tesseract  v4.0.0-17-g361f3264
Open Source OCR Engine
tesseract::LanguageModel Member List

This is the complete list of members for tesseract::LanguageModel, including all inherited members.

acceptable_choice_found_tesseract::LanguageModelprotected
AcceptableChoiceFound()tesseract::LanguageModelinline
AcceptablePath(const ViterbiStateEntry &vse)tesseract::LanguageModelinlineprotected
AddViterbiStateEntry(LanguageModelFlagsType top_choice_flags, float denom, bool word_end, int curr_col, int curr_row, BLOB_CHOICE *b, LanguageModelState *curr_state, ViterbiStateEntry *parent_vse, LMPainPoints *pain_points, WERD_RES *word_res, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle)tesseract::LanguageModelprotected
beginning_active_dawgs_tesseract::LanguageModelprotected
BOOL_VAR_H(language_model_ngram_on, false, "Turn on/off the use of character ngram model")tesseract::LanguageModel
BOOL_VAR_H(language_model_ngram_use_only_first_uft8_step, false, "Use only the first UTF8 step of the given string" " when computing log probabilities")tesseract::LanguageModel
BOOL_VAR_H(language_model_ngram_space_delimited_language, true, "Words are delimited by space")tesseract::LanguageModel
BOOL_VAR_H(language_model_use_sigmoidal_certainty, false, "Use sigmoidal score for certainty")tesseract::LanguageModel
CertaintyScore(float cert)tesseract::LanguageModelinlineprotected
ComputeAdjustedPathCost(ViterbiStateEntry *vse)tesseract::LanguageModelprotected
ComputeAdjustment(int num_problems, float penalty)tesseract::LanguageModelinlineprotected
ComputeAssociateStats(int col, int row, float max_char_wh_ratio, ViterbiStateEntry *parent_vse, WERD_RES *word_res, AssociateStats *associate_stats)tesseract::LanguageModelinlineprotected
ComputeConsistencyAdjustment(const LanguageModelDawgInfo *dawg_info, const LMConsistencyInfo &consistency_info)tesseract::LanguageModelinlineprotected
ComputeDenom(BLOB_CHOICE_LIST *curr_list)tesseract::LanguageModelprotected
ComputeNgramCost(const char *unichar, float certainty, float denom, const char *context, int *unichar_step_len, bool *found_small_prob, float *ngram_prob)tesseract::LanguageModelprotected
ConstructWord(ViterbiStateEntry *vse, WERD_RES *word_res, DANGERR *fixpt, BlamerBundle *blamer_bundle, bool *truth_path)tesseract::LanguageModelprotected
correct_segmentation_explored_tesseract::LanguageModelprotected
dawg_args_tesseract::LanguageModelprotected
dict_tesseract::LanguageModelprotected
double_VAR_H(language_model_ngram_small_prob, 0.000001, "To avoid overly small denominators use this as the floor" " of the probability returned by the ngram model")tesseract::LanguageModel
double_VAR_H(language_model_ngram_nonmatch_score, -40.0, "Average classifier score of a non-matching unichar")tesseract::LanguageModel
double_VAR_H(language_model_ngram_scale_factor, 0.03, "Strength of the character ngram model relative to the" " character classifier ")tesseract::LanguageModel
double_VAR_H(language_model_ngram_rating_factor, 16.0, "Factor to bring log-probs into the same range as ratings" " when multiplied by outline length ")tesseract::LanguageModel
double_VAR_H(language_model_penalty_non_freq_dict_word, 0.1, "Penalty for words not in the frequent word dictionary")tesseract::LanguageModel
double_VAR_H(language_model_penalty_non_dict_word, 0.15, "Penalty for non-dictionary words")tesseract::LanguageModel
double_VAR_H(language_model_penalty_punc, 0.2, "Penalty for inconsistent punctuation")tesseract::LanguageModel
double_VAR_H(language_model_penalty_case, 0.1, "Penalty for inconsistent case")tesseract::LanguageModel
double_VAR_H(language_model_penalty_script, 0.5, "Penalty for inconsistent script")tesseract::LanguageModel
double_VAR_H(language_model_penalty_chartype, 0.3, "Penalty for inconsistent character type")tesseract::LanguageModel
double_VAR_H(language_model_penalty_font, 0.00, "Penalty for inconsistent font")tesseract::LanguageModel
double_VAR_H(language_model_penalty_spacing, 0.05, "Penalty for inconsistent spacing")tesseract::LanguageModel
double_VAR_H(language_model_penalty_increment, 0.01, "Penalty increment")tesseract::LanguageModel
ExtractFeaturesFromPath(const ViterbiStateEntry &vse, float features[])tesseract::LanguageModelstatic
FillConsistencyInfo(int curr_col, bool word_end, BLOB_CHOICE *b, ViterbiStateEntry *parent_vse, WERD_RES *word_res, LMConsistencyInfo *consistency_info)tesseract::LanguageModelprotected
fixed_pitch_tesseract::LanguageModelprotected
fontinfo_table_tesseract::LanguageModelprotected
GenerateDawgInfo(bool word_end, int curr_col, int curr_row, const BLOB_CHOICE &b, const ViterbiStateEntry *parent_vse)tesseract::LanguageModelprotected
GenerateNgramInfo(const char *unichar, float certainty, float denom, int curr_col, int curr_row, float outline_length, const ViterbiStateEntry *parent_vse)tesseract::LanguageModelprotected
GenerateTopChoiceInfo(ViterbiStateEntry *new_vse, const ViterbiStateEntry *parent_vse, LanguageModelState *lms)tesseract::LanguageModelprotected
GetNextParentVSE(bool just_classified, bool mixed_alnum, const BLOB_CHOICE *bc, LanguageModelFlagsType blob_choice_flags, const UNICHARSET &unicharset, WERD_RES *word_res, ViterbiStateEntry_IT *vse_it, LanguageModelFlagsType *top_choice_flags) consttesseract::LanguageModelprotected
getParamsModel()tesseract::LanguageModelinline
GetTopLowerUpperDigit(BLOB_CHOICE_LIST *curr_list, BLOB_CHOICE **first_lower, BLOB_CHOICE **first_upper, BLOB_CHOICE **first_digit) consttesseract::LanguageModelprotected
InitForWord(const WERD_CHOICE *prev_word, bool fixed_pitch, float max_char_wh_ratio, float rating_cert_scale)tesseract::LanguageModel
INT_VAR_H(language_model_debug_level, 0, "Language model debug level")tesseract::LanguageModel
INT_VAR_H(language_model_ngram_order, 8, "Maximum order of the character ngram model")tesseract::LanguageModel
INT_VAR_H(language_model_viterbi_list_max_num_prunable, 10, "Maximum number of prunable (those for which PrunablePath() is" " true) entries in each viterbi list recorded in BLOB_CHOICEs")tesseract::LanguageModel
INT_VAR_H(language_model_viterbi_list_max_size, 500, "Maximum size of viterbi lists recorded in BLOB_CHOICEs")tesseract::LanguageModel
INT_VAR_H(language_model_min_compound_length, 3, "Minimum length of compound words")tesseract::LanguageModel
INT_VAR_H(wordrec_display_segmentations, 0, "Display Segmentations")tesseract::LanguageModel
kDigitFlagtesseract::LanguageModelstatic
kLowerCaseFlagtesseract::LanguageModelstatic
kMaxAvgNgramCosttesseract::LanguageModelstatic
kSmallestRatingFlagtesseract::LanguageModelstatic
kUpperCaseFlagtesseract::LanguageModelstatic
kXhtConsistentFlagtesseract::LanguageModelstatic
LanguageModel(const UnicityTable< FontInfo > *fontinfo_table, Dict *dict)tesseract::LanguageModel
max_char_wh_ratio_tesseract::LanguageModelprotected
params_model_tesseract::LanguageModelprotected
prev_word_str_tesseract::LanguageModelprotected
prev_word_unichar_step_len_tesseract::LanguageModelprotected
PrunablePath(const ViterbiStateEntry &vse)tesseract::LanguageModelinlineprotected
rating_cert_scale_tesseract::LanguageModelprotected
SetAcceptableChoiceFound(bool val)tesseract::LanguageModelinline
SetTopParentLowerUpperDigit(LanguageModelState *parent_node) consttesseract::LanguageModelprotected
UpdateBestChoice(ViterbiStateEntry *vse, LMPainPoints *pain_points, WERD_RES *word_res, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle)tesseract::LanguageModelprotected
UpdateState(bool just_classified, int curr_col, int curr_row, BLOB_CHOICE_LIST *curr_list, LanguageModelState *parent_node, LMPainPoints *pain_points, WERD_RES *word_res, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle)tesseract::LanguageModel
very_beginning_active_dawgs_tesseract::LanguageModelprotected
~LanguageModel()tesseract::LanguageModel