AddOns - kana112233/tesseract GitHub Wiki

有关Tesseract和其他第三方项目的GUI界面,请参阅用户项目 - 第三方

#Tesseract的外部工具,包装和培训项目

Tesseract盒子编辑器和培训工具

平台支持取决于使用的语言和用户体验.

###对于Tesseract-OCR 3.0x

Box文件编辑器

Name	Last update	Language	Multipage support
jTessBoxEditor	2018	Java	yes
QT Box Editor	2018	C++, Qt4/Qt5	yes
tesseract-box-editor	2013	.NET 4	yes
Tesseract-OCR boxfile AJAX editor	2012	online tool
cowboxer	2012	C++, Qt4	no
moshPyTT	2011	Python, GTK2	no
pytesseracttrainer	2011	Python, GTK2	no

###对于Tesseract-OCR 2.0x

Box文件编辑器

Name	Last update	Language
Tesseract-OCR boxfile AJAX editor	2012	online tool
owlboxer	2010	C++, Qt4
Tessboxer	2009	.NET
boxfilereader.php	2009	php
tessboxes	2008	C
JTesseract	2008	C#
wx-tetra	2008	perl, wx
bbtesseract	2008	VB.NET 2008

Other Training Tools

• jTessBoxEditor | Box Editor and Training Tool

• MzTesseract - MS Windows program that can train new language from top to bottom

• FrankenPlus - tool for creating font training for Tesseract OCR engine from page images. More information about Franken+ is at at IT'S ALIVE! and Franken+ homepage.

• python-tesseract-3.02-training - script to automate the generation of Tesseract 3.02 training files

• tesseract-box-file - autoit script to make editing the box file easier

• Serak Tesseract Trainer for Tesseract 3.02 - a front end GUI for training tesseract 3.02

• BoxMaker is online tool for generating image&box pair. Offline version is available in download section of PersianOCR project

• boxFactory is a tool for quickly creating box files to train the Tesseract OCR engine. You can identify characters in the image by simply drawing boxes around them.

• https://github.com/BaltoRouberol/TesseractTrainer - TesseractTrainer is a simple Python API, taking over the tedious process of manually training Tesseract3

• tess_school - a set of handy scripts to make the tesseract training process a bit easier

• txt2img: Qt GUI application that generate image and box file based on text imput

• DangAmbigs Generator: Creates a DangAmbigs file automatically given a set of OCR text output and correct text. Requirements: Python

• train.ps1: Windows powershell script for Automate Tesseract 3.01 language data pack generation process.

• Update unicharambigs.exe: A small (windows) C# program for editing "lang.unicharambigs" file

• train_tess.pl: perl script to facilitate training

• boxedit A web-based editor for Tesseract box files

• TrainYourTesseract | Free online "no-hassle" TTF file to trainedata converter

##社区培训项目

• ** Tesseract-MICR-OCR **:https://github.com/BigPino67/Tesseract-MICR-OCR   
• ** MRZ **:https://groups.google.com/group/tesseract-ocr/attach/10d7c711c9cc80/mrz.traineddata   
• 拉丁语:https://github.com/ryanfb/latinocr-lattraining   
• ** tesseract-georgian **:https://github.com/ddohler/tesseract-georgian   
• ** Polish Fraktur **:作为[IMPACT项目的结果]进行培训(http://dl.psnc.pl/activities/projekty/impact/results/),[训练数据集](http://dl.psnc 特等/下载/tesseract_traineddata.zip)   
• 古希腊语:http://ancientgreekocr.org   
• 印度:http://code.google.com/p/tesseractindic/,https://github.com/debayan/Tesseract-Indic-OCR/,http://code.google.com/p /parichit/(全部已过时)   
• **印度语 - OCR ** http://indic-ocr.github.io/tessdata/  
• **爱尔兰uncial **:https://github.com/jimregan/tesseract-gle-uncial   
• 波兰语:http://code.google.com/p/tesseract-polish/  
• ** Fraktur **(dan,deu,swe):https://github.com/paalberti/tesseract-dan-fraktur   
• 缅甸:http://code.google.com/p/myaocr/  
• 波斯语(波斯语):https://github.com/reza1615/PersianOcr   
• ** 7段字体**:https://github.com/arturaugusto/display_ocr/tree/master/letsgodigital

##端口

• Naptha项目   
• tesseract.js-core - Tesseract C ++ API的Emscripten端口   
• tesseract.js - 纯Javascript OCR

Tesseract包装器

Tesseract 4.0x

** **的Java   

• bytedeco - 基于来自https://bytedeco.org的“JavaCPP-Presets”库的Tesseract的Java配置和接口类 - https://github.com/bytedeco/javacpp-presets

Tesseract 3.0x

C   

• Tesseract 3.02及更高版本包括C API

.净   

• charlesw/tesseract - 项目提供[tesseract-ocr 64bit Windows库](https://github.com/charlesw/tesseract/tree/master/src/ LIB/TesseractOcr/x64)的   
• http://code.google.com/p/tesseractdotnet/

蟒蛇   

• tesserocr - 围绕Tesseract的C ++ API的Python包装器   
• pyocr - Tesseract(和楔形文字)的Python包装器   
• tesserwrap - 与Tesseract API的Python绑定   
• tesseract-sip - 用于libtesseract的python SIP包装器(Apache许可证)   
• pytesseract - Tesseract OCR的包装类   
• python-tesseract(替代链接) - 一个包装类 Tesseract OCR允许任何传统图像文件(基于SWIG)   
• http://code.google.com/p/pytess/ - 一个简单的基于SWIG的Tesseract界面

** R **   

• tesseract与R编程语言的C ++ API绑定

红宝石   

• ruby-tesseract-ocr - 使用C ++ API的tesseract 3.0x包装器   
• rtesseract

** **的Java   

• bytedeco - 基于来自https://bytedeco.org的“JavaCPP-Presets”库的Tesseract的Java配置和接口类 - https://github.com/bytedeco/javacpp-presets   
• tess4j - JNA包装器. 文档和讨论 - http://tess4j.sourceforge.net/

** **的Node.js   

• penteract - 本机node.js绑定到Tesseract OCR项目.

** ** PHP   

• tesseract-ocr-for-php   
• https://code.google.com/p/php-tesseract/

**目标C **   

• Tesseract-macOS   
• Tesseract-OCR-iOS   
• tesseract-ios

走   

• gosseract

** **的Clojure   

• clj-tesseract

Tesseract 2.0x

蟒蛇   

• https://github.com/hoffstaetter/python-tesseract/wiki   
• http://code.google.com/p/pytesser/  
• http://code.google.com/p/tesseract-python(pytesser clone)   
• https://github.com/hoffstaetter/python-tesseract/wiki   
• http://pokerai.org/pf3/viewtopic.php?f=3&t=2677&start=0&st=0&sk=t&sd=a   
• SWIG包装的补丁for python

.净   

• http://www.pixel-technology.com/freeware/tessnet2/

** **的Java   

• tess4j(0.4) - JNA包装器. 文档和讨论 - http://tess4j.sourceforge.net/