tesseract-ocr/tessdata issues and pull requests

#183 - Required GUI Based App To Train Data On fonts And Different Languages

Issue - State: open - Opened by Farazioo 4 months ago

#182 - Cannot build Tesseract's training tool from source code on M1 Macbook

Issue - State: closed - Opened by yaofuzhou 4 months ago - 3 comments

#181 - Failed loading language 'eng'

Issue - State: closed - Opened by Alookima21 6 months ago - 2 comments
Labels: question

#180 - Rename frk -> deu_latf (ISO 639-3, ISO 15924)

Pull Request - State: closed - Opened by stweil 7 months ago - 1 comment

#179 - Word list in eng.traineddata

Issue - State: open - Opened by jbarth-ubhd 8 months ago - 4 comments

#178 - Need new trained-data for Myanmar.

Issue - State: open - Opened by NChanko 9 months ago

#177 - About the identification of national currency symbol icons

Issue - State: open - Opened by t15137830 12 months ago

#176 - hin.traindata,devnagri.traindata

Issue - State: open - Opened by omuskaikar about 1 year ago

#175 - Failed to load list of training filenames from data/eng/list.train

Issue - State: closed - Opened by xReniar about 1 year ago - 5 comments

#174 - Python: pytesseract does not recognize language Romanian characters on converting PDF files (that contains photocopied images)

Issue - State: closed - Opened by me-suzy over 1 year ago - 1 comment

#173 - Added fast LSTM+legacy model for Akkadian

Pull Request - State: closed - Opened by wincentbalin over 1 year ago - 5 comments

#172 - OCR by chi_tra_vert or chi_sim_vert returns garbled results

Issue - State: closed - Opened by chiehan1 over 1 year ago - 1 comment

#171 - Select screen area bug

Issue - State: closed - Opened by VladislavSharoshkin over 1 year ago - 1 comment

#170 - Tessdata on Homebrew

Issue - State: open - Opened by KaiVinter over 1 year ago - 1 comment
Labels: question

#169 - size of eng.traineddata best/fast/...

Issue - State: closed - Opened by jbarth-ubhd over 1 year ago - 1 comment

#168 - Error: LSTM requested, but not present!! Loading tesseract

Issue - State: closed - Opened by Pierre918 over 1 year ago - 5 comments

#167 - Which font is used for Bengali tessdata?

Issue - State: closed - Opened by debdip about 2 years ago - 1 comment
Labels: question

#166 - orc Portugues Brazil not found

Issue - State: closed - Opened by Level0r0s about 2 years ago - 1 comment
Labels: question

#165 - VietOCR - how to manually config language file if I don't have write access to C:\Program Files\Tesseract-OCR\tessdata folder?

Issue - State: closed - Opened by leolle about 2 years ago - 1 comment

#164 - Which library recognizes operators and numbers？

Issue - State: closed - Opened by stathamcheng over 2 years ago - 1 comment
Labels: question

#163 - Arabic issue

Issue - State: closed - Opened by AbdallahAwd over 2 years ago

#162 - Cannot extract tessdata

Issue - State: closed - Opened by mabrydozier over 2 years ago - 2 comments
Labels: duplicate

#161 - The release is corrupted

Issue - State: closed - Opened by V-kto over 2 years ago - 9 comments
Labels: question

#160 - Modern Greek data issues

Issue - State: open - Opened by chopinesque over 2 years ago - 10 comments
Labels: help wanted

#159 - How to get or make training data for digits only, means `\d` or `[0-9]`

Issue - State: closed - Opened by http600 over 2 years ago - 1 comment
Labels: question

#158 - Problems building tesseract for x86

Issue - State: closed - Opened by mbrunecky over 2 years ago - 1 comment

#157 - How do I use these files?

Issue - State: closed - Opened by pr0fsmith over 2 years ago - 1 comment

#156 - ground truth for enm.traineddata

Issue - State: closed - Opened by whisere over 2 years ago - 7 comments

#155 - symbolic languages like Chinese, Korean and Japanese needs to to be update

Issue - State: open - Opened by SatyamSSJ10 over 2 years ago - 1 comment
Labels: enhancement, help wanted

#154 - ..

Issue - State: closed - Opened by m0binasadi almost 3 years ago

#153 - Removed Inaccessible Submodules

Pull Request - State: closed - Opened by mohamadmansourX about 3 years ago - 1 comment

#151 - Should there be a release made?

Issue - State: closed - Opened by datalogics-kam over 3 years ago - 2 comments
Labels: enhancement

#150 - How to use two. Traineddata files

Issue - State: closed - Opened by D06F6E67 almost 4 years ago - 2 comments

#149 - How to create training data for custom character image

Issue - State: closed - Opened by ghost almost 4 years ago - 1 comment
Labels: question

#148 - ocr quality on `chi_sim`

Issue - State: open - Opened by englianhu almost 4 years ago - 2 comments

#147 - Update README.md

Pull Request - State: closed - Opened by howardjones almost 4 years ago

#146 - orc Chinese image return '\f'

Issue - State: open - Opened by lhyfcs almost 4 years ago - 1 comment

#145 - ita.special-words still missing

Issue - State: closed - Opened by Jmuccigr about 4 years ago - 5 comments
Labels: bug

#144 - any tessdata ocr traineddata for micr (e13b+cmc7) fonts

Issue - State: closed - Opened by ahmadkisswani about 4 years ago - 1 comment
Labels: duplicate

#143 - asking for micr tessdata && cmc7 font tessdata

Issue - State: open - Opened by ahmadkisswani about 4 years ago - 1 comment

#142 - osd.trainedData for orientation detection

Issue - State: closed - Opened by kamrapooja about 4 years ago - 2 comments
Labels: question

#141 - Spanish traineddata name

Issue - State: closed - Opened by lagunero23 about 4 years ago - 6 comments
Labels: question

#140 - update traineddata

Issue - State: closed - Opened by softboy99 over 4 years ago - 1 comment
Labels: question

#139 - Tesseract doesn't recognize "0" and "6" in this image

Issue - State: closed - Opened by dream811 over 4 years ago - 1 comment

#138 - Create OCR

Pull Request - State: closed - Opened by pengjing8 over 4 years ago

#137 - tiffbpl is too small

Issue - State: closed - Opened by mxm2776 over 4 years ago - 1 comment

#136 - Tesseract not recognising character which is in training data for German

Issue - State: closed - Opened by IdiosApps over 4 years ago - 10 comments

#135 - chi_tra.traineddata problem

Issue - State: open - Opened by 13270285331 almost 5 years ago

#134 - Failed loading language 'eng' Tesseract couldn't load any languages! Could not initialize tesseract.

Issue - State: closed - Opened by Uysim almost 5 years ago - 1 comment

#133 - crash in nativeInitOem

Issue - State: closed - Opened by liaosongmao almost 5 years ago - 1 comment

#132 - crash in nativeGetUTF8Text

Issue - State: closed - Opened by liaosongmao almost 5 years ago - 3 comments
Labels: question

#131 - It does not allow selecting languages

Issue - State: closed - Opened by jalle007 almost 5 years ago - 3 comments

#130 - Slovak language tessdata/slk.traineddata not working correctly

Issue - State: closed - Opened by tomasdrgon almost 5 years ago - 1 comment

#128 - How can I in invoke the tessdata in Matlab?

Issue - State: closed - Opened by xxxingzhe about 5 years ago - 1 comment

#126 - Update description for repo - Suggested Text:

Issue - State: open - Opened by Shreeshrii about 5 years ago - 1 comment

#125 - /usr/local/bin/tesstrain_utils.sh: line 80: syntax error near unexpected token `&'

Issue - State: closed - Opened by eravallirao about 5 years ago - 2 comments

#124 - How to apply the copyright

Issue - State: closed - Opened by firiona over 5 years ago - 3 comments

#123 - Add Apache license file

Pull Request - State: closed - Opened by stweil over 5 years ago

#122 - Cannot find protocol declaration for 'G8TesseractDelegate'

Issue - State: closed - Opened by losheredos over 5 years ago - 2 comments

#121 - Add files via upload: MICR for cheque traineddata ocr

Pull Request - State: open - Opened by lloydalido over 5 years ago - 3 comments

#120 - financial numbers reading

Pull Request - State: open - Opened by kpanuragh over 5 years ago - 7 comments

#119 - require an update of japanese trained data

Issue - State: open - Opened by horohoro over 5 years ago - 3 comments

#118 - rename kur_ara.traineddata to kmr.traineddata

Pull Request - State: closed - Opened by Shreeshrii over 5 years ago - 2 comments

#117 - require Updated english traineddata

Issue - State: open - Opened by AnandTiwari1997 over 5 years ago

#116 - Issue on android platform

Issue - State: closed - Opened by jingxinp over 5 years ago - 1 comment

#115 - When I used the language library I trained, the program crashed

Issue - State: closed - Opened by KGDeveloper over 5 years ago - 1 comment

#114 - Add tessconfigs/ and configs/ to .gitignore

Pull Request - State: closed - Opened by wmanley over 5 years ago - 3 comments

#113 - int returnCode = _tesseract->Init(self.absoluteDataPath.UTF8String, self.language.UTF8String, (tesseract::OcrEngineMode)self.engineMode, (char **)configs, count, &tessKeys, &tessValues, false);

Issue - State: closed - Opened by KGDeveloper over 5 years ago - 4 comments

#112 - Pytesseract 4.0 .traineddata on Handwritten Images

Issue - State: closed - Opened by supersaiyan12 almost 6 years ago - 1 comment

#111 - Using language pack for OCR on Windows

Issue - State: closed - Opened by grdesai about 6 years ago - 2 comments

#110 - Issues when using Arabic language

Issue - State: open - Opened by OsamaKhodroj about 6 years ago - 1 comment

#109 - When using jpn.traineddata, numbers are enclosed by cricle

Issue - State: open - Opened by atuyosi about 6 years ago - 1 comment

#108 - Synthetical comparison with Abbyy

Issue - State: open - Opened by jbarth-ubhd about 6 years ago - 18 comments

#107 - Tesseract 4 failed to recognise some words in tabular data

Issue - State: open - Opened by engahmed1190 about 6 years ago

#106 - tessdata- Chinese Simplified Vertical

Issue - State: closed - Opened by tingfengx about 6 years ago - 1 comment

#105 - Best way for tesstwo to recognize decimals and several other characters?

Issue - State: open - Opened by uzbekbear over 6 years ago - 2 comments

#104 - Android error “Fatal signal 6 (SIGABRT), code -6 in tid 9961 (ple.myApp)” when using tesstwo

Issue - State: closed - Opened by uzbekbear over 6 years ago - 1 comment

#103 - is the "IsBinary" funtion return wrong value?

Issue - State: open - Opened by zzb-client over 6 years ago - 1 comment

#102 - Fraktur: Ligatures ch, ck, ſz

Issue - State: closed - Opened by jbarth-ubhd over 6 years ago - 34 comments

#101 - captcha letters is not well recognized

Issue - State: closed - Opened by engahmed1190 over 6 years ago - 1 comment

#100 - Russian language

Issue - State: open - Opened by juhnowski over 6 years ago - 3 comments

#99 - Add scripts from tessdata_best (converted to fast integer models)

Pull Request - State: closed - Opened by stweil over 6 years ago

#98 - Update traineddata

Pull Request - State: closed - Opened by stweil over 6 years ago

#97 - ara.traineddata tesseract4.0 can't recognize

Issue - State: closed - Opened by AbdelsalamHaa over 6 years ago - 1 comment

#96 - ParamsModel::Incomplete line on deu.traineddata

Issue - State: closed - Opened by dg583 over 6 years ago - 6 comments

#95 - crash visualstudio 2017 , windos 10 when tesseract 4 is add

Issue - State: closed - Opened by AbdelsalamHaa over 6 years ago - 1 comment

#94 - Fix typo in README.md

Pull Request - State: closed - Opened by jharia over 6 years ago

#93 - Which data set should i use for Integer recognition ....?

Issue - State: open - Opened by Denaindra over 6 years ago - 1 comment

#92 - Remove parameter textord_tabfind_vertical_horizontal_mix

Pull Request - State: closed - Opened by stweil over 6 years ago

#91 - Tesseract 4.0_Train Katakana Characters for Japanese Language

Issue - State: open - Opened by GunjiVijay over 6 years ago - 1 comment

#90 - Only int best model for indic and arabic script languages

Pull Request - State: closed - Opened by Shreeshrii over 6 years ago - 8 comments

#89 - Update LSTM Models to integerized tessdata_best for files<25mb - 2nd set

Pull Request - State: closed - Opened by Shreeshrii over 6 years ago - 4 comments

#88 - update readme for integerized LSTM models

Pull Request - State: closed - Opened by Shreeshrii over 6 years ago - 11 comments

#87 - jonathanpalma/react-native-tesseract-ocr Error: Data file not found at /storage/emulated/0/com.dvastarter/tessdata/eng.traineddata at createErrorFromErrorData

Issue - State: closed - Opened by dapengJia over 6 years ago - 2 comments

#86 - eng.traindata size

Issue - State: closed - Opened by deepakcrk almost 7 years ago - 1 comment

#85 - Need Mongolian traineddata

Issue - State: open - Opened by Skeetfly almost 7 years ago - 9 comments

#84 - Need handwritten english character Dataset

Issue - State: open - Opened by surajtarade18 almost 7 years ago - 7 comments
Labels: question

GitHub / tesseract-ocr/tessdata issues and pull requests