tesseract::Wordrec Class Reference

#include <wordrec.h>

Inheritance diagram for tesseract::Wordrec:

List of all members.

Public Member Functions

Wordrec ()

~Wordrec ()

void save_summary (inT32 elapsed_time)

int end_recog ()

BLOB_CHOICE_LIST_VECTOR * evaluate_chunks (CHUNKS_RECORD *chunks_record, SEARCH_STATE search_state)

void update_ratings (const BLOB_CHOICE_LIST_VECTOR &new_choices, const CHUNKS_RECORD *chunks_record, const SEARCH_STATE search_state)

void expand_node (FLOAT32 worst_priority, CHUNKS_RECORD *chunks_record, SEARCH_RECORD *the_search)

BLOB_CHOICE_LIST * join_blobs_and_classify (TBLOB *blobs, SEAMS seam_list, int x, int y, int fx, const MATRIX *ratings, BLOB_CHOICE_LIST_VECTOR *old_choices)

MATRIX * word_associator (TBLOB *blobs, SEAMS seams, STATE *state, int fxid, WERD_CHOICE *best_choice, WERD_CHOICE *raw_choice, char *correct, DANGERR *fixpt, STATE *best_state)

void mfeature_init ()

BLOB_CHOICE_LIST * classify_piece (TBLOB *pieces, SEAMS seams, inT16 start, inT16 end)

BLOB_CHOICE_LIST * get_piece_rating (MATRIX *ratings, TBLOB *blobs, SEAMS seams, inT16 start, inT16 end)

void dj_statistics (FILE *File)

void dj_cleanup ()

FLOAT32 prioritize_state (CHUNKS_RECORD *chunks_record, SEARCH_RECORD *the_search)

FLOAT32 width_priority (CHUNKS_RECORD *chunks_record, STATE *state, int num_joints)

FLOAT32 seamcut_priority (SEAMS seams, STATE *state, int num_joints)

FLOAT32 rating_priority (CHUNKS_RECORD *chunks_record, STATE *state, int num_joints)

program_editup

Initialize all the things in the program that need to be initialized. init_permute determines whether to initialize the permute functions and Dawg models.

void program_editup (const char *textbase, bool init_permute)

cc_recog

Recognize a word.

BLOB_CHOICE_LIST_VECTOR * cc_recog (TWERD *tessword, WERD_CHOICE *best_choice, WERD_CHOICE *best_raw_choice, BOOL8 tester, BOOL8 trainer, bool last_word_on_line)

program_editdown

This function holds any nessessary post processing for the Wise Owl program.

void program_editdown (inT32 elasped_time)

set_pass1

Get ready to do some pass 1 stuff.

void set_pass1 ()

set_pass2

Get ready to do some pass 2 stuff.

void set_pass2 ()

start_recog

Startup recog program ready to recognize words.

int start_recog (const char *textbase)

call_matcher

Called from Tess with a blob in tess form. Convert the blob to editor form. Call the matcher setup by the segmenter in tess_matcher. Convert the output choices back to tess form.

BLOB_CHOICE_LIST * call_matcher (TBLOB *ptblob, TBLOB *tessblob, TBLOB *ntblob, void *, TEXTROW *)

program_init

Initialize all the things in the program that need to be initialized.

void program_init ()

classify_blob

Classify the this blob if it is not already recorded in the match table. Attempt to recognize this blob as a character. The recognition rating for this blob will be stored as a part of the blob. This value will also be returned to the caller.

Parameters:

	pblob	Previous blob
	blob	Current blob
	nlob	Next blob
	row	The row to process
	string	The string to display in ScrollView
	color	The colour to use when displayed with ScrollView

BLOB_CHOICE_LIST * classify_blob (TBLOB *pblob, TBLOB *blob, TBLOB *nblob, TEXTROW *row, const char *string, C_COL color)

update_blob_classifications

For each blob in the given word update match_table with the corresponding BLOB_CHOICES_LIST from choices.

void update_blob_classifications (TWERD *word, const BLOB_CHOICE_LIST_VECTOR &choices)

evaluate_state

Evaluate the segmentation that is represented by this state in the best first search. Add this state to the "states_seen" list.

inT16 evaluate_state (CHUNKS_RECORD *chunks_record, SEARCH_RECORD *the_search, DANGERR *fixpt)

BLOB_CHOICE_LIST_VECTOR * rebuild_current_state (TBLOB *blobs, SEAMS seam_list, STATE *state, BLOB_CHOICE_LIST_VECTOR *char_choices, int fx, bool force_rebuild, const WERD_CHOICE &best_choice, const MATRIX *ratings)

best_first_search

Find the best segmentation by doing a best first search of the solution space.

void best_first_search (CHUNKS_RECORD *chunks_record, WERD_CHOICE *best_choice, WERD_CHOICE *raw_choice, STATE *state, DANGERR *fixpt, STATE *best_state)

improve_one_blob

Start with the current word of blobs and its classification. Find the worst blobs and try to divide it up to improve the ratings.

bool improve_one_blob (TWERD *word, BLOB_CHOICE_LIST_VECTOR *char_choices, int fx, inT32 *blob_number, SEAMS *seam_list, DANGERR *fixpt, bool split_next_to_fragment)

modify_blob_choice

Takes a blob and its chop index, converts that chop index to a unichar_id, and stores the chop index in place of the blob's original unichar_id.

void modify_blob_choice (BLOB_CHOICE_LIST *answer, int chop_index)

chop_one_blob

Start with the current one-blob word and its classification. Find the worst blobs and try to divide it up to improve the ratings. Used for testing chopper.

bool chop_one_blob (TWERD *word, BLOB_CHOICE_LIST_VECTOR *char_choices, inT32 *blob_number, SEAMS *seam_list, int *right_chop_index)

chop_word_main

Classify the blobs in this word and permute the results. Find the worst blob in the word and chop it up. Continue this process until a good answer has been found or all the blobs have been chopped up enough. Return the word level ratings.

BLOB_CHOICE_LIST_VECTOR * chop_word_main (register TWERD *word, int fx, WERD_CHOICE *best_choice, WERD_CHOICE *raw_choice, BOOL8 tester, BOOL8 trainer)

improve_by_chopping

Start with the current word of blobs and its classification. Find the worst blobs and try to divide them up to improve the ratings. As long as ratings are produced by the new blob splitting. When all the splitting has been accomplished all the ratings memory is reclaimed.

void improve_by_chopping (register TWERD *word, BLOB_CHOICE_LIST_VECTOR *char_choices, int fx, STATE *best_state, WERD_CHOICE *best_choice, WERD_CHOICE *raw_choice, SEAMS *seam_list, DANGERR *fixpt, STATE *chop_states, inT32 *state_count)

inT16 select_blob_to_split (const BLOB_CHOICE_LIST_VECTOR &char_choices, float rating_ceiling, bool split_next_to_fragment)

dict_word()

Test the dictionaries, returning NO_PERM (0) if not found, or one of the PermuterType values if found, according to the dictionary.

int dict_word (const WERD_CHOICE &word)

Public Attributes

DENORM * tess_denorm

WERD * tess_word

Constructor & Destructor Documentation

tesseract::Wordrec::Wordrec ( )

tesseract::Wordrec::~Wordrec ( )

Member Function Documentation

void tesseract::Wordrec::best_first_search	(	CHUNKS_RECORD *	chunks_record,
		WERD_CHOICE *	best_choice,
		WERD_CHOICE *	raw_choice,
		STATE *	state,
		DANGERR *	fixpt,
		STATE *	best_state
	)

BLOB_CHOICE_LIST * tesseract::Wordrec::call_matcher	(	TBLOB *	ptblob,
		TBLOB *	tessblob,
		TBLOB *	ntblob,
		void *	,
		TEXTROW *
	)

BLOB_CHOICE_LIST_VECTOR * tesseract::Wordrec::cc_recog	(	TWERD *	tessword,
		WERD_CHOICE *	best_choice,
		WERD_CHOICE *	best_raw_choice,
		BOOL8	tester,
		BOOL8	trainer,
		bool	last_word_on_line
	)

bool tesseract::Wordrec::chop_one_blob	(	TWERD *	word,
		BLOB_CHOICE_LIST_VECTOR *	char_choices,
		inT32 *	blob_number,
		SEAMS *	seam_list,
		int *	right_chop_index
	)

BLOB_CHOICE_LIST_VECTOR * tesseract::Wordrec::chop_word_main	(	register TWERD *	word,
		int	fx,
		WERD_CHOICE *	best_choice,
		WERD_CHOICE *	raw_choice,
		BOOL8	tester,
		BOOL8	trainer
	)

BLOB_CHOICE_LIST * tesseract::Wordrec::classify_blob	(	TBLOB *	pblob,
		TBLOB *	blob,
		TBLOB *	nblob,
		TEXTROW *	row,
		const char *	string,
		C_COL	color
	)

BLOB_CHOICE_LIST * tesseract::Wordrec::classify_piece	(	TBLOB *	pieces,
		SEAMS	seams,
		inT16	start,
		inT16	end
	)

int tesseract::Wordrec::dict_word ( const WERD_CHOICE & word )

void tesseract::Wordrec::dj_cleanup ( ) [inline]

void tesseract::Wordrec::dj_statistics ( FILE * File ) [inline]

int tesseract::Wordrec::end_recog ( )

BLOB_CHOICE_LIST_VECTOR * tesseract::Wordrec::evaluate_chunks	(	CHUNKS_RECORD *	chunks_record,
		SEARCH_STATE	search_state
	)

evaluate_chunks

A particular word level segmentation has been chosen. Evaluation this to find the word list that corresponds to it.

inT16 tesseract::Wordrec::evaluate_state	(	CHUNKS_RECORD *	chunks_record,
		SEARCH_RECORD *	the_search,
		DANGERR *	fixpt
	)

void tesseract::Wordrec::expand_node	(	FLOAT32	worst_priority,
		CHUNKS_RECORD *	chunks_record,
		SEARCH_RECORD *	the_search
	)

BLOB_CHOICE_LIST * tesseract::Wordrec::get_piece_rating	(	MATRIX *	ratings,
		TBLOB *	blobs,
		SEAMS	seams,
		inT16	start,
		inT16	end
	)

void tesseract::Wordrec::improve_by_chopping	(	register TWERD *	word,
		BLOB_CHOICE_LIST_VECTOR *	char_choices,
		int	fx,
		STATE *	best_state,
		WERD_CHOICE *	best_choice,
		WERD_CHOICE *	raw_choice,
		SEAMS *	seam_list,
		DANGERR *	fixpt,
		STATE *	chop_states,
		inT32 *	state_count
	)

bool tesseract::Wordrec::improve_one_blob	(	TWERD *	word,
		BLOB_CHOICE_LIST_VECTOR *	char_choices,
		int	fx,
		inT32 *	blob_number,
		SEAMS *	seam_list,
		DANGERR *	fixpt,
		bool	split_next_to_fragment
	)

BLOB_CHOICE_LIST * tesseract::Wordrec::join_blobs_and_classify	(	TBLOB *	blobs,
		SEAMS	seam_list,
		int	x,
		int	y,
		int	fx,
		const MATRIX *	ratings,
		BLOB_CHOICE_LIST_VECTOR *	old_choices
	)

void tesseract::Wordrec::mfeature_init ( )

void tesseract::Wordrec::modify_blob_choice	(	BLOB_CHOICE_LIST *	answer,
		int	chop_index
	)

FLOAT32 tesseract::Wordrec::prioritize_state	(	CHUNKS_RECORD *	chunks_record,
		SEARCH_RECORD *	the_search
	)

void tesseract::Wordrec::program_editdown ( inT32 elasped_time )

void tesseract::Wordrec::program_editup	(	const char *	textbase,
		bool	init_permute
	)

void tesseract::Wordrec::program_init ( )

FLOAT32 tesseract::Wordrec::rating_priority	(	CHUNKS_RECORD *	chunks_record,
		STATE *	state,
		int	num_joints
	)

BLOB_CHOICE_LIST_VECTOR * tesseract::Wordrec::rebuild_current_state	(	TBLOB *	blobs,
		SEAMS	seam_list,
		STATE *	state,
		BLOB_CHOICE_LIST_VECTOR *	old_choices,
		int	fx,
		bool	force_rebuild,
		const WERD_CHOICE &	best_choice,
		const MATRIX *	ratings
	)

rebuild_current_state

Evaluate the segmentation that is represented by this state in the best first search. Add this state to the "states_seen" list.

void tesseract::Wordrec::save_summary ( inT32 elapsed_time )

FLOAT32 tesseract::Wordrec::seamcut_priority	(	SEAMS	seams,
		STATE *	state,
		int	num_joints
	)

inT16 tesseract::Wordrec::select_blob_to_split	(	const BLOB_CHOICE_LIST_VECTOR &	char_choices,
		float	rating_ceiling,
		bool	split_next_to_fragment
	)

void tesseract::Wordrec::set_pass1 ( )

void tesseract::Wordrec::set_pass2 ( )

int tesseract::Wordrec::start_recog ( const char * textbase )

void tesseract::Wordrec::update_blob_classifications	(	TWERD *	word,
		const BLOB_CHOICE_LIST_VECTOR &	choices
	)

void tesseract::Wordrec::update_ratings	(	const BLOB_CHOICE_LIST_VECTOR &	new_choices,
		const CHUNKS_RECORD *	chunks_record,
		const SEARCH_STATE	search_state
	)

FLOAT32 tesseract::Wordrec::width_priority	(	CHUNKS_RECORD *	chunks_record,
		STATE *	state,
		int	num_joints
	)

MATRIX * tesseract::Wordrec::word_associator	(	TBLOB *	blobs,
		SEAMS	seams,
		STATE *	state,
		int	fxid,
		WERD_CHOICE *	best_choice,
		WERD_CHOICE *	raw_choice,
		char *	correct,
		DANGERR *	fixpt,
		STATE *	best_state
	)

Member Data Documentation

DENORM* tesseract::Wordrec::tess_denorm

POLY_MATCHER tesseract::Wordrec::tess_matcher

POLY_TESTER tesseract::Wordrec::tess_tester

POLY_TESTER tesseract::Wordrec::tess_trainer

WERD* tesseract::Wordrec::tess_word

The documentation for this class was generated from the following files:

tesseract-doxygen/wordrec/wordrec.h
tesseract-doxygen/wordrec/bestfirst.cpp
tesseract-doxygen/wordrec/chopper.cpp
tesseract-doxygen/wordrec/heuristic.cpp
tesseract-doxygen/wordrec/metrics.cpp
tesseract-doxygen/wordrec/mfvars.cpp
tesseract-doxygen/wordrec/pieces.cpp
tesseract-doxygen/wordrec/tessinit.cpp
tesseract-doxygen/wordrec/tface.cpp
tesseract-doxygen/wordrec/wordclass.cpp
tesseract-doxygen/wordrec/wordrec.cpp