akira
/
tesseract.js
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Browse Source

Merge pull request #20 from radarhere/patch-1 

Fixed typos
pull/25/head
bijection 8 years ago committed by GitHub
parent
b3cc0c0293 162deeebdb
commit
e9735cdc9c
1 changed files with 7 additions and 7 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 14
      docs/tesseract_parameters.md

14
docs/tesseract_parameters.md
Unescape View File

@ -298,10 +298,10 @@ You can override the following parameters in the options object passed to `Tesse @@ -298,10 +298,10 @@ You can override the following parameters in the options object passed to `Tesse
| segment_penalty_dict_frequent_word | 1 | Score multiplier for word matches which have good case andare frequent in the given language (lower is better). |
| segment_penalty_dict_nonword | 1.25 | Score multiplier for glyph fragment segmentations which do not match a dictionary word (lower is better). |
| segment_penalty_garbage | 1.5 | Score multiplier for poorly cased strings that are not in the dictionary and generally look like garbage (lower is better). |
| segment_penalty_ngram_best_choice | 1.24 | Multipler to for the best choice from the ngram model. |
| segment_reward_chartype | 0.97 | Score multipler for char type consistency within a word. |
| segment_reward_ngram_best_choice | 0.99 | Score multipler for ngram permuter's best choice (only used in the Han script path). |
| segment_reward_script | 0.95 | Score multipler for script consistency within a word. Being a 'reward' factor, it should be <= 1. Smaller value implies bigger reward. |
| segment_penalty_ngram_best_choice | 1.24 | Multiplier to for the best choice from the ngram model. |
| segment_reward_chartype | 0.97 | Score multiplier for char type consistency within a word. |
| segment_reward_ngram_best_choice | 0.99 | Score multiplier for ngram permuter's best choice (only used in the Han script path). |
| segment_reward_script | 0.95 | Score multiplier for script consistency within a word. Being a 'reward' factor, it should be <= 1. Smaller value implies bigger reward. |
| segment_segcost_rating | 0 | incorporate segmentation cost in word rating? |
| segsearch_debug_level | 0 | SegSearch debug level |
| segsearch_max_char_wh_ratio | 2 | Maximum character width-to-height ratio |
@ -310,7 +310,7 @@ You can override the following parameters in the options object passed to `Tesse @@ -310,7 +310,7 @@ You can override the following parameters in the options object passed to `Tesse
| segsearch_max_pain_points | 2000 | Maximum number of pain points stored in the queue |
| speckle_large_max_size | 0.3 | Max large speckle size |
| speckle_rating_penalty | 10 | Penalty to add to worst rating for noise |
| stopper_allowable_character_badness | 3 | Max certaintly variation allowed in a word (in sigma) |
| stopper_allowable_character_badness | 3 | Max certainty variation allowed in a word (in sigma) |
| stopper_certainty_per_char | -0.5 | Certainty to add for each dict char above small word size. |
| stopper_debug_level | 0 | Stopper debug level |
| stopper_no_acceptable_choices | 0 | Make AcceptableChoice() always return false. Useful when there is a need to explore all segmentations |
@ -374,7 +374,7 @@ You can override the following parameters in the options object passed to `Tesse @@ -374,7 +374,7 @@ You can override the following parameters in the options object passed to `Tesse
| tessedit_ocr_engine_mode | 0 | Which OCR engine(s) to run (Tesseract, Cube, both). Defaults to loading and running only Tesseract (no Cube,no combiner). Values from OcrEngineMode enum in tesseractclass.h) |
| tessedit_ok_mode | 5 | Acceptance decision algorithm |
| tessedit_override_permuter | 1 | According to dict_word |
| tessedit_page_number | -1 | -1 -> All pages , else specifc page to process |
| tessedit_page_number | -1 | -1 -> All pages , else specific page to process |
| tessedit_pageseg_mode | 6 | 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) |
| tessedit_parallelize | 0 | Run in parallel where possible |
| tessedit_prefer_joined_punct | 0 | Reward punctation joins |
@ -414,7 +414,7 @@ You can override the following parameters in the options object passed to `Tesse @@ -414,7 +414,7 @@ You can override the following parameters in the options object passed to `Tesse
| test_pt | 0 | Test for point |
| test_pt_x | 100000 | xcoord |
| test_pt_y | 100000 | ycoord |
| textord_all_prop | 0 | All doc is proportial text |
| textord_all_prop | 0 | All doc is proportional text |
| textord_ascheight_mode_fraction | 0.08 | Min pile height to make ascheight |
| textord_ascx_ratio_max | 1.8 | Max cap/xheight |
| textord_ascx_ratio_min | 1.25 | Min cap/xheight |

Write Preview
Loading…
Cancel
Save