mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2024-12-12 07:29:07 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Removed unused parameters

Browse Source 
The following parameters are not used anywhere anymore:

 * use_definite_ambigs_for_classifier
 * max_viterbi_list_size
 * word_to_debug_lengths
 * fragments_debug
 * tessedit_redo_xheight
 * debug_acceptable_wds
 * tessedit_matcher_log
 * tessedit_test_adaption_mode
 * docqual_excuse_outline_errs
 * crunch_pot_garbage
 * suspect_space_level
 * tessedit_consistent_reps
 * wordrec_display_all_words
 * wordrec_no_block
 * wordrec_worst_state
 * fragments_guide_chopper
 * segment_adjust_debug
 * classify_adapt_feature_thresh (classify_adapt_feature_threshold still exists)
 * classify_adapt_proto_thresh (classify_adapt_proto_threshold still exists)
 * classify_min_norm_scale_x
 * classify_max_norm_scale_x
 * classify_min_norm_scale_y
 * classify_max_norm_scale_y
 * il1_adaption_test
 * textord_blob_size_bigile
 * textord_blob_size_smallile
 * editor_debug_config_file
 * textord_tabfind_show_color_fit

The list was generated by a python script and each parameter occurence checked
manually.

# Conflicts:
#	src/classify/classify.cpp
This commit is contained in:
zdenop 2019-11-01 14:58:36 +01:00
parent 58122ea313
commit b244bd1c13
22 changed files with 0 additions and 101 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/ccmain/pgedit.cpp
View File

@ -141,8 +141,6 @@ INT_VAR(editor_word_ypos, 510, "Word window Y Pos");
INT_VAR(editor_word_height, 240, "Word window height");
INT_VAR(editor_word_width, 655, "Word window width");
static STRING_VAR(editor_debug_config_file, "", "Config file to apply to single words");
/**
* show_point()
*

16
src/ccmain/tesseractclass.cpp
View File

@ -137,8 +137,6 @@ Tesseract::Tesseract()
"Don't bother with word plausibility", this->params()),
BOOL_MEMBER(tessedit_fix_hyphens, true, "Crunch double hyphens?",
this->params()),
BOOL_MEMBER(tessedit_redo_xheight, true, "Check/Correct x-height",
this->params()),
BOOL_MEMBER(tessedit_enable_doc_dict, true,
"Add words to the document dictionary", this->params()),
BOOL_MEMBER(tessedit_debug_fonts, false, "Output font info per char",
@ -182,8 +180,6 @@ Tesseract::Tesseract()
INT_MEMBER(noise_maxperword, 16, "Max diacritics to apply to a word",
this->params()),
INT_MEMBER(debug_x_ht_level, 0, "Reestimate debug", this->params()),
BOOL_MEMBER(debug_acceptable_wds, false, "Dump word pass/fail chk",
this->params()),
STRING_MEMBER(chs_leading_punct, "('`\"", "Leading punctuation",
this->params()),
STRING_MEMBER(chs_trailing_punct1, ").,;:?!", "1st Trailing punctuation",
@ -206,10 +202,6 @@ Tesseract::Tesseract()
"Do minimal rejection on pass 1 output", this->params()),
BOOL_MEMBER(tessedit_test_adaption, false, "Test adaption criteria",
this->params()),
BOOL_MEMBER(tessedit_matcher_log, false, "Log matcher activity",
this->params()),
INT_MEMBER(tessedit_test_adaption_mode, 3,
"Adaptation decision algorithm for tess", this->params()),
BOOL_MEMBER(test_pt, false, "Test for point", this->params()),
double_MEMBER(test_pt_x, 99999.99, "xcoord", this->params()),
double_MEMBER(test_pt_y, 99999.99, "ycoord", this->params()),
@ -227,8 +219,6 @@ Tesseract::Tesseract()
this->params()),
STRING_MEMBER(outlines_2, "ij!?%\":;", "Non standard number of outlines",
this->params()),
BOOL_MEMBER(docqual_excuse_outline_errs, false,
"Allow outline errs in unrejection?", this->params()),
BOOL_MEMBER(tessedit_good_quality_unrej, true,
"Reduce rejection on good docs", this->params()),
BOOL_MEMBER(tessedit_use_reject_spaces, true, "Reject spaces?",
@ -291,8 +281,6 @@ Tesseract::Tesseract()
this->params()),
double_MEMBER(crunch_pot_poor_cert, -8.0, "POTENTIAL crunch cert lt this",
this->params()),
BOOL_MEMBER(crunch_pot_garbage, true, "POTENTIAL crunch garbage",
this->params()),
double_MEMBER(crunch_del_rating, 60, "POTENTIAL crunch rating lt this",
this->params()),
double_MEMBER(crunch_del_cert, -10.0, "POTENTIAL crunch cert lt this",
@ -410,8 +398,6 @@ Tesseract::Tesseract()
STRING_MEMBER(unrecognised_char, "|",
"Output char for unidentified blobs", this->params()),
INT_MEMBER(suspect_level, 99, "Suspect marker level", this->params()),
INT_MEMBER(suspect_space_level, 100,
"Min suspect level for rejecting spaces", this->params()),
INT_MEMBER(suspect_short_words, 2,
"Don't suspect dict wds longer than this", this->params()),
BOOL_MEMBER(suspect_constrain_1Il, false, "UNLV keep 1Il chars rejected",
@ -428,8 +414,6 @@ Tesseract::Tesseract()
"Make output have exactly one word per WERD", this->params()),
BOOL_MEMBER(tessedit_zero_kelvin_rejection, false,
"Don't reject ANYTHING AT ALL", this->params()),
BOOL_MEMBER(tessedit_consistent_reps, true,
"Force all rep chars the same", this->params()),
INT_MEMBER(tessedit_reject_mode, 0, "Rejection algorithm",
this->params()),
BOOL_MEMBER(tessedit_rejection_debug, false, "Adaption debug",

10
src/ccmain/tesseractclass.h
View File

@ -839,7 +839,6 @@ class Tesseract : public Wordrec {
BOOL_VAR_H(tessedit_unrej_any_wd, false,
"Don't bother with word plausibility");
BOOL_VAR_H(tessedit_fix_hyphens, true, "Crunch double hyphens?");
BOOL_VAR_H(tessedit_redo_xheight, true, "Check/Correct x-height");
BOOL_VAR_H(tessedit_enable_doc_dict, true,
"Add words to the document dictionary");
BOOL_VAR_H(tessedit_debug_fonts, false, "Output font info per char");
@ -870,7 +869,6 @@ class Tesseract : public Wordrec {
INT_VAR_H(noise_maxperblob, 8, "Max diacritics to apply to a blob");
INT_VAR_H(noise_maxperword, 16, "Max diacritics to apply to a word");
INT_VAR_H(debug_x_ht_level, 0, "Reestimate debug");
BOOL_VAR_H(debug_acceptable_wds, false, "Dump word pass/fail chk");
STRING_VAR_H(chs_leading_punct, "('`\"", "Leading punctuation");
STRING_VAR_H(chs_trailing_punct1, ").,;:?!", "1st Trailing punctuation");
STRING_VAR_H(chs_trailing_punct2, ")'`\"", "2nd Trailing punctuation");
@ -885,9 +883,6 @@ class Tesseract : public Wordrec {
BOOL_VAR_H(tessedit_minimal_rej_pass1, false,
"Do minimal rejection on pass 1 output");
BOOL_VAR_H(tessedit_test_adaption, false, "Test adaption criteria");
BOOL_VAR_H(tessedit_matcher_log, false, "Log matcher activity");
INT_VAR_H(tessedit_test_adaption_mode, 3,
"Adaptation decision algorithm for tess");
BOOL_VAR_H(test_pt, false, "Test for point");
double_VAR_H(test_pt_x, 99999.99, "xcoord");
double_VAR_H(test_pt_y, 99999.99, "ycoord");
@ -899,8 +894,6 @@ class Tesseract : public Wordrec {
BOOL_VAR_H(lstm_use_matrix, 1, "Use ratings matrix/beam searct with lstm");
STRING_VAR_H(outlines_odd, "%| ", "Non standard number of outlines");
STRING_VAR_H(outlines_2, "ij!?%\":;", "Non standard number of outlines");
BOOL_VAR_H(docqual_excuse_outline_errs, false,
"Allow outline errs in unrejection?");
BOOL_VAR_H(tessedit_good_quality_unrej, true,
"Reduce rejection on good docs");
BOOL_VAR_H(tessedit_use_reject_spaces, true, "Reject spaces?");
@ -945,7 +938,6 @@ class Tesseract : public Wordrec {
double_VAR_H(crunch_poor_garbage_rate, 60, "crunch garbage rating lt this");
double_VAR_H(crunch_pot_poor_rate, 40, "POTENTIAL crunch rating lt this");
double_VAR_H(crunch_pot_poor_cert, -8.0, "POTENTIAL crunch cert lt this");
BOOL_VAR_H(crunch_pot_garbage, true, "POTENTIAL crunch garbage");
double_VAR_H(crunch_del_rating, 60, "POTENTIAL crunch rating lt this");
double_VAR_H(crunch_del_cert, -10.0, "POTENTIAL crunch cert lt this");
double_VAR_H(crunch_del_min_ht, 0.7, "Del if word ht lt xht x this");
@ -1019,7 +1011,6 @@ class Tesseract : public Wordrec {
"Specify minimum characters to try during OSD");
STRING_VAR_H(unrecognised_char, "|", "Output char for unidentified blobs");
INT_VAR_H(suspect_level, 99, "Suspect marker level");
INT_VAR_H(suspect_space_level, 100, "Min suspect level for rejecting spaces");
INT_VAR_H(suspect_short_words, 2, "Don't Suspect dict wds longer than this");
BOOL_VAR_H(suspect_constrain_1Il, false, "UNLV keep 1Il chars rejected");
double_VAR_H(suspect_rating_per_ch, 999.9, "Don't touch bad rating limit");
@ -1030,7 +1021,6 @@ class Tesseract : public Wordrec {
"Make output have exactly one word per WERD");
BOOL_VAR_H(tessedit_zero_kelvin_rejection, false,
"Don't reject ANYTHING AT ALL");
BOOL_VAR_H(tessedit_consistent_reps, true, "Force all rep chars the same");
INT_VAR_H(tessedit_reject_mode, 0, "Rejection algorithm");
BOOL_VAR_H(tessedit_rejection_debug, false, "Adaption debug");
BOOL_VAR_H(tessedit_flip_0O, true, "Contextual 0O O0 flips");

2
src/ccutil/ccutil.cpp
View File

@ -17,8 +17,6 @@ CCUtil::CCUtil() :
params_(),
INT_INIT_MEMBER(ambigs_debug_level, 0, "Debug level for unichar ambiguities",
&params_),
BOOL_MEMBER(use_definite_ambigs_for_classifier, false, "Use definite"
" ambiguities when running character classifier", &params_),
BOOL_MEMBER(use_ambigs_for_adaption, false, "Use ambigs for deciding"
" whether to adapt to a character", &params_) {
}

2
src/ccutil/ccutil.h
View File

@ -85,8 +85,6 @@ class CCUtil {
// These have to be declared and initialized after params_ member, since
// params_ should be initialized before parameters are added to it.
INT_VAR_H(ambigs_debug_level, 0, "Debug level for unichar ambiguities");
BOOL_VAR_H(use_definite_ambigs_for_classifier, false,
"Use definite ambiguities when running character classifier");
BOOL_VAR_H(use_ambigs_for_adaption, false,
"Use ambigs for deciding whether to adapt to a character");
};

13
src/classify/classify.cpp
View File

@ -70,16 +70,6 @@ Classify::Classify()
this->params()),
double_MEMBER(classify_char_norm_range, 0.2,
"Character Normalization Range ...", this->params()),
double_MEMBER(classify_min_norm_scale_x, 0.0, "Min char x-norm scale ...",
this->params()), /* PREV DEFAULT 0.1 */
double_MEMBER(classify_max_norm_scale_x, 0.325,
"Max char x-norm scale ...",
this->params()), /* PREV DEFAULT 0.3 */
double_MEMBER(classify_min_norm_scale_y, 0.0, "Min char y-norm scale ...",
this->params()), /* PREV DEFAULT 0.1 */
double_MEMBER(classify_max_norm_scale_y, 0.325,
"Max char y-norm scale ...",
this->params()), /* PREV DEFAULT 0.3 */
double_MEMBER(classify_max_rating_ratio, 1.5,
"Veto ratio between classifier ratings", this->params()),
double_MEMBER(classify_max_certainty_margin, 5.5,
@ -173,9 +163,6 @@ Classify::Classify()
"Class Pruner CutoffStrength: ", this->params()),
INT_MEMBER(classify_integer_matcher_multiplier, 10,
"Integer Matcher Multiplier 0-255: ", this->params()),
EnableLearning(true),
INT_MEMBER(il1_adaption_test, 0,
"Don't adapt to i/I at beginning of word", this->params()),
BOOL_MEMBER(classify_bln_numeric_mode, 0,
"Assume the input is numbers [0-9].", this->params()),
double_MEMBER(speckle_large_max_size, 0.30, "Max large speckle size",

5
src/classify/classify.h
View File

@ -434,10 +434,6 @@ class Classify : public CCStruct {
INT_VAR_H(classify_norm_method, character, "Normalization Method ...");
double_VAR_H(classify_char_norm_range, 0.2,
"Character Normalization Range ...");
double_VAR_H(classify_min_norm_scale_x, 0.0, "Min char x-norm scale ...");
double_VAR_H(classify_max_norm_scale_x, 0.325, "Max char x-norm scale ...");
double_VAR_H(classify_min_norm_scale_y, 0.0, "Min char y-norm scale ...");
double_VAR_H(classify_max_norm_scale_y, 0.325, "Max char y-norm scale ...");
double_VAR_H(classify_max_rating_ratio, 1.5,
"Veto ratio between classifier ratings");
double_VAR_H(classify_max_certainty_margin, 5.5,
@ -508,7 +504,6 @@ class Classify : public CCStruct {
INT_VAR_H(classify_integer_matcher_multiplier, 10,
"Integer Matcher Multiplier 0-255: ");
INT_VAR_H(il1_adaption_test, 0, "Don't adapt to i/I at beginning of word");
BOOL_VAR_H(classify_bln_numeric_mode, 0,
"Assume the input is numbers [0-9].");
double_VAR_H(speckle_large_max_size, 0.30, "Max large speckle size");

9
src/classify/intmatcher.h
View File

@ -47,15 +47,6 @@ struct CP_RESULT_STRUCT {
CLASS_ID Class;
};
/*----------------------------------------------------------------------------
Variables
-----------------------------------------------------------------------------*/
extern INT_VAR_H(classify_adapt_proto_thresh, 230,
"Threshold for good protos during adaptive 0-255: ");
extern INT_VAR_H(classify_adapt_feature_thresh, 230,
"Threshold for good features during adaptive 0-255: ");
/**----------------------------------------------------------------------------
Public Function Prototypes

7
src/dict/dict.cpp
View File

@ -105,8 +105,6 @@ Dict::Dict(CCUtil* ccutil)
getCCUtil()->params()),
INT_MEMBER(hyphen_debug_level, 0, "Debug level for hyphenated words.",
getCCUtil()->params()),
INT_MEMBER(max_viterbi_list_size, 10, "Maximum size of viterbi list.",
getCCUtil()->params()),
BOOL_MEMBER(use_only_first_uft8_step, false,
"Use only the first UTF8 step of the given string"
" when computing log probabilities.",
@ -140,11 +138,6 @@ Dict::Dict(CCUtil* ccutil)
"Word for which stopper debug"
" information should be printed to stdout",
getCCUtil()->params()),
STRING_MEMBER(word_to_debug_lengths, "",
"Lengths of unichars in word_to_debug",
getCCUtil()->params()),
INT_MEMBER(fragments_debug, 0, "Debug character fragments",
getCCUtil()->params()),
BOOL_MEMBER(segment_nonalphabetic_script, false,
"Don't use any alphabetic-specific tricks."
" Set to true in the traineddata config file for"

4
src/dict/dict.h
View File

@ -621,7 +621,6 @@ class Dict {
INT_VAR_H(dawg_debug_level, 0, "Set to 1 for general debug info"
", to 2 for more details, to 3 to see all the debug messages");
INT_VAR_H(hyphen_debug_level, 0, "Debug level for hyphenated words.");
INT_VAR_H(max_viterbi_list_size, 10, "Maximum size of viterbi list.");
BOOL_VAR_H(use_only_first_uft8_step, false,
"Use only the first UTF8 step of the given string"
" when computing log probabilities.");
@ -643,9 +642,6 @@ class Dict {
INT_VAR_H(tessedit_truncate_wordchoice_log, 10, "Max words to keep in list");
STRING_VAR_H(word_to_debug, "", "Word for which stopper debug information"
" should be printed to stdout");
STRING_VAR_H(word_to_debug_lengths, "",
"Lengths of unichars in word_to_debug");
INT_VAR_H(fragments_debug, 0, "Debug character fragments");
BOOL_VAR_H(segment_nonalphabetic_script, false,
"Don't use any alphabetic-specific tricks."
"Set to true in the traineddata config file for"

2
src/textord/colpartitiongrid.cpp
View File

@ -28,8 +28,6 @@
namespace tesseract {
static BOOL_VAR(textord_tabfind_show_color_fit, false, "Show stroke widths");
// Max pad factor used to search the neighbourhood of a partition to smooth
// partition types.
const int kMaxPadFactor = 6;

4
src/textord/textord.cpp
View File

@ -185,12 +185,8 @@ Textord::Textord(CCStruct* ccstruct)
ccstruct_->params()),
INT_MEMBER(textord_baseline_debug, 0, "Baseline debug level",
ccstruct_->params()),
double_MEMBER(textord_blob_size_bigile, 95, "Percentile for large blobs",
ccstruct_->params()),
double_MEMBER(textord_noise_area_ratio, 0.7,
"Fraction of bounding box for noise", ccstruct_->params()),
double_MEMBER(textord_blob_size_smallile, 20,
"Percentile for small blobs", ccstruct_->params()),
double_MEMBER(textord_initialx_ile, 0.75,
"Ile of sizes for xheight guess", ccstruct_->params()),
double_MEMBER(textord_initialasc_ile, 0.90,

2
src/textord/textord.h
View File

@ -375,10 +375,8 @@ class Textord {
BOOL_VAR_H(textord_show_boxes, false, "Display boxes");
INT_VAR_H(textord_max_noise_size, 7, "Pixel size of noise");
INT_VAR_H(textord_baseline_debug, 0, "Baseline debug level");
double_VAR_H(textord_blob_size_bigile, 95, "Percentile for large blobs");
double_VAR_H(textord_noise_area_ratio, 0.7,
"Fraction of bounding box for noise");
double_VAR_H(textord_blob_size_smallile, 20, "Percentile for small blobs");
double_VAR_H(textord_initialx_ile, 0.75, "Ile of sizes for xheight guess");
double_VAR_H(textord_initialasc_ile, 0.90, "Ile of sizes for xheight guess");
INT_VAR_H(textord_noise_sizefraction, 10, "Fraction of size for maxima");

2
src/wordrec/render.cpp
View File

@ -38,8 +38,6 @@ C_COL color_list[] = {
BOOL_VAR(wordrec_display_all_blobs, 0, "Display Blobs");
BOOL_VAR(wordrec_display_all_words, 0, "Display Words");
BOOL_VAR(wordrec_blob_pause, 0, "Blob pause");
/*----------------------------------------------------------------------

2
src/wordrec/render.h
View File

@ -37,8 +37,6 @@ extern C_COL color_list[]; /* Colors for outlines */
extern BOOL_VAR_H(wordrec_display_all_blobs, 0, "Display Blobs");
extern BOOL_VAR_H(wordrec_display_all_words, 0, "Display Words");
extern BOOL_VAR_H(wordrec_blob_pause, 0, "Blob pause");
#define NUM_COLORS 6

9
src/wordrec/wordrec.cpp
View File

@ -49,19 +49,12 @@ Wordrec::Wordrec() :
BOOL_MEMBER(merge_fragments_in_matrix, true,
"Merge the fragments in the ratings matrix and delete them"
" after merging", params()),
BOOL_MEMBER(wordrec_no_block, false, "Don't output block information",
params()),
BOOL_MEMBER(wordrec_enable_assoc, true, "Associator Enable",
params()),
BOOL_MEMBER(force_word_assoc, false,
"force associator to run regardless of what enable_assoc is."
" This is used for CJK where component grouping is necessary.",
CCUtil::params()),
double_MEMBER(wordrec_worst_state, 1.0, "Worst segmentation state",
params()),
BOOL_MEMBER(fragments_guide_chopper, false,
"Use information from fragments to guide chopping process",
params()),
INT_MEMBER(repair_unchopped_blobs, 1, "Fix blobs that aren't chopped",
params()),
double_MEMBER(tessedit_certainty_threshold, -2.25, "Good blob limit",
@ -104,8 +97,6 @@ Wordrec::Wordrec() :
params()),
INT_MEMBER(chop_x_y_weight, 3, "X / Y length weight",
params()),
INT_MEMBER(segment_adjust_debug, 0, "Segmentation adjustment debug",
params()),
BOOL_MEMBER(assume_fixed_pitch_char_segment, false,
"include fixed-pitch heuristics in char segmentation",
params()),

5
src/wordrec/wordrec.h
View File

@ -195,14 +195,10 @@ class Wordrec : public Classify {
BOOL_VAR_H(merge_fragments_in_matrix, true,
"Merge the fragments in the ratings matrix and delete them "
"after merging");
BOOL_VAR_H(wordrec_no_block, false, "Don't output block information");
BOOL_VAR_H(wordrec_enable_assoc, true, "Associator Enable");
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.");
double_VAR_H(wordrec_worst_state, 1, "Worst segmentation state");
BOOL_VAR_H(fragments_guide_chopper, false,
"Use information from fragments to guide chopping process");
INT_VAR_H(repair_unchopped_blobs, 1, "Fix blobs that aren't chopped");
double_VAR_H(tessedit_certainty_threshold, -2.25, "Good blob limit");
INT_VAR_H(chop_debug, 0, "Chop debug");
@ -225,7 +221,6 @@ class Wordrec : public Classify {
double_VAR_H(chop_ok_split, 100.0, "OK split limit");
double_VAR_H(chop_good_split, 50.0, "Good split limit");
INT_VAR_H(chop_x_y_weight, 3, "X / Y length weight");
INT_VAR_H(segment_adjust_debug, 0, "Segmentation adjustment debug");
BOOL_VAR_H(assume_fixed_pitch_char_segment, false,
"include fixed-pitch heuristics in char segmentation");
INT_VAR_H(wordrec_debug_level, 0, "Debug level for wordrec");

1
tessdata/configs/box.train
View File

@ -4,7 +4,6 @@ textord_fast_pitch_test T
tessedit_zero_rejection T
tessedit_minimal_rejection F
tessedit_write_rep_codes F
il1_adaption_test 1
edges_children_fix F
edges_childarea 0.65
edges_boxarea 0.9

1
tessdata/configs/box.train.stderr
View File

@ -4,7 +4,6 @@ textord_fast_pitch_test T
tessedit_zero_rejection T
tessedit_minimal_rejection F
tessedit_write_rep_codes F
il1_adaption_test 1
edges_children_fix F
edges_childarea 0.65
edges_boxarea 0.9

1
tessdata/configs/lstm.train
View File

@ -4,7 +4,6 @@ textord_fast_pitch_test T
tessedit_zero_rejection T
tessedit_minimal_rejection F
tessedit_write_rep_codes F
il1_adaption_test 1
edges_children_fix F
edges_childarea 0.65
edges_boxarea 0.9

1
tessdata/tessconfigs/msdemo
View File

@ -7,7 +7,6 @@ matcher_debug_flags 6
matcher_debug_level 1
wordrec_display_splits 0
wordrec_display_all_words 1
wordrec_display_all_blobs 1
wordrec_display_segmentations 2
classify_debug_level 1

1
tessdata/tessconfigs/segdemo
View File

@ -3,7 +3,6 @@
#################################################
wordrec_display_splits 0
wordrec_display_all_words 1
wordrec_display_all_blobs 1
wordrec_display_segmentations 2
classify_debug_level 1