_model_->UpdateState(p->changed, col, p->child_row,
                                     current_node, p->parent, pain_points,
                                     best_path_by_column,
                                     chunks_record, best_choice_bundle);
      if (new_changed) {
        // Since the language model state of this entry changed, add all the
        // pairs with it as a parent and each of its children to pending, so
        // that the children are updated as well.
        int child_col = p->child_row + 1;
        for (int child_row = child_col;
             child_row < ratings->dimension(); ++child_row) {
          if (ratings->get(child_col, child_row) != NOT_CLASSIFIED) {
            SEG_SEARCH_PENDING *new_pending =
              new SEG_SEARCH_PENDING(child_row, current_node, 0);
            SEG_SEARCH_PENDING *actual_new_pending =
              reinterpret_cast<SEG_SEARCH_PENDING *>(
                  (*pending)[child_col].add_sorted_and_find(
                  SEG_SEARCH_PENDING::compare, true, new_pending));
            if (new_pending != actual_new_pending) delete new_pending;
            actual_new_pending->changed |= new_changed;
            if (segsearch_debug_level > 0) {
                  tprintf("Added child(col=%d row=%d) parent(col=%d row=%d)"
                          " changed=0x%x to pending\n", child_col,
                          actual_new_pending->child_row,
                          col, p->child_row, actual_new_pending->changed);
            }
          }
        }
      }  // end if new_changed
      delete p;  // clean up
      pending_it.forward();
    } // end while !pending_it.empty()
    language_model_->GeneratePainPointsFromColumn(
      col, non_empty_rows, best_choice_bundle->best_choice->certainty(),
      pain_points, best_path_by_column, chunks_record);
  }  // end for col

  if (best_choice_bundle->updated) {
    language_model_->GeneratePainPointsFromBestChoice(
        pain_points, chunks_record, best_choice_bundle);
  }

  language_model_->CleanUp();
}

}  // namespace tesseract