blamer.h File Reference

#include <cstdint>
#include <cstring>
#include "boxword.h"
#include "genericvector.h"
#include "params_training_featdef.h"
#include "ratngs.h"
#include "rect.h"
#include "strngs.h"
#include "tprintf.h"
#include "unichar.h"

Go to the source code of this file.

Classes
struct	BlamerBundle

Enumerations
enum	IncorrectResultReason {   IRR_CORRECT , IRR_CLASSIFIER , IRR_CHOPPER , IRR_CLASS_LM_TRADEOFF ,   IRR_PAGE_LAYOUT , IRR_SEGSEARCH_HEUR , IRR_SEGSEARCH_PP , IRR_CLASS_OLD_LM_TRADEOFF ,   IRR_ADAPTION , IRR_NO_TRUTH_SPLIT , IRR_NO_TRUTH , IRR_UNKNOWN ,   IRR_NUM_REASONS }

Enumeration Type Documentation

IncorrectResultReason

enum IncorrectResultReason

Enumerator
IRR_CORRECT
IRR_CLASSIFIER
IRR_CHOPPER
IRR_CLASS_LM_TRADEOFF
IRR_PAGE_LAYOUT
IRR_SEGSEARCH_HEUR
IRR_SEGSEARCH_PP
IRR_CLASS_OLD_LM_TRADEOFF
IRR_ADAPTION
IRR_NO_TRUTH_SPLIT
IRR_NO_TRUTH
IRR_UNKNOWN
IRR_NUM_REASONS

Definition at line 51 of file blamer.h.

                           {
  // The text recorded in best choice == truth text
  IRR_CORRECT,
  // Either: Top choice is incorrect and is a dictionary word (language model
  // is unlikely to help correct such errors, so blame the classifier).
  // Or: the correct unichar was not included in shortlist produced by the
  // classifier at all.
  IRR_CLASSIFIER,
  // Chopper have not found one or more splits that correspond to the correct
  // character bounding boxes recorded in BlamerBundle::truth_word.
  IRR_CHOPPER,
  // Classifier did include correct unichars for each blob in the correct
  // segmentation, however its rating could have been too bad to allow the
  // language model to pull out the correct choice. On the other hand the
  // strength of the language model might have been too weak to favor the
  // correct answer, this we call this case a classifier-language model
  // tradeoff error.
  IRR_CLASS_LM_TRADEOFF,
  // Page layout failed to produce the correct bounding box. Blame page layout
  // if the truth was not found for the word, which implies that the bounding
  // box of the word was incorrect (no truth word had a similar bounding box).
  IRR_PAGE_LAYOUT,
  // SegSearch heuristic prevented one or more blobs from the correct
  // segmentation state to be classified (e.g. the blob was too wide).
  IRR_SEGSEARCH_HEUR,
  // The correct segmentaiton state was not explored because of poor SegSearch
  // pain point prioritization. We blame SegSearch pain point prioritization
  // if the best rating of a choice constructed from correct segmentation is
  // better than that of the best choice (i.e. if we got to explore the correct
  // segmentation state, language model would have picked the correct choice).
  IRR_SEGSEARCH_PP,
  // Same as IRR_CLASS_LM_TRADEOFF, but used when we only run chopper on a word,
  // and thus use the old language model (permuters).
  // TODO(antonova): integrate the new language mode with chopper
  IRR_CLASS_OLD_LM_TRADEOFF,
  // If there is an incorrect adaptive template match with a better score than
  // a correct one (either pre-trained or adapted), mark this as adaption error.
  IRR_ADAPTION,
  // split_and_recog_word() failed to find a suitable split in truth.
  IRR_NO_TRUTH_SPLIT,
  // Truth is not available for this word (e.g. when words in corrected content
  // file are turned into ~~~~ because an appropriate alignment was not found.
  IRR_NO_TRUTH,
  // The text recorded in best choice != truth text, but none of the above
  // reasons are set.
  IRR_UNKNOWN,
 
  IRR_NUM_REASONS
};