This is the complete list of members for tesseract::Tesseract, including all inherited members.
acceptable_number_string(const char *s, const char *lengths) | tesseract::Tesseract | |
acceptable_word_string(const UNICHARSET &char_set, const char *s, const char *lengths) | tesseract::Tesseract | |
AdaptableWord(WERD_RES *word) | tesseract::Classify | |
AdaptedTemplates | tesseract::Classify | |
AdaptiveClassifier(TBLOB *Blob, BLOB_CHOICE_LIST *Choices) | tesseract::Classify | |
AdaptiveClassifierIsEmpty() const | tesseract::Classify | inline |
AdaptiveClassifierIsFull() const | tesseract::Classify | inline |
AdaptToChar(TBLOB *Blob, CLASS_ID ClassId, int FontinfoId, float Threshold, ADAPT_TEMPLATES adaptive_templates) | tesseract::Classify | |
add_point_to_list(PointHeap *point_heap, EDGEPT *point) | tesseract::Wordrec | |
add_seam_to_queue(float new_priority, SEAM *new_seam, SeamQueue *seams) | tesseract::Wordrec | |
AddLargeSpeckleTo(int blob_length, BLOB_CHOICE_LIST *choices) | tesseract::Classify | |
AddNewResult(const UnicharRating &new_result, ADAPT_RESULTS *results) | tesseract::Classify | |
AllConfigsOff | tesseract::Classify | |
AllConfigsOn | tesseract::Classify | |
AllProtosOn | tesseract::Classify | |
alpha_count(const char *word, const char *word_lengths) | tesseract::Tesseract | |
AmbigClassifier(const GenericVector< INT_FEATURE_STRUCT > &int_features, const INT_FX_RESULT_STRUCT &fx_info, const TBLOB *blob, INT_TEMPLATES templates, ADAPT_CLASS *classes, UNICHAR_ID *ambiguities, ADAPT_RESULTS *results) | tesseract::Classify | |
ambigs_classify_and_output(const char *label, PAGE_RES_IT *pr_it, FILE *output_file) | tesseract::Tesseract | |
ambigs_debug_level | tesseract::CCUtil | |
angle_change(EDGEPT *point1, EDGEPT *point2, EDGEPT *point3) | tesseract::Wordrec | |
AnyLSTMLang() const | tesseract::Tesseract | inline |
AnyTessLang() const | tesseract::Tesseract | inline |
ApplyBoxes(const STRING &fname, bool find_segmentation, BLOCK_LIST *block_list) | tesseract::Tesseract | |
ApplyBoxTraining(const STRING &fontname, PAGE_RES *page_res) | tesseract::Tesseract | |
AssignDiacriticsToNewBlobs(const GenericVector< C_OUTLINE *> &outlines, int pass, WERD *real_word, PAGE_RES_IT *pr_it, GenericVector< bool > *word_wanted, GenericVector< C_BLOB *> *target_blobs) | tesseract::Tesseract | |
AssignDiacriticsToOverlappingBlobs(const GenericVector< C_OUTLINE *> &outlines, int pass, WERD *real_word, PAGE_RES_IT *pr_it, GenericVector< bool > *word_wanted, GenericVector< bool > *overlapped_any_blob, GenericVector< C_BLOB *> *target_blobs) | tesseract::Tesseract | |
attempt_blob_chop(TWERD *word, TBLOB *blob, int32_t blob_number, bool italic_blob, const GenericVector< SEAM *> &seams) | tesseract::Wordrec | |
AutoPageSeg(PageSegMode pageseg_mode, BLOCK_LIST *blocks, TO_BLOCK_LIST *to_blocks, BLOBNBOX_LIST *diacritic_blobs, Tesseract *osd_tess, OSResults *osr) | tesseract::Tesseract | |
backup_config_file_ | tesseract::Tesseract | private |
BackupAdaptedTemplates | tesseract::Classify | |
BaselineClassifier(TBLOB *Blob, const GenericVector< INT_FEATURE_STRUCT > &int_features, const INT_FX_RESULT_STRUCT &fx_info, ADAPT_TEMPLATES Templates, ADAPT_RESULTS *Results) | tesseract::Classify | |
BelievableSuperscript(bool debug, const WERD_RES &word, float certainty_threshold, int *left_ok, int *right_ok) const | tesseract::Tesseract | |
BestPix() const | tesseract::Tesseract | inline |
bigram_correction_pass(PAGE_RES *page_res) | tesseract::Tesseract | |
blame_reasons_ | tesseract::Wordrec | |
blamer_pass(PAGE_RES *page_res) | tesseract::Tesseract | |
blob_feature_display(PAGE_RES *page_res, const TBOX &selection_box) | tesseract::Tesseract | |
blob_noise_score(TBLOB *blob) | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_resegment_from_boxes, false, "Take segmentation and labeling from box file") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_resegment_from_line_boxes, false, "Conversion of word/line box file to char box file") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_train_from_boxes, false, "Generate training data from boxed chars") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_make_boxes_from_boxes, false, "Generate more boxes from boxed chars") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_train_line_recognizer, false, "Break input into lines and remap boxes if present") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_dump_pageseg_images, false, "Dump intermediate images made during page segmentation") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_ambigs_training, false, "Perform training for ambiguities") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_adaption_debug, false, "Generate and print debug information for adaption") | tesseract::Tesseract | |
BOOL_VAR_H(applybox_learn_chars_and_char_frags_mode, false, "Learn both character fragments (as is done in the" " special low exposure mode) as well as unfragmented" " characters.") | tesseract::Tesseract | |
BOOL_VAR_H(applybox_learn_ngrams_mode, false, "Each bounding box is assumed to contain ngrams. Only" " learn the ngrams whose outlines overlap horizontally.") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_display_outwords, false, "Draw output words") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_dump_choices, false, "Dump char choices") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_timing_debug, false, "Print timing stats") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_fix_fuzzy_spaces, true, "Try to improve fuzzy spaces") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_unrej_any_wd, false, "Don't bother with word plausibility") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_fix_hyphens, true, "Crunch double hyphens?") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_redo_xheight, true, "Check/Correct x-height") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_enable_doc_dict, true, "Add words to the document dictionary") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_debug_fonts, false, "Output font info per char") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_debug_block_rejection, false, "Block and Row stats") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_enable_bigram_correction, true, "Enable correction based on the word bigram dictionary.") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_enable_dict_correction, false, "Enable single word correction based on the dictionary.") | tesseract::Tesseract | |
BOOL_VAR_H(enable_noise_removal, true, "Remove and conditionally reassign small outlines when they" " confuse layout analysis, determining diacritics vs noise") | tesseract::Tesseract | |
BOOL_VAR_H(debug_acceptable_wds, false, "Dump word pass/fail chk") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_minimal_rej_pass1, false, "Do minimal rejection on pass 1 output") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_test_adaption, false, "Test adaption criteria") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_matcher_log, false, "Log matcher activity") | tesseract::Tesseract | |
BOOL_VAR_H(test_pt, false, "Test for point") | tesseract::Tesseract | |
BOOL_VAR_H(paragraph_text_based, true, "Run paragraph detection on the post-text-recognition " "(more accurate)") | tesseract::Tesseract | |
BOOL_VAR_H(lstm_use_matrix, 1, "Use ratings matrix/beam searct with lstm") | tesseract::Tesseract | |
BOOL_VAR_H(docqual_excuse_outline_errs, false, "Allow outline errs in unrejection?") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_good_quality_unrej, true, "Reduce rejection on good docs") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_use_reject_spaces, true, "Reject spaces?") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_preserve_blk_rej_perfect_wds, true, "Only rej partially rejected words in block rejection") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_preserve_row_rej_perfect_wds, true, "Only rej partially rejected words in row rejection") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_dont_blkrej_good_wds, false, "Use word segmentation quality metric") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_dont_rowrej_good_wds, false, "Use word segmentation quality metric") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_row_rej_good_docs, true, "Apply row rejection to good docs") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_reject_bad_qual_wds, true, "Reject all bad quality wds") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_debug_doc_rejection, false, "Page stats") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_debug_quality_metrics, false, "Output data to debug file") | tesseract::Tesseract | |
BOOL_VAR_H(bland_unrej, false, "unrej potential with no checks") | tesseract::Tesseract | |
BOOL_VAR_H(unlv_tilde_crunching, false, "Mark v.bad words for tilde crunch") | tesseract::Tesseract | |
BOOL_VAR_H(hocr_font_info, false, "Add font info to hocr output") | tesseract::Tesseract | |
BOOL_VAR_H(crunch_early_merge_tess_fails, true, "Before word crunch?") | tesseract::Tesseract | |
BOOL_VAR_H(crunch_early_convert_bad_unlv_chs, false, "Take out ~^ early?") | tesseract::Tesseract | |
BOOL_VAR_H(crunch_terrible_garbage, true, "As it says") | tesseract::Tesseract | |
BOOL_VAR_H(crunch_pot_garbage, true, "POTENTIAL crunch garbage") | tesseract::Tesseract | |
BOOL_VAR_H(crunch_leave_ok_strings, true, "Don't touch sensible strings") | tesseract::Tesseract | |
BOOL_VAR_H(crunch_accept_ok, true, "Use acceptability in okstring") | tesseract::Tesseract | |
BOOL_VAR_H(crunch_leave_accept_strings, false, "Don't pot crunch sensible strings") | tesseract::Tesseract | |
BOOL_VAR_H(crunch_include_numerals, false, "Fiddle alpha figures") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_prefer_joined_punct, false, "Reward punctuation joins") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_write_block_separators, false, "Write block separators in output") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_write_rep_codes, false, "Write repetition char code") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_write_unlv, false, "Write .unlv output file") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_create_txt, false, "Write .txt output file") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_create_hocr, false, "Write .html hOCR output file") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_create_tsv, false, "Write .tsv output file") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_create_pdf, false, "Write .pdf output file") | tesseract::Tesseract | |
BOOL_VAR_H(textonly_pdf, false, "Create PDF with only one invisible text layer") | tesseract::Tesseract | |
BOOL_VAR_H(suspect_constrain_1Il, false, "UNLV keep 1Il chars rejected") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_minimal_rejection, false, "Only reject tess failures") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_zero_rejection, false, "Don't reject ANYTHING") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_word_for_word, false, "Make output have exactly one word per WERD") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_zero_kelvin_rejection, false, "Don't reject ANYTHING AT ALL") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_consistent_reps, true, "Force all rep chars the same") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_rejection_debug, false, "Adaption debug") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_flip_0O, true, "Contextual 0O O0 flips") | tesseract::Tesseract | |
BOOL_VAR_H(rej_trust_doc_dawg, false, "Use DOC dawg in 11l conf. detector") | tesseract::Tesseract | |
BOOL_VAR_H(rej_1Il_use_dict_word, false, "Use dictword test") | tesseract::Tesseract | |
BOOL_VAR_H(rej_1Il_trust_permuter_type, true, "Don't double check") | tesseract::Tesseract | |
BOOL_VAR_H(rej_use_tess_accepted, true, "Individual rejection control") | tesseract::Tesseract | |
BOOL_VAR_H(rej_use_tess_blanks, true, "Individual rejection control") | tesseract::Tesseract | |
BOOL_VAR_H(rej_use_good_perm, true, "Individual rejection control") | tesseract::Tesseract | |
BOOL_VAR_H(rej_use_sensible_wd, false, "Extend permuter check") | tesseract::Tesseract | |
BOOL_VAR_H(rej_alphas_in_number_perm, false, "Extend permuter check") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_create_boxfile, false, "Output text with boxes") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_write_images, false, "Capture the image from the IPE") | tesseract::Tesseract | |
BOOL_VAR_H(interactive_display_mode, false, "Run interactively?") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_override_permuter, true, "According to dict_word") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_use_primary_params_model, false, "In multilingual mode use params model of the primary language") | tesseract::Tesseract | |
BOOL_VAR_H(textord_tabfind_show_vlines, false, "Debug line finding") | tesseract::Tesseract | |
BOOL_VAR_H(textord_use_cjk_fp_model, FALSE, "Use CJK fixed pitch model") | tesseract::Tesseract | |
BOOL_VAR_H(poly_allow_detailed_fx, false, "Allow feature extractors to see the original outline") | tesseract::Tesseract | |
BOOL_VAR_H(tessedit_init_config_only, false, "Only initialize with the config file. Useful if the instance is " "not going to be used for OCR but say only for layout analysis.") | tesseract::Tesseract | |
BOOL_VAR_H(textord_equation_detect, false, "Turn on equation detector") | tesseract::Tesseract | |
BOOL_VAR_H(textord_tabfind_vertical_text, true, "Enable vertical detection") | tesseract::Tesseract | |
BOOL_VAR_H(textord_tabfind_force_vertical_text, false, "Force using vertical text page mode") | tesseract::Tesseract | |
BOOL_VAR_H(preserve_interword_spaces, false, "Preserve multiple interword spaces") | tesseract::Tesseract | |
tesseract::Wordrec::BOOL_VAR_H(merge_fragments_in_matrix, TRUE, "Merge the fragments in the ratings matrix and delete them " "after merging") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(wordrec_no_block, FALSE, "Don't output block information") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(wordrec_enable_assoc, TRUE, "Associator Enable") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(force_word_assoc, FALSE, "force associator to run regardless of what enable_assoc is." "This is used for CJK where component grouping is necessary.") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(fragments_guide_chopper, FALSE, "Use information from fragments to guide chopping process") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(chop_enable, 1, "Chop enable") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(chop_vertical_creep, 0, "Vertical creep") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(chop_new_seam_pile, 1, "Use new seam_pile") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(assume_fixed_pitch_char_segment, FALSE, "include fixed-pitch heuristics in char segmentation") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(wordrec_skip_no_truth_words, false, "Only run OCR for words that had truth recorded in BlamerBundle") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(wordrec_debug_blamer, false, "Print blamer debug messages") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(wordrec_run_blamer, false, "Try to set the blame for errors") | tesseract::Wordrec | |
tesseract::Wordrec::BOOL_VAR_H(save_alt_choices, true, "Save alternative paths found during chopping " "and segmentation search") | tesseract::Wordrec | |
tesseract::Classify::BOOL_VAR_H(allow_blob_division, true, "Use divisible blobs chopping") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(prioritize_division, FALSE, "Prioritize blob division over chopping") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(classify_enable_learning, true, "Enable adaptive classifier") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(tess_cn_matching, 0, "Character Normalized Matching") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(tess_bn_matching, 0, "Baseline Normalized Matching") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(classify_enable_adaptive_matcher, 1, "Enable adaptive classifier") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(classify_use_pre_adapted_templates, 0, "Use pre-adapted classifier templates") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(classify_save_adapted_templates, 0, "Save adapted templates to a file") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(classify_enable_adaptive_debugger, 0, "Enable match debugger") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(classify_nonlinear_norm, 0, "Non-linear stroke-density normalization") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(disable_character_fragments, TRUE, "Do not include character fragments in the" " results of the classifier") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(classify_debug_character_fragments, FALSE, "Bring up graphical debugging windows for fragments training") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(matcher_debug_separate_windows, FALSE, "Use two different windows for debugging the matching: " "One for the protos and one for the features.") | tesseract::Classify | |
tesseract::Classify::BOOL_VAR_H(classify_bln_numeric_mode, 0, "Assume the input is numbers [0-9].") | tesseract::Classify | |
break_noisiest_blob_word(WERD_RES_LIST &words) | tesseract::Tesseract | |
build_menu_new() | tesseract::Tesseract | |
call_matcher(TBLOB *blob) | tesseract::Wordrec | |
CallFillLattice(const MATRIX &ratings, const WERD_CHOICE_LIST &best_choices, const UNICHARSET &unicharset, BlamerBundle *blamer_bundle) | tesseract::Wordrec | inline |
cc_recog(WERD_RES *word) | tesseract::Wordrec | |
CCStruct()=default | tesseract::CCStruct | |
CCUtil() | tesseract::CCUtil | |
CharNormClassifier(TBLOB *blob, const TrainingSample &sample, ADAPT_RESULTS *adapt_results) | tesseract::Classify | |
CharNormTrainingSample(bool pruner_only, int keep_this, const TrainingSample &sample, GenericVector< UnicharRating > *results) | tesseract::Classify | |
check_debug_pt(WERD_RES *word, int location) | tesseract::Tesseract | |
choose_best_seam(SeamQueue *seam_queue, const SPLIT *split, PRIORITY priority, SEAM **seam_result, TBLOB *blob, SeamPile *seam_pile) | tesseract::Wordrec | |
chop_numbered_blob(TWERD *word, int32_t blob_number, bool italic_blob, const GenericVector< SEAM *> &seams) | tesseract::Wordrec | |
chop_one_blob(const GenericVector< TBOX > &boxes, const GenericVector< BLOB_CHOICE *> &blob_choices, WERD_RES *word_res, int *blob_number) | tesseract::Wordrec | |
chop_overlapping_blob(const GenericVector< TBOX > &boxes, bool italic_blob, WERD_RES *word_res, int *blob_number) | tesseract::Wordrec | |
chop_word_main(WERD_RES *word) | tesseract::Wordrec | |
ClassAndConfigIDToFontOrShapeID(int class_id, int int_result_config) const | tesseract::Classify | |
ClassIDToDebugStr(const INT_TEMPLATES_STRUCT *templates, int class_id, int config_id) const | tesseract::Classify | |
Classify() | tesseract::Classify | |
classify_blob(TBLOB *blob, const char *string, C_COL color, BlamerBundle *blamer_bundle) | tesseract::Wordrec | |
classify_piece(const GenericVector< SEAM *> &seams, int16_t start, int16_t end, const char *description, TWERD *word, BlamerBundle *blamer_bundle) | tesseract::Wordrec | virtual |
classify_word_and_language(int pass_n, PAGE_RES_IT *pr_it, WordData *word_data) | tesseract::Tesseract | |
classify_word_pass1(const WordData &word_data, WERD_RES **in_word, PointerVector< WERD_RES > *out_words) | tesseract::Tesseract | |
classify_word_pass2(const WordData &word_data, WERD_RES **in_word, PointerVector< WERD_RES > *out_words) | tesseract::Tesseract | |
ClassifyAsNoise(ADAPT_RESULTS *Results) | tesseract::Classify | |
ClassifyBlobAsWord(int pass_n, PAGE_RES_IT *pr_it, C_BLOB *blob, STRING *best_str, float *c2) | tesseract::Tesseract | |
ClassifyBlobPlusOutlines(const GenericVector< bool > &ok_outlines, const GenericVector< C_OUTLINE *> &outlines, int pass_n, PAGE_RES_IT *pr_it, C_BLOB *blob, STRING *best_str) | tesseract::Tesseract | |
Clear() | tesseract::Tesseract | |
ClearCharNormArray(uint8_t *char_norm_array) | tesseract::Classify | |
combine_seam(const SeamPile &seam_pile, const SEAM *seam, SeamQueue *seam_queue) | tesseract::Wordrec | |
ComputeCharNormArrays(FEATURE_STRUCT *norm_feature, INT_TEMPLATES_STRUCT *templates, uint8_t *char_norm_array, uint8_t *pruner_array) | tesseract::Classify | |
ComputeCompatibleXheight(WERD_RES *word_res, float *baseline_shift) | tesseract::Tesseract | |
ComputeCorrectedRating(bool debug, int unichar_id, double cp_rating, double im_rating, int feature_misses, int bottom, int top, int blob_length, int matcher_multiplier, const uint8_t *cn_factors) | tesseract::Classify | |
ComputeIntCharNormArray(const FEATURE_STRUCT &norm_feature, uint8_t *char_norm_array) | tesseract::Classify | |
ComputeIntFeatures(FEATURE_SET Features, INT_FEATURE_ARRAY IntFeatures) | tesseract::Classify | |
ComputeNormMatch(CLASS_ID ClassId, const FEATURE_STRUCT &feature, bool DebugMatch) | tesseract::Classify | |
convert_bad_unlv_chs(WERD_RES *word_res) | tesseract::Tesseract | |
ConvertMatchesToChoices(const DENORM &denorm, const TBOX &box, ADAPT_RESULTS *Results, BLOB_CHOICE_LIST *Choices) | tesseract::Classify | |
ConvertProto(PROTO Proto, int ProtoId, INT_CLASS Class) | tesseract::Classify | |
ConvertStringToUnichars(const char *utf8, GenericVector< UNICHAR_ID > *class_ids) | tesseract::Tesseract | |
CorrectClassifyWords(PAGE_RES *page_res) | tesseract::Tesseract | |
count_alphanums(const WERD_CHOICE &word) | tesseract::Tesseract | |
count_alphanums(WERD_RES *word) | tesseract::Tesseract | |
count_alphas(const WERD_CHOICE &word) | tesseract::Tesseract | |
count_outline_errs(char c, int16_t outline_count) | tesseract::Tesseract | |
CountMisfitTops(WERD_RES *word_res) | tesseract::Tesseract | |
CreateIntTemplates(CLASSES FloatProtos, const UNICHARSET &target_unicharset) | tesseract::Classify | |
CUtil()=default | tesseract::CUtil | |
datadir | tesseract::CCUtil | |
debug_word(PAGE_RES *page_res, const TBOX &selection_box) | tesseract::Tesseract | |
DebugAdaptiveClassifier(TBLOB *Blob, ADAPT_RESULTS *Results) | tesseract::Classify | |
deskew_ | tesseract::Tesseract | private |
dict_word(const WERD_CHOICE &word) | tesseract::Wordrec | |
dictionary_correction_pass(PAGE_RES *page_res) | tesseract::Tesseract | |
digit_or_numeric_punct(WERD_RES *word, int char_position) | tesseract::Tesseract | |
directory | tesseract::CCUtil | |
DisplayAdaptedChar(TBLOB *blob, INT_CLASS_STRUCT *int_class) | tesseract::Classify | |
do_re_display(bool(tesseract::Tesseract::*word_painter)(PAGE_RES_IT *pr_it)) | tesseract::Tesseract | |
DoAdaptiveMatch(TBLOB *Blob, ADAPT_RESULTS *Results) | tesseract::Classify | |
doc_and_block_rejection(PAGE_RES_IT &page_res_it, bool good_quality_doc) | tesseract::Tesseract | |
dont_allow_1Il(WERD_RES *word) | tesseract::Tesseract | |
DoSegSearch(WERD_RES *word_res) | tesseract::Wordrec | |
double_VAR_H(noise_cert_basechar, -8.0, "Hingepoint for base char certainty") | tesseract::Tesseract | |
double_VAR_H(noise_cert_disjoint, -2.5, "Hingepoint for disjoint certainty") | tesseract::Tesseract | |
double_VAR_H(noise_cert_punc, -2.5, "Threshold for new punc char certainty") | tesseract::Tesseract | |
double_VAR_H(noise_cert_factor, 0.375, "Scaling on certainty diff from Hingepoint") | tesseract::Tesseract | |
double_VAR_H(quality_rej_pc, 0.08, "good_quality_doc lte rejection limit") | tesseract::Tesseract | |
double_VAR_H(quality_blob_pc, 0.0, "good_quality_doc gte good blobs limit") | tesseract::Tesseract | |
double_VAR_H(quality_outline_pc, 1.0, "good_quality_doc lte outline error limit") | tesseract::Tesseract | |
double_VAR_H(quality_char_pc, 0.95, "good_quality_doc gte good char limit") | tesseract::Tesseract | |
double_VAR_H(test_pt_x, 99999.99, "xcoord") | tesseract::Tesseract | |
double_VAR_H(test_pt_y, 99999.99, "ycoord") | tesseract::Tesseract | |
double_VAR_H(tessedit_reject_doc_percent, 65.00, "%rej allowed before rej whole doc") | tesseract::Tesseract | |
double_VAR_H(tessedit_reject_block_percent, 45.00, "%rej allowed before rej whole block") | tesseract::Tesseract | |
double_VAR_H(tessedit_reject_row_percent, 40.00, "%rej allowed before rej whole row") | tesseract::Tesseract | |
double_VAR_H(tessedit_whole_wd_rej_row_percent, 70.00, "Number of row rejects in whole word rejects" "which prevents whole row rejection") | tesseract::Tesseract | |
double_VAR_H(tessedit_good_doc_still_rowrej_wd, 1.1, "rej good doc wd if more than this fraction rejected") | tesseract::Tesseract | |
double_VAR_H(quality_rowrej_pc, 1.1, "good_quality_doc gte good char limit") | tesseract::Tesseract | |
double_VAR_H(crunch_terrible_rating, 80.0, "crunch rating lt this") | tesseract::Tesseract | |
double_VAR_H(crunch_poor_garbage_cert, -9.0, "crunch garbage cert lt this") | tesseract::Tesseract | |
double_VAR_H(crunch_poor_garbage_rate, 60, "crunch garbage rating lt this") | tesseract::Tesseract | |
double_VAR_H(crunch_pot_poor_rate, 40, "POTENTIAL crunch rating lt this") | tesseract::Tesseract | |
double_VAR_H(crunch_pot_poor_cert, -8.0, "POTENTIAL crunch cert lt this") | tesseract::Tesseract | |
double_VAR_H(crunch_del_rating, 60, "POTENTIAL crunch rating lt this") | tesseract::Tesseract | |
double_VAR_H(crunch_del_cert, -10.0, "POTENTIAL crunch cert lt this") | tesseract::Tesseract | |
double_VAR_H(crunch_del_min_ht, 0.7, "Del if word ht lt xht x this") | tesseract::Tesseract | |
double_VAR_H(crunch_del_max_ht, 3.0, "Del if word ht gt xht x this") | tesseract::Tesseract | |
double_VAR_H(crunch_del_min_width, 3.0, "Del if word width lt xht x this") | tesseract::Tesseract | |
double_VAR_H(crunch_del_high_word, 1.5, "Del if word gt xht x this above bl") | tesseract::Tesseract | |
double_VAR_H(crunch_del_low_word, 0.5, "Del if word gt xht x this below bl") | tesseract::Tesseract | |
double_VAR_H(crunch_small_outlines_size, 0.6, "Small if lt xht x this") | tesseract::Tesseract | |
double_VAR_H(fixsp_small_outlines_size, 0.28, "Small if lt xht x this") | tesseract::Tesseract | |
double_VAR_H(superscript_worse_certainty, 2.0, "How many times worse " "certainty does a superscript position glyph need to be for us " "to try classifying it as a char with a different baseline?") | tesseract::Tesseract | |
double_VAR_H(superscript_bettered_certainty, 0.97, "What reduction in " "badness do we think sufficient to choose a superscript over " "what we'd thought. For example, a value of 0.6 means we want " "to reduce badness of certainty by 40%") | tesseract::Tesseract | |
double_VAR_H(superscript_scaledown_ratio, 0.4, "A superscript scaled down more than this is unbelievably " "small. For example, 0.3 means we expect the font size to " "be no smaller than 30% of the text line font size.") | tesseract::Tesseract | |
double_VAR_H(subscript_max_y_top, 0.5, "Maximum top of a character measured as a multiple of x-height " "above the baseline for us to reconsider whether it's a " "subscript.") | tesseract::Tesseract | |
double_VAR_H(superscript_min_y_bottom, 0.3, "Minimum bottom of a character measured as a multiple of " "x-height above the baseline for us to reconsider whether it's " "a superscript.") | tesseract::Tesseract | |
double_VAR_H(suspect_rating_per_ch, 999.9, "Don't touch bad rating limit") | tesseract::Tesseract | |
double_VAR_H(suspect_accept_rating, -999.9, "Accept good rating limit") | tesseract::Tesseract | |
double_VAR_H(tessedit_lower_flip_hyphen, 1.5, "Aspect ratio dot/hyphen test") | tesseract::Tesseract | |
double_VAR_H(tessedit_upper_flip_hyphen, 1.8, "Aspect ratio dot/hyphen test") | tesseract::Tesseract | |
double_VAR_H(rej_whole_of_mostly_reject_word_fract, 0.85, "if >this fract") | tesseract::Tesseract | |
double_VAR_H(min_orientation_margin, 7.0, "Min acceptable orientation margin") | tesseract::Tesseract | |
double_VAR_H(textord_tabfind_vertical_text_ratio, 0.5, "Fraction of textlines deemed vertical to use vertical page " "mode") | tesseract::Tesseract | |
double_VAR_H(textord_tabfind_aligned_gap_fraction, 0.75, "Fraction of height used as a minimum gap for aligned blobs.") | tesseract::Tesseract | |
tesseract::Wordrec::double_VAR_H(wordrec_worst_state, 1, "Worst segmentation state") | tesseract::Wordrec | |
tesseract::Wordrec::double_VAR_H(tessedit_certainty_threshold, -2.25, "Good blob limit") | tesseract::Wordrec | |
tesseract::Wordrec::double_VAR_H(chop_split_dist_knob, 0.5, "Split length adjustment") | tesseract::Wordrec | |
tesseract::Wordrec::double_VAR_H(chop_overlap_knob, 0.9, "Split overlap adjustment") | tesseract::Wordrec | |
tesseract::Wordrec::double_VAR_H(chop_center_knob, 0.15, "Split center adjustment") | tesseract::Wordrec | |
tesseract::Wordrec::double_VAR_H(chop_sharpness_knob, 0.06, "Split sharpness adjustment") | tesseract::Wordrec | |
tesseract::Wordrec::double_VAR_H(chop_width_change_knob, 5.0, "Width change adjustment") | tesseract::Wordrec | |
tesseract::Wordrec::double_VAR_H(chop_ok_split, 100.0, "OK split limit") | tesseract::Wordrec | |
tesseract::Wordrec::double_VAR_H(chop_good_split, 50.0, "Good split limit") | tesseract::Wordrec | |
tesseract::Wordrec::double_VAR_H(segsearch_max_char_wh_ratio, 2.0, "Maximum character width-to-height ratio") | tesseract::Wordrec | |
tesseract::Classify::double_VAR_H(classify_char_norm_range, 0.2, "Character Normalization Range ...") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(classify_min_norm_scale_x, 0.0, "Min char x-norm scale ...") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(classify_max_norm_scale_x, 0.325, "Max char x-norm scale ...") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(classify_min_norm_scale_y, 0.0, "Min char y-norm scale ...") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(classify_max_norm_scale_y, 0.325, "Max char y-norm scale ...") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(classify_max_rating_ratio, 1.5, "Veto ratio between classifier ratings") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(classify_max_certainty_margin, 5.5, "Veto difference between classifier certainties") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(matcher_good_threshold, 0.125, "Good Match (0-1)") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(matcher_reliable_adaptive_result, 0.0, "Great Match (0-1)") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(matcher_perfect_threshold, 0.02, "Perfect Match (0-1)") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(matcher_bad_match_pad, 0.15, "Bad Match Pad (0-1)") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(matcher_rating_margin, 0.1, "New template margin (0-1)") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(matcher_avg_noise_size, 12.0, "Avg. noise blob length: ") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(matcher_clustering_max_angle_delta, 0.015, "Maximum angle delta for prototype clustering") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(classify_misfit_junk_penalty, 0.0, "Penalty to apply when a non-alnum is vertically out of " "its expected textline position") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(rating_scale, 1.5, "Rating scaling factor") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(certainty_scale, 20.0, "Certainty scaling factor") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(tessedit_class_miss_scale, 0.00390625, "Scale factor for features not used") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(classify_adapted_pruning_factor, 2.5, "Prune poor adapted results this much worse than best result") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(classify_adapted_pruning_threshold, -1.0, "Threshold at which classify_adapted_pruning_factor starts") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(classify_character_fragments_garbage_certainty_threshold, -3.0, "Exclude fragments that do not match any whole character" " with at least this certainty") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(speckle_large_max_size, 0.30, "Max large speckle size") | tesseract::Classify | |
tesseract::Classify::double_VAR_H(speckle_rating_penalty, 10.0, "Penalty to add to worst rating for noise") | tesseract::Classify | |
dump_words(WERD_RES_LIST &perm, int16_t score, int16_t mode, bool improved) | tesseract::Tesseract | |
EnableLearning | tesseract::Classify | |
end_recog() | tesseract::Wordrec | |
end_tesseract() | tesseract::Tesseract | |
EndAdaptiveClassifier() | tesseract::Classify | |
equ_detect_ | tesseract::Tesseract | private |
eval_word_spacing(WERD_RES_LIST &word_res_list) | tesseract::Tesseract | |
ExpandShapesAndApplyCorrections(ADAPT_CLASS *classes, bool debug, int class_id, int bottom, int top, float cp_rating, int blob_length, int matcher_multiplier, const uint8_t *cn_factors, UnicharRating *int_result, ADAPT_RESULTS *final_results) | tesseract::Classify | |
ExtractFeatures(const TBLOB &blob, bool nonlinear_norm, GenericVector< INT_FEATURE_STRUCT > *bl_features, GenericVector< INT_FEATURE_STRUCT > *cn_features, INT_FX_RESULT_STRUCT *results, GenericVector< int > *outline_cn_counts) | tesseract::Classify | static |
ExtractIntCNFeatures(const TBLOB &blob, const INT_FX_RESULT_STRUCT &fx_info) | tesseract::Classify | |
ExtractIntGeoFeatures(const TBLOB &blob, const INT_FX_RESULT_STRUCT &fx_info) | tesseract::Classify | |
ExtractOutlineFeatures(TBLOB *Blob) | tesseract::Classify | |
ExtractPicoFeatures(TBLOB *Blob) | tesseract::Classify | |
failure_count(WERD_RES *word) | tesseract::Tesseract | |
feature_defs_ | tesseract::Classify | protected |
fill_filtered_fragment_list(BLOB_CHOICE_LIST *choices, int fragment_pos, int num_frag_parts, BLOB_CHOICE_LIST *filtered_choices) | tesseract::Wordrec | |
fill_lattice_ | tesseract::Wordrec | |
FillLattice(const MATRIX &ratings, const WERD_CHOICE_LIST &best_choices, const UNICHARSET &unicharset, BlamerBundle *blamer_bundle) | tesseract::Wordrec | |
FindSegmentation(const GenericVector< UNICHAR_ID > &target_text, WERD_RES *word_res) | tesseract::Tesseract | |
first_alphanum_index(const char *word, const char *word_lengths) | tesseract::Tesseract | |
first_alphanum_offset(const char *word, const char *word_lengths) | tesseract::Tesseract | |
fix_fuzzy_space_list(WERD_RES_LIST &best_perm, ROW *row, BLOCK *block) | tesseract::Tesseract | |
fix_fuzzy_spaces(ETEXT_DESC *monitor, int32_t word_count, PAGE_RES *page_res) | tesseract::Tesseract | |
fix_noisy_space_list(WERD_RES_LIST &best_perm, ROW *row, BLOCK *block) | tesseract::Tesseract | |
fix_rep_char(PAGE_RES_IT *page_res_it) | tesseract::Tesseract | |
fix_sp_fp_word(WERD_RES_IT &word_res_it, ROW *row, BLOCK *block) | tesseract::Tesseract | |
fixspace_thinks_word_done(WERD_RES *word) | tesseract::Tesseract | |
flip_0O(WERD_RES *word) | tesseract::Tesseract | |
flip_hyphens(WERD_RES *word) | tesseract::Tesseract | |
font_recognition_pass(PAGE_RES *page_res) | tesseract::Tesseract | |
font_table_size_ | tesseract::Tesseract | private |
fontinfo_table_ | tesseract::Classify | |
fontset_table_ | tesseract::Classify | |
fp_eval_word_spacing(WERD_RES_LIST &word_res_list) | tesseract::Tesseract | |
FreeNormProtos() | tesseract::Classify | |
garbage_word(WERD_RES *word, BOOL8 ok_dict_word) | tesseract::Tesseract | |
get_fontinfo_table() | tesseract::Classify | inline |
get_fontinfo_table() const | tesseract::Classify | inline |
get_fontset_table() | tesseract::Classify | inline |
get_fragment_lists(int16_t current_frag, int16_t current_row, int16_t start, int16_t num_frag_parts, int16_t num_blobs, MATRIX *ratings, BLOB_CHOICE_LIST *choice_lists) | tesseract::Wordrec | |
get_rep_char(WERD_RES *word) | tesseract::Tesseract | |
get_sub_lang(int index) const | tesseract::Tesseract | inline |
GetAdaptiveFeatures(TBLOB *Blob, INT_FEATURE_ARRAY IntFeatures, FEATURE_SET *FloatFeatures) | tesseract::Classify | |
GetAmbiguities(TBLOB *Blob, CLASS_ID CorrectClass) | tesseract::Classify | |
GetCharNormFeature(const INT_FX_RESULT_STRUCT &fx_info, INT_TEMPLATES templates, uint8_t *pruner_norm_array, uint8_t *char_norm_array) | tesseract::Classify | |
GetClassToDebug(const char *Prompt, bool *adaptive_on, bool *pretrained_on, int *shape_id) | tesseract::Classify | |
getDict() override | tesseract::Tesseract | virtual |
GetFontinfoId(ADAPT_CLASS Class, uint8_t ConfigId) | tesseract::Classify | |
GetLineData(const TBOX &line_box, const GenericVector< TBOX > &boxes, const GenericVector< STRING > &texts, int start_box, int end_box, const BLOCK &block) | tesseract::Tesseract | |
GetRectImage(const TBOX &box, const BLOCK &block, int padding, TBOX *revised_box) const | tesseract::Tesseract | |
GetSubAndSuperscriptCandidates(const WERD_RES *word, int *num_rebuilt_leading, ScriptPos *leading_pos, float *leading_certainty, int *num_rebuilt_trailing, ScriptPos *trailing_pos, float *trailing_certainty, float *avg_certainty, float *unlikely_threshold) | tesseract::Tesseract | |
grade_sharpness(SPLIT *split) | tesseract::Wordrec | |
grade_split_length(SPLIT *split) | tesseract::Wordrec | |
im_ | tesseract::Classify | protected |
imagebasename | tesseract::CCUtil | |
imagefile | tesseract::CCUtil | |
ImageHeight() const | tesseract::Tesseract | inline |
ImageWidth() const | tesseract::Tesseract | inline |
improve_by_chopping(float rating_cert_scale, WERD_RES *word, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle, LMPainPoints *pain_points, GenericVector< SegSearchPending > *pending) | tesseract::Wordrec | |
improve_one_blob(const GenericVector< BLOB_CHOICE *> &blob_choices, DANGERR *fixpt, bool split_next_to_fragment, bool italic_blob, WERD_RES *word, int *blob_number) | tesseract::Wordrec | |
init_recog_training(const STRING &fname) | tesseract::Tesseract | |
init_tesseract(const char *arg0, const char *textbase, const char *language, OcrEngineMode oem, char **configs, int configs_size, const GenericVector< STRING > *vars_vec, const GenericVector< STRING > *vars_values, bool set_only_init_params, TessdataManager *mgr) | tesseract::Tesseract | |
init_tesseract(const char *datapath, const char *language, OcrEngineMode oem) | tesseract::Tesseract | inline |
init_tesseract_internal(const char *arg0, const char *textbase, const char *language, OcrEngineMode oem, char **configs, int configs_size, const GenericVector< STRING > *vars_vec, const GenericVector< STRING > *vars_values, bool set_only_init_params, TessdataManager *mgr) | tesseract::Tesseract | |
init_tesseract_lang_data(const char *arg0, const char *textbase, const char *language, OcrEngineMode oem, char **configs, int configs_size, const GenericVector< STRING > *vars_vec, const GenericVector< STRING > *vars_values, bool set_only_init_params, TessdataManager *mgr) | tesseract::Tesseract | |
init_tesseract_lm(const char *arg0, const char *textbase, const char *language, TessdataManager *mgr) | tesseract::Tesseract | |
InitAdaptedClass(TBLOB *Blob, CLASS_ID ClassId, int FontinfoId, ADAPT_CLASS Class, ADAPT_TEMPLATES Templates) | tesseract::Classify | |
InitAdaptiveClassifier(TessdataManager *mgr) | tesseract::Classify | |
InitBlamerForSegSearch(WERD_RES *word_res, LMPainPoints *pain_points, BlamerBundle *blamer_bundle, STRING *blamer_debug) | tesseract::Wordrec | protected |
InitialSegSearch(WERD_RES *word_res, LMPainPoints *pain_points, GenericVector< SegSearchPending > *pending, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle) | tesseract::Wordrec | |
INT_VAR_H(tessedit_pageseg_mode, PSM_SINGLE_BLOCK, "Page seg mode: 0=osd only, 1=auto+osd, 2=auto, 3=col, 4=block," " 5=line, 6=word, 7=char" " (Values from PageSegMode enum in publictypes.h)") | tesseract::Tesseract | |
INT_VAR_H(tessedit_ocr_engine_mode, tesseract::OEM_DEFAULT, "Which OCR engine(s) to run (Tesseract, LSTM, both). Defaults" " to loading and running the most accurate available.") | tesseract::Tesseract | |
INT_VAR_H(pageseg_devanagari_split_strategy, tesseract::ShiroRekhaSplitter::NO_SPLIT, "Whether to use the top-line splitting process for Devanagari " "documents while performing page-segmentation.") | tesseract::Tesseract | |
INT_VAR_H(ocr_devanagari_split_strategy, tesseract::ShiroRekhaSplitter::NO_SPLIT, "Whether to use the top-line splitting process for Devanagari " "documents while performing ocr.") | tesseract::Tesseract | |
INT_VAR_H(bidi_debug, 0, "Debug level for BiDi") | tesseract::Tesseract | |
INT_VAR_H(applybox_debug, 1, "Debug level") | tesseract::Tesseract | |
INT_VAR_H(applybox_page, 0, "Page number to apply boxes from") | tesseract::Tesseract | |
INT_VAR_H(tessedit_bigram_debug, 0, "Amount of debug output for bigram " "correction.") | tesseract::Tesseract | |
INT_VAR_H(debug_noise_removal, 0, "Debug reassignment of small outlines") | tesseract::Tesseract | |
INT_VAR_H(noise_maxperblob, 8, "Max diacritics to apply to a blob") | tesseract::Tesseract | |
INT_VAR_H(noise_maxperword, 16, "Max diacritics to apply to a word") | tesseract::Tesseract | |
INT_VAR_H(debug_x_ht_level, 0, "Reestimate debug") | tesseract::Tesseract | |
INT_VAR_H(quality_min_initial_alphas_reqd, 2, "alphas in a good word") | tesseract::Tesseract | |
INT_VAR_H(tessedit_tess_adaption_mode, 0x27, "Adaptation decision algorithm for tess") | tesseract::Tesseract | |
INT_VAR_H(tessedit_test_adaption_mode, 3, "Adaptation decision algorithm for tess") | tesseract::Tesseract | |
INT_VAR_H(multilang_debug_level, 0, "Print multilang debug info.") | tesseract::Tesseract | |
INT_VAR_H(paragraph_debug_level, 0, "Print paragraph debug info.") | tesseract::Tesseract | |
INT_VAR_H(tessedit_preserve_min_wd_len, 2, "Only preserve wds longer than this") | tesseract::Tesseract | |
INT_VAR_H(crunch_rating_max, 10, "For adj length in rating per ch") | tesseract::Tesseract | |
INT_VAR_H(crunch_pot_indicators, 1, "How many potential indicators needed") | tesseract::Tesseract | |
INT_VAR_H(crunch_leave_lc_strings, 4, "Don't crunch words with long lower case strings") | tesseract::Tesseract | |
INT_VAR_H(crunch_leave_uc_strings, 4, "Don't crunch words with long lower case strings") | tesseract::Tesseract | |
INT_VAR_H(crunch_long_repetitions, 3, "Crunch words with long repetitions") | tesseract::Tesseract | |
INT_VAR_H(crunch_debug, 0, "As it says") | tesseract::Tesseract | |
INT_VAR_H(fixsp_non_noise_limit, 1, "How many non-noise blbs either side?") | tesseract::Tesseract | |
INT_VAR_H(fixsp_done_mode, 1, "What constitues done for spacing") | tesseract::Tesseract | |
INT_VAR_H(debug_fix_space_level, 0, "Contextual fixspace debug") | tesseract::Tesseract | |
INT_VAR_H(x_ht_acceptance_tolerance, 8, "Max allowed deviation of blob top outside of font data") | tesseract::Tesseract | |
INT_VAR_H(x_ht_min_change, 8, "Min change in xht before actually trying it") | tesseract::Tesseract | |
INT_VAR_H(superscript_debug, 0, "Debug level for sub & superscript fixer") | tesseract::Tesseract | |
INT_VAR_H(jpg_quality, 85, "Set JPEG quality level") | tesseract::Tesseract | |
INT_VAR_H(user_defined_dpi, 0, "Specify DPI for input image") | tesseract::Tesseract | |
INT_VAR_H(min_characters_to_try, 50, "Specify minimum characters to try during OSD") | tesseract::Tesseract | |
INT_VAR_H(suspect_level, 99, "Suspect marker level") | tesseract::Tesseract | |
INT_VAR_H(suspect_space_level, 100, "Min suspect level for rejecting spaces") | tesseract::Tesseract | |
INT_VAR_H(suspect_short_words, 2, "Don't Suspect dict wds longer than this") | tesseract::Tesseract | |
INT_VAR_H(tessedit_reject_mode, 0, "Rejection algorithm") | tesseract::Tesseract | |
INT_VAR_H(tessedit_image_border, 2, "Rej blbs near image edge limit") | tesseract::Tesseract | |
INT_VAR_H(min_sane_x_ht_pixels, 8, "Reject any x-ht lt or eq than this") | tesseract::Tesseract | |
INT_VAR_H(tessedit_page_number, -1, "-1 -> All pages, else specific page to process") | tesseract::Tesseract | |
INT_VAR_H(tessedit_parallelize, 0, "Run in parallel where possible") | tesseract::Tesseract | |
INT_VAR_H(lstm_choice_mode, 0, "Allows to include alternative symbols choices in the hOCR output. " "Valid input values are 0, 1 and 2. 0 is the default value. " "With 1 the alternative symbol choices per timestep are included. " "With 2 the alternative symbol choices are accumulated per character.") | tesseract::Tesseract | |
tesseract::Wordrec::INT_VAR_H(repair_unchopped_blobs, 1, "Fix blobs that aren't chopped") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(chop_debug, 0, "Chop debug") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(chop_split_length, 10000, "Split Length") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(chop_same_distance, 2, "Same distance") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(chop_min_outline_points, 6, "Min Number of Points on Outline") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(chop_seam_pile_size, 150, "Max number of seams in seam_pile") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(chop_inside_angle, -50, "Min Inside Angle Bend") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(chop_min_outline_area, 2000, "Min Outline Area") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(chop_centered_maxwidth, 90, "Width of (smaller) chopped blobs " "above which we don't care that a chop is not near the center.") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(chop_x_y_weight, 3, "X / Y length weight") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(segment_adjust_debug, 0, "Segmentation adjustment debug") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(wordrec_debug_level, 0, "Debug level for wordrec") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(wordrec_max_join_chunks, 4, "Max number of broken pieces to associate") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(segsearch_debug_level, 0, "SegSearch debug level") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(segsearch_max_pain_points, 2000, "Maximum number of pain points stored in the queue") | tesseract::Wordrec | |
tesseract::Wordrec::INT_VAR_H(segsearch_max_futile_classifications, 10, "Maximum number of pain point classifications per word.") | tesseract::Wordrec | |
tesseract::Classify::INT_VAR_H(tessedit_single_match, FALSE, "Top choice only from CP") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(classify_debug_level, 0, "Classify debug level") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(classify_norm_method, character, "Normalization Method ...") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(matcher_debug_level, 0, "Matcher Debug Level") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(matcher_debug_flags, 0, "Matcher Debug Flags") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(classify_learning_debug_level, 0, "Learning Debug Level: ") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(matcher_permanent_classes_min, 1, "Min # of permanent classes") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(matcher_min_examples_for_prototyping, 3, "Reliable Config Threshold") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(matcher_sufficient_examples_for_prototyping, 5, "Enable adaption even if the ambiguities have not been seen") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(classify_adapt_proto_threshold, 230, "Threshold for good protos during adaptive 0-255") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(classify_adapt_feature_threshold, 230, "Threshold for good features during adaptive 0-255") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(classify_class_pruner_threshold, 229, "Class Pruner Threshold 0-255") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(classify_class_pruner_multiplier, 15, "Class Pruner Multiplier 0-255: ") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(classify_cp_cutoff_strength, 7, "Class Pruner CutoffStrength: ") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(classify_integer_matcher_multiplier, 10, "Integer Matcher Multiplier 0-255: ") | tesseract::Classify | |
tesseract::Classify::INT_VAR_H(il1_adaption_test, 0, "Don't adapt to i/I at beginning of word") | tesseract::Classify | |
is_inside_angle(EDGEPT *pt) | tesseract::Wordrec | |
join_words(WERD_RES *word, WERD_RES *word2, BlamerBundle *orig_bb) const | tesseract::Tesseract | |
kAscenderFraction | tesseract::CCStruct | static |
kDescenderFraction | tesseract::CCStruct | static |
kXHeightCapRatio | tesseract::CCStruct | static |
kXHeightFraction | tesseract::CCStruct | static |
lang | tesseract::CCUtil | |
language_data_path_prefix | tesseract::CCUtil | |
language_model_ | tesseract::Wordrec | |
LargeSpeckle(const TBLOB &blob) | tesseract::Classify | |
LearnBlob(const STRING &fontname, TBLOB *Blob, const DENORM &cn_denorm, const INT_FX_RESULT_STRUCT &fx_info, const char *blob_text) | tesseract::Classify | |
LearnPieces(const char *fontname, int start, int length, float threshold, CharSegmentationType segmentation, const char *correct_text, WERD_RES *word) | tesseract::Classify | |
LearnWord(const char *fontname, WERD_RES *word) | tesseract::Classify | |
LooksLikeGarbage(TBLOB *blob) | tesseract::Classify | |
lstm_recognizer_ | tesseract::Tesseract | private |
LSTMRecognizeWord(const BLOCK &block, ROW *row, WERD_RES *word, PointerVector< WERD_RES > *words) | tesseract::Tesseract | |
main_setup(const char *argv0, const char *basename) | tesseract::CCUtil | |
make_reject_map(WERD_RES *word, ROW *row, int16_t pass) | tesseract::Tesseract | |
MakeNewTemporaryConfig(ADAPT_TEMPLATES Templates, CLASS_ID ClassId, int FontinfoId, int NumFeatures, INT_FEATURE_ARRAY Features, FEATURE_SET FloatFeatures) | tesseract::Classify | |
MakeNewTempProtos(FEATURE_SET Features, int NumBadFeat, FEATURE_ID BadFeat[], INT_CLASS IClass, ADAPT_CLASS Class, BIT_VECTOR TempProtoMask) | tesseract::Classify | |
MakePermanent(ADAPT_TEMPLATES Templates, CLASS_ID ClassId, int ConfigId, TBLOB *Blob) | tesseract::Classify | |
MasterMatcher(INT_TEMPLATES templates, int16_t num_features, const INT_FEATURE_STRUCT *features, const uint8_t *norm_factors, ADAPT_CLASS *classes, int debug, int matcher_multiplier, const TBOX &blob_box, const GenericVector< CP_RESULT_STRUCT > &results, ADAPT_RESULTS *final_results) | tesseract::Classify | |
match_current_words(WERD_RES_LIST &words, ROW *row, BLOCK *block) | tesseract::Tesseract | |
match_word_pass_n(int pass_n, WERD_RES *word, ROW *row, BLOCK *block) | tesseract::Tesseract | |
MaximallyChopWord(const GenericVector< TBOX > &boxes, BLOCK *block, ROW *row, WERD_RES *word_res) | tesseract::Tesseract | |
merge_and_put_fragment_lists(int16_t row, int16_t column, int16_t num_frag_parts, BLOB_CHOICE_LIST *choice_lists, MATRIX *ratings) | tesseract::Wordrec | |
merge_fragments(MATRIX *ratings, int16_t num_blobs) | tesseract::Wordrec | |
most_recently_used_ | tesseract::Tesseract | private |
mutable_pix_binary() | tesseract::Tesseract | inline |
mutable_textord() | tesseract::Tesseract | inline |
near_point(EDGEPT *point, EDGEPT *line_pt_0, EDGEPT *line_pt_1, EDGEPT **near_pt) | tesseract::Wordrec | |
new_max_point(EDGEPT *local_max, PointHeap *points) | tesseract::Wordrec | |
new_min_point(EDGEPT *local_min, PointHeap *points) | tesseract::Wordrec | |
NewAdaptedTemplates(bool InitFromUnicharset) | tesseract::Classify | |
nn_match_word(WERD_RES *word, ROW *row) | tesseract::Tesseract | |
nn_recover_rejects(WERD_RES *word, ROW *row) | tesseract::Tesseract | |
noise_outlines(TWERD *word) | tesseract::Tesseract | |
non_0_digit(const UNICHARSET &ch_set, UNICHAR_ID unichar_id) | tesseract::Tesseract | |
non_O_upper(const UNICHARSET &ch_set, UNICHAR_ID unichar_id) | tesseract::Tesseract | |
NormalizeOutlines(LIST Outlines, float *XScale, float *YScale) | tesseract::Classify | |
NormProtos | tesseract::Classify | |
num_sub_langs() const | tesseract::Tesseract | inline |
one_ell_conflict(WERD_RES *word_res, bool update_map) | tesseract::Tesseract | |
output_pass(PAGE_RES_IT &page_res_it, const TBOX *target_word_box) | tesseract::Tesseract | |
params() | tesseract::CCUtil | inline |
ParseLanguageString(const char *lang_str, GenericVector< STRING > *to_load, GenericVector< STRING > *not_to_load) | tesseract::Tesseract | |
pass2_ok_split | tesseract::Wordrec | |
pgeditor_main(int width, int height, PAGE_RES *page_res) | tesseract::Tesseract | |
pick_close_point(EDGEPT *critical_point, EDGEPT *vertical_point, int *best_dist) | tesseract::Wordrec | |
pick_good_seam(TBLOB *blob) | tesseract::Wordrec | |
pix_binary() const | tesseract::Tesseract | inline |
pix_binary_ | tesseract::Tesseract | private |
pix_grey() const | tesseract::Tesseract | inline |
pix_grey_ | tesseract::Tesseract | private |
pix_original() const | tesseract::Tesseract | inline |
pix_original_ | tesseract::Tesseract | private |
pix_thresholds_ | tesseract::Tesseract | private |
pixa_debug_ | tesseract::Tesseract | private |
point_priority(EDGEPT *point) | tesseract::Wordrec | |
potential_word_crunch(WERD_RES *word, GARBAGE_LEVEL garbage_level, bool ok_dict_word) | tesseract::Tesseract | |
PreenXHeights(BLOCK_LIST *block_list) | tesseract::Tesseract | |
PrepareForPageseg() | tesseract::Tesseract | |
PrepareForTessOCR(BLOCK_LIST *block_list, Tesseract *osd_tess, OSResults *osr) | tesseract::Tesseract | |
PrerecAllWordsPar(const GenericVector< WordData > &words) | tesseract::Tesseract | |
PreTrainedTemplates | tesseract::Classify | |
prev_word_best_choice_ | tesseract::Wordrec | |
PrintAdaptedTemplates(FILE *File, ADAPT_TEMPLATES Templates) | tesseract::Classify | |
PrintAdaptiveMatchResults(const ADAPT_RESULTS &results) | tesseract::Classify | |
prioritize_points(TESSLINE *outline, PointHeap *points) | tesseract::Wordrec | |
process_cmd_win_event(int32_t cmd_event, char *new_value) | tesseract::Tesseract | |
process_image_event(const SVEvent &event) | tesseract::Tesseract | |
process_selected_words(PAGE_RES *page_res, TBOX &selection_box, bool(tesseract::Tesseract::*word_processor)(PAGE_RES_IT *pr_it)) | tesseract::Tesseract | |
ProcessSegSearchPainPoint(float pain_point_priority, const MATRIX_COORD &pain_point, const char *pain_point_type, GenericVector< SegSearchPending > *pending, WERD_RES *word_res, LMPainPoints *pain_points, BlamerBundle *blamer_bundle) | tesseract::Wordrec | protected |
ProcessTargetWord(const TBOX &word_box, const TBOX &target_word_box, const char *word_config, int pass) | tesseract::Tesseract | |
program_editdown(int32_t elasped_time) | tesseract::Wordrec | |
program_editup(const char *textbase, TessdataManager *init_classifier, TessdataManager *init_dict) | tesseract::Wordrec | |
PruneClasses(const INT_TEMPLATES_STRUCT *int_templates, int num_features, int keep_this, const INT_FEATURE_STRUCT *features, const uint8_t *normalization_factors, const uint16_t *expected_num_features, GenericVector< CP_RESULT_STRUCT > *results) | tesseract::Classify | |
quality_based_rejection(PAGE_RES_IT &page_res_it, bool good_quality_doc) | tesseract::Tesseract | |
read_config_file(const char *filename, SetParamConstraint constraint) | tesseract::Tesseract | |
read_variables(const char *filename, bool global_only) | tesseract::CUtil | |
ReadAdaptedTemplates(TFile *File) | tesseract::Classify | |
ReadIntTemplates(TFile *fp) | tesseract::Classify | |
ReadNewCutoffs(TFile *fp, CLASS_CUTOFF_ARRAY Cutoffs) | tesseract::Classify | |
ReadNormProtos(TFile *fp) | tesseract::Classify | |
ReassignDiacritics(int pass, PAGE_RES_IT *pr_it, bool *make_next_word_fuzzy) | tesseract::Tesseract | |
recog_all_words(PAGE_RES *page_res, ETEXT_DESC *monitor, const TBOX *target_word_box, const char *word_config, int dopasses) | tesseract::Tesseract | |
recog_interactive(PAGE_RES_IT *pr_it) | tesseract::Tesseract | |
recog_pseudo_word(PAGE_RES *page_res, TBOX &selection_box) | tesseract::Tesseract | |
recog_training_segmented(const STRING &fname, PAGE_RES *page_res, volatile ETEXT_DESC *monitor, FILE *output_file) | tesseract::Tesseract | |
recog_word(WERD_RES *word) | tesseract::Tesseract | |
recog_word_recursive(WERD_RES *word) | tesseract::Tesseract | |
RecogAllWordsPassN(int pass_n, ETEXT_DESC *monitor, PAGE_RES_IT *pr_it, GenericVector< WordData > *words) | tesseract::Tesseract | |
recognize_page(STRING &image_name) | tesseract::Tesseract | |
RefreshDebugWindow(ScrollView **win, const char *msg, int y_offset, const TBOX &wbox) | tesseract::Classify | |
reject_edge_blobs(WERD_RES *word) | tesseract::Tesseract | |
reject_I_1_L(WERD_RES *word) | tesseract::Tesseract | |
reject_mostly_rejects(WERD_RES *word) | tesseract::Tesseract | |
rejection_passes(PAGE_RES *page_res, ETEXT_DESC *monitor, const TBOX *target_word_box, const char *word_config) | tesseract::Tesseract | |
RemoveBadMatches(ADAPT_RESULTS *Results) | tesseract::Classify | |
RemoveExtraPuncs(ADAPT_RESULTS *Results) | tesseract::Classify | |
repeated_nonalphanum_wd(WERD_RES *word, ROW *row) | tesseract::Tesseract | |
ReportFailedBox(int boxfile_lineno, TBOX box, const char *box_ch, const char *err_msg) | tesseract::Tesseract | |
ReportXhtFixResult(bool accept_new_word, float new_x_ht, WERD_RES *word, WERD_RES *new_word) | tesseract::Tesseract | |
ReSegmentByClassification(PAGE_RES *page_res) | tesseract::Tesseract | |
ResegmentCharBox(PAGE_RES *page_res, const TBOX *prev_box, const TBOX &box, const TBOX *next_box, const char *correct_text) | tesseract::Tesseract | |
ResegmentWordBox(BLOCK_LIST *block_list, const TBOX &box, const TBOX *next_box, const char *correct_text) | tesseract::Tesseract | |
ResetAdaptiveClassifier() | tesseract::Tesseract | |
ResetAdaptiveClassifierInternal() | tesseract::Classify | |
ResetDocumentDictionary() | tesseract::Tesseract | |
ResetNGramSearch(WERD_RES *word_res, BestChoiceBundle *best_choice_bundle, GenericVector< SegSearchPending > *pending) | tesseract::Wordrec | protected |
reskew() const | tesseract::Tesseract | inline |
reskew_ | tesseract::Tesseract | private |
RetryWithLanguage(const WordData &word_data, WordRecognizer recognizer, bool debug, WERD_RES **in_word, PointerVector< WERD_RES > *best_words) | tesseract::Tesseract | |
right_to_left() const | tesseract::Tesseract | inline |
right_to_left_ | tesseract::Tesseract | private |
RunOldFixXht(WERD_RES *word, BLOCK *block, ROW *row) | tesseract::Tesseract | |
safe_dict_word(const WERD_RES *werd_res) | tesseract::Tesseract | |
SaveAltChoices(const LIST &best_choices, WERD_RES *word) | tesseract::Wordrec | |
scaled_color() const | tesseract::Tesseract | inline |
scaled_color_ | tesseract::Tesseract | private |
scaled_factor() const | tesseract::Tesseract | inline |
scaled_factor_ | tesseract::Tesseract | private |
script_pos_pass(PAGE_RES *page_res) | tesseract::Tesseract | |
SearchForText(const GenericVector< BLOB_CHOICE_LIST *> *choices, int choices_pos, int choices_length, const GenericVector< UNICHAR_ID > &target_text, int text_index, float rating, GenericVector< int > *segmentation, float *best_rating, GenericVector< int > *best_segmentation) | tesseract::Tesseract | |
SearchWords(PointerVector< WERD_RES > *words) | tesseract::Tesseract | |
SegmentPage(const STRING *input_file, BLOCK_LIST *blocks, Tesseract *osd_tess, OSResults *osr) | tesseract::Tesseract | |
SegSearch(WERD_RES *word_res, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle) | tesseract::Wordrec | |
SegSearchDone(int num_futile_classifications) | tesseract::Wordrec | inlineprotected |
select_blob_to_split(const GenericVector< BLOB_CHOICE *> &blob_choices, float rating_ceiling, bool split_next_to_fragment) | tesseract::Wordrec | |
select_blob_to_split_from_fixpt(DANGERR *fixpt) | tesseract::Wordrec | |
SelectGoodDiacriticOutlines(int pass, float certainty_threshold, PAGE_RES_IT *pr_it, C_BLOB *blob, const GenericVector< C_OUTLINE *> &outlines, int num_outlines, GenericVector< bool > *ok_outlines) | tesseract::Tesseract | |
set_done(WERD_RES *word, int16_t pass) | tesseract::Tesseract | |
set_pass1() | tesseract::Wordrec | |
set_pass2() | tesseract::Wordrec | |
set_pix_grey(Pix *grey_pix) | tesseract::Tesseract | inline |
set_pix_original(Pix *original_pix) | tesseract::Tesseract | inline |
set_pix_thresholds(Pix *thresholds) | tesseract::Tesseract | inline |
set_source_resolution(int ppi) | tesseract::Tesseract | inline |
set_unlv_suspects(WERD_RES *word) | tesseract::Tesseract | |
set_word_fonts(WERD_RES *word) | tesseract::Tesseract | |
SetAdaptiveThreshold(float Threshold) | tesseract::Classify | |
SetBlackAndWhitelist() | tesseract::Tesseract | |
SetEquationDetect(EquationDetect *detector) | tesseract::Tesseract | |
SetScaledColor(int factor, Pix *color) | tesseract::Tesseract | inline |
SetStaticClassifier(ShapeClassifier *static_classifier) | tesseract::Classify | |
SettupPass1() | tesseract::Classify | |
SettupPass2() | tesseract::Classify | |
SetupAllWordsPassN(int pass_n, const TBOX *target_word_box, const char *word_config, PAGE_RES *page_res, GenericVector< WordData > *words) | tesseract::Tesseract | |
SetupApplyBoxes(const GenericVector< TBOX > &boxes, BLOCK_LIST *block_list) | tesseract::Tesseract | |
SetupBLCNDenorms(const TBLOB &blob, bool nonlinear_norm, DENORM *bl_denorm, DENORM *cn_denorm, INT_FX_RESULT_STRUCT *fx_info) | tesseract::Classify | static |
SetupPageSegAndDetectOrientation(PageSegMode pageseg_mode, BLOCK_LIST *blocks, Tesseract *osd_tess, OSResults *osr, TO_BLOCK_LIST *to_blocks, Pix **photo_mask_pix, Pix **music_mask_pix) | tesseract::Tesseract | |
SetupUniversalFontIds() | tesseract::Tesseract | |
SetupWordPassN(int pass_n, WordData *word) | tesseract::Tesseract | |
SetupWordScripts(BLOCK_LIST *blocks) | tesseract::Tesseract | |
shape_table() const | tesseract::Classify | inline |
shape_table_ | tesseract::Classify | protected |
ShapeIDToClassID(int shape_id) const | tesseract::Classify | |
ShowBestMatchFor(int shape_id, const INT_FEATURE_STRUCT *features, int num_features) | tesseract::Classify | |
ShowMatchDisplay() | tesseract::Classify | |
source_resolution() const | tesseract::Tesseract | inline |
source_resolution_ | tesseract::Tesseract | private |
split_and_recog_word(WERD_RES *word) | tesseract::Tesseract | |
split_word(WERD_RES *word, int split_pt, WERD_RES **right_piece, BlamerBundle **orig_blamer_bundle) const | tesseract::Tesseract | |
splitter_ | tesseract::Tesseract | private |
StartBackupAdaptiveClassifier() | tesseract::Classify | |
stats_ | tesseract::Tesseract | private |
STRING_VAR_H(tessedit_char_blacklist, "", "Blacklist of chars not to recognize") | tesseract::Tesseract | |
STRING_VAR_H(tessedit_char_whitelist, "", "Whitelist of chars to recognize") | tesseract::Tesseract | |
STRING_VAR_H(tessedit_char_unblacklist, "", "List of chars to override tessedit_char_blacklist") | tesseract::Tesseract | |
STRING_VAR_H(tessedit_write_params_to_file, "", "Write all parameters to the given file.") | tesseract::Tesseract | |
STRING_VAR_H(applybox_exposure_pattern, ".exp", "Exposure value follows this pattern in the image" " filename. The name of the image files are expected" " to be in the form [lang].[fontname].exp[num].tif") | tesseract::Tesseract | |
STRING_VAR_H(chs_leading_punct, "('`\, "Leading punctuation") | tesseract::Tesseract | |
STRING_VAR_H(chs_trailing_punct1, ").,;:?!", "1st Trailing punctuation") | tesseract::Tesseract | |
STRING_VAR_H(chs_trailing_punct2, ")'`\, "2nd Trailing punctuation") | tesseract::Tesseract | |
STRING_VAR_H(outlines_odd, "%| ", "Non standard number of outlines") | tesseract::Tesseract | |
STRING_VAR_H(outlines_2, "ij!?%\;", "Non standard number of outlines") | tesseract::Tesseract | |
STRING_VAR_H(numeric_punctuation, ".,", "Punct. chs expected WITHIN numbers") | tesseract::Tesseract | |
STRING_VAR_H(unrecognised_char, "|", "Output char for unidentified blobs") | tesseract::Tesseract | |
STRING_VAR_H(ok_repeated_ch_non_alphanum_wds, "-?*\5", "Allow NN to unrej") | tesseract::Tesseract | |
STRING_VAR_H(conflict_set_I_l_1, "Il1[]", "Il1 conflict set") | tesseract::Tesseract | |
STRING_VAR_H(file_type, ".tif", "Filename extension") | tesseract::Tesseract | |
STRING_VAR_H(tessedit_load_sublangs, "", "List of languages to load with this one") | tesseract::Tesseract | |
STRING_VAR_H(page_separator, "\, "Page separator(default is form feed control character)") | tesseract::Tesseract | |
tesseract::Wordrec::STRING_VAR_H(classify_learn_debug_str, "", "Class str to debug learning") | tesseract::Classify | |
sub_langs_ | tesseract::Tesseract | private |
SubAndSuperscriptFix(WERD_RES *word_res) | tesseract::Tesseract | |
SwitchAdaptiveClassifier() | tesseract::Classify | |
TempConfigReliable(CLASS_ID class_id, const TEMP_CONFIG &config) | tesseract::Classify | |
TempProtoMask | tesseract::Classify | |
terrible_word_crunch(WERD_RES *word, GARBAGE_LEVEL garbage_level) | tesseract::Tesseract | |
tess_acceptable_word(WERD_RES *word) | tesseract::Tesseract | |
tess_add_doc_word(WERD_CHOICE *word_choice) | tesseract::Tesseract | |
tess_segment_pass_n(int pass_n, WERD_RES *word) | tesseract::Tesseract | |
Tesseract() | tesseract::Tesseract | |
TestNewNormalization(int original_misfits, float baseline_shift, float new_x_ht, WERD_RES *word, BLOCK *block, ROW *row) | tesseract::Tesseract | |
textord() const | tesseract::Tesseract | inline |
textord_ | tesseract::Tesseract | private |
TidyUp(PAGE_RES *page_res) | tesseract::Tesseract | |
tilde_crunch(PAGE_RES_IT &page_res_it) | tesseract::Tesseract | |
tilde_delete(PAGE_RES_IT &page_res_it) | tesseract::Tesseract | |
train_line_page_num_ | tesseract::Tesseract | private |
TrainedXheightFix(WERD_RES *word, BLOCK *block, ROW *row) | tesseract::Tesseract | |
TrainFromBoxes(const GenericVector< TBOX > &boxes, const GenericVector< STRING > &texts, BLOCK_LIST *block_list, DocumentData *training_data) | tesseract::Tesseract | |
TrainLineRecognizer(const STRING &input_imagename, const STRING &output_basename, BLOCK_LIST *block_list) | tesseract::Tesseract | |
try_point_pairs(EDGEPT *points[50], int16_t num_points, SeamQueue *seam_queue, SeamPile *seam_pile, SEAM **seam, TBLOB *blob) | tesseract::Wordrec | |
try_vertical_splits(EDGEPT *points[50], int16_t num_points, EDGEPT_CLIST *new_points, SeamQueue *seam_queue, SeamPile *seam_pile, SEAM **seam, TBLOB *blob) | tesseract::Wordrec | |
TrySuperscriptSplits(int num_chopped_leading, float leading_certainty, ScriptPos leading_pos, int num_chopped_trailing, float trailing_certainty, ScriptPos trailing_pos, WERD_RES *word, bool *is_good, int *retry_leading, int *retry_trailing) | tesseract::Tesseract | |
unichar_ambigs | tesseract::CCUtil | |
unicharset | tesseract::CCUtil | |
unrej_good_chs(WERD_RES *word, ROW *row) | tesseract::Tesseract | |
unrej_good_quality_words(PAGE_RES_IT &page_res_it) | tesseract::Tesseract | |
UpdateAmbigsGroup(CLASS_ID class_id, TBLOB *Blob) | tesseract::Classify | |
UpdateSegSearchNodes(float rating_cert_scale, int starting_col, GenericVector< SegSearchPending > *pending, WERD_RES *word_res, LMPainPoints *pain_points, BestChoiceBundle *best_choice_bundle, BlamerBundle *blamer_bundle) | tesseract::Wordrec | protected |
use_ambigs_for_adaption | tesseract::CCUtil | |
use_definite_ambigs_for_classifier | tesseract::CCUtil | |
vertical_projection_point(EDGEPT *split_point, EDGEPT *target_point, EDGEPT **best_point, EDGEPT_CLIST *new_points) | tesseract::Wordrec | |
word_adaptable(WERD_RES *word, uint16_t mode) | tesseract::Tesseract | |
word_blank_and_set_display(PAGE_RES_IT *pr_its) | tesseract::Tesseract | |
word_bln_display(PAGE_RES_IT *pr_it) | tesseract::Tesseract | |
word_blob_quality(WERD_RES *word, ROW *row) | tesseract::Tesseract | |
word_char_quality(WERD_RES *word, ROW *row, int16_t *match_count, int16_t *accepted_match_count) | tesseract::Tesseract | |
word_config_ | tesseract::Tesseract | private |
word_contains_non_1_digit(const char *word, const char *word_lengths) | tesseract::Tesseract | |
word_deletable(WERD_RES *word, int16_t &delete_mode) | tesseract::Tesseract | |
word_display(PAGE_RES_IT *pr_it) | tesseract::Tesseract | |
word_dumper(PAGE_RES_IT *pr_it) | tesseract::Tesseract | |
word_outline_errs(WERD_RES *word) | tesseract::Tesseract | |
word_set_display(PAGE_RES_IT *pr_it) | tesseract::Tesseract | |
Wordrec() | tesseract::Wordrec | |
worst_noise_blob(WERD_RES *word_res, float *worst_noise_score) | tesseract::Tesseract | |
write_results(PAGE_RES_IT &page_res_it, char newline_type, bool force_eol) | tesseract::Tesseract | |
WriteAdaptedTemplates(FILE *File, ADAPT_TEMPLATES Templates) | tesseract::Classify | |
WriteIntTemplates(FILE *File, INT_TEMPLATES Templates, const UNICHARSET &target_unicharset) | tesseract::Classify | |
WriteTRFile(const STRING &filename) | tesseract::Classify | |
~CCStruct() | tesseract::CCStruct | virtual |
~CCUtil() | tesseract::CCUtil | virtual |
~Classify() | tesseract::Classify | virtual |
~CUtil() | tesseract::CUtil | virtual |
~Tesseract() | tesseract::Tesseract | |
~Wordrec()=default | tesseract::Wordrec | virtual |