# **Call for contributor(paper summary,dataset generation,algorithm implementation and any other useful resources)**
# awesome-ocr
A curated list of promising OCR resources
## Librarys
* [Free Offline OCR 离线的文本识别SDK https://github.com/myhub/tr ](https://github.com/myhub/tr)
* [百度api store](http://apistore.baidu.com/astore/servicesearch?word=ocr&searchType=null)
```
有2个api
都支持图片
百度自家的 ：基本可以放弃
化验单识别：也只能提取化验单上三个字段的一个
```
* [阿里云市场](https://market.aliyun.com/products/#ymk=%7B%22keywords%22:%22ocr%22,%22pageSize%22:10,%22saleMode%22:0,%22pageIndex%22:1,%22categoryId%22:%22%22%7D)
```
第三方和阿里自己提供的 API 集中在身份证、银行卡、驾驶证、护照、电商商品评论文本、车牌、名片、贴吧文本、视频中的文本，多输出字符及相应坐标，卡片类可输出成结构化字段，价格在0.01左右
另外有三家提供了简历的解析，输出结果多为结构化字段，支持文档和图片格式 价格在0.1-0.3次不等
```
* [腾讯云](https://cloud.tencent.com/document/product/641/12399)
```
目前无第三方入驻，仅有腾讯自有的api 涵盖车牌、名片、身份证、驾驶证、银行卡、营业执照、通用印刷体，价格最高可达0.2左右。
```
* [ Codes And Documents For OcrKing Api ](https://github.com/AvensLab/OcrKing)
```
OcrKing 从哪来?
OcrKing 源自2009年初 Aven 在数据挖掘中的自用项目，在对技术的执着和爱好的驱动下积累已近七载经多年的积累和迭代，如今已经进化为云架构的集多层神经网络与深度学习于一体的OCR识别系统2010年初为方便更多用户使用，特制作web版文字OCR识别，从始至今 OcrKing一直提供免费识别服务及开发接口，今后将继续提供免费云OCR识别服务。OcrKing从未做过推广，
但也确确实实默默地存在，因为他相信有需求的朋友肯定能找得到。欢迎把 OcrKing 在线识别介绍给您身边有类似需求的朋友！希望这个工具对你有用，谢谢各位的支持！
OcrKing 能做什么?
OcrKing 是一个免费的快速易用的在线云OCR平台，可以将PDF及图片中的内容识别出来，生成一个内容可编辑的文档。支持多种文件格式输入及输出，支持多语种（简体中文，繁体中文，英语，日语，韩语，德语，法语等）识别，支持多种识别方式， 支持多种系统平台， 支持多形式API调用！
```
* [Tesseract-OCR](https://github.com/tesseract-ocr/tesseract)
* [Tesseract.js is a pure Javascript port of the popular Tesseract OCR engine. ](http://tesseract.projectnaptha.com/)
* [tesseract is an R package providing bindings to Tesseract.](https://github.com/ropensci/tesseract)
* [List of Tesseract add-ons including wrappers in different languages.](https://github.com/tesseract-ocr/tesseract/wiki/AddOns)
* [ Ocular is a state-of-the-art historical OCR system. ](https://github.com/tberg12/ocular/)
* [sfhistory Making a map of historical SF photos -博文4所带库 ](https://github.com/danvk/sfhistory)
* [ocropy-论文1所带库 by Adnan Ul-Hasan](https://github.com/tmbdev/ocropy)
* [ A small C++ implementation of LSTM networks, focused on OCR.by Adnan Ul-Hasan ](https://github.com/tmbdev/clstm)
* [ End to end OCR system for Telugu. Based on Convolutional Neural Networks. ](https://github.com/TeluguOCR/banti_telugu_ocr )
* [ Telugu OCR framework using RNN, CTC in Theano & Python3. ](https://github.com/rakeshvar/chamanti_ocr)
* [ Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal Classification implemented in Theano. Includes a Toy training example. ](https://github.com/rakeshvar/rnn_ctc )
* [ implement CTC with keras? #383 ](https://github.com/fchollet/keras/issues/383#issuecomment-166850153)
* [mxnet and ocr ](https://github.com/dmlc/mxnet/issues/1023#issuecomment-167189233)
* [ An OCR-system based on Torch using the technique of LSTM/GRU-RNN, CTC and referred to the works of rnnlib and clstm.](https://github.com/edward-zhu/umaru)
* [ pure javascript lstm rnn implementation based on ocropus ](https://github.com/naptha/ocracy)
* ['caffe-ocr - OCR with caffe deep learning framework' by pannous ](https://github.com/pannous/caffe-ocr)
* [ A implementation of LSTM and CTC to recognize image without splitting ](https://github.com/aaron-xichen/cnn-lstm-ctc)
* [ RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling. It's written by C# language and based on .NET framework 4.6 or above version. RNNSharp supports many different types of RNNs, such as BPTT and LSTM RNN, forward and bi-directional RNNs, and RNN-CRF. ](https://github.com/zhongkaifu/RNNSharp)
* [warp-ctc A fast parallel implementation of CTC, on both CPU and GPU. by BAIDU](https://github.com/baidu-research/warp-ctc)
```
Connectionist Temporal Classification is a loss function useful for performing supervised learning on sequence data, without needing an alignment between input data and labels. For example, CTC can be used to train end-to-end systems for speech recognition, which is how we have been using it at Baidu's Silicon Valley AI Lab.
Warp-CTC是一个可以应用在CPU和GPU上高效并行的CTC代码库 （library） 介绍 CTCConnectionist Temporal Classification作为一个损失函数，用于在序列数据上进行监督式学习，不需要对齐输入数据及标签。比如，CTC可以被用来训练端对端的语音识别系统，这正是我们在百度硅谷试验室所使用的方法。 端到端 系统 语音识别
```
* [ Test mxnet with own trained model,用训练好的网络模型进行数字，少量汉字，特殊字符（./等）的识别（总共有210类）](https://github.com/mittlin/mxnet_test)
* [ An expandable and scalable OCR pipeline ](https://github.com/OpenPhilology/nidaba)
* [OpenOCR makes it simple to host your own OCR REST API.](http://www.openocr.net/)
* [ OCRmyPDF uses Tesseract for OCR, and relies on its language packs. ](https://github.com/jbarlow83/OCRmyPDF)
* [ OwncloudOCR uses tesseract OCR and OCRmyPDF for reading text from images and images in PDF files. ](https://github.com/Pogij/owncloudOCR)
* [ Nextcloud OCR (optical character recoginition) processing for images and PDF with tesseract-ocr, OCRmyPDF and php-native message queueing for asynchronous purpose. http://janis91.github.io/ocr/ ](https://github.com/janis91/ocr)
* [ 多标签分类,端到端的中文车牌识别基于mxnet, End-to-End Chinese plate recognition base on mxnet](https://github.com/szad670401/end-to-end-for-chinese-plate-recognition)
* [中国二代身份证光学识别 ](https://github.com/KevinGong2013/ChineseIDCardOCR)
* [ SwiftOCR:Fast and simple OCR library written in Swift ](https://github.com/garnele007/SwiftOCR)
* [Attention-OCR :Visual Attention based OCR ](https://github.com/da03/Attention-OCR)
* [ Added support for CTC in both Theano and Tensorflow along with image OCR example. #3436](https://github.com/fchollet/keras/blob/master/examples/image_ocr.py)
* [EasyPR是一个开源的中文车牌识别系统，其目标是成为一个简单、高效、准确的车牌识别库。](https://github.com/liuruoze/EasyPR)
* [Deep Embedded Clustering for OCR based on caffe](https://github.com/piiswrong/dec)
* [ Deep Embedded Clustering for OCR based on MXNet](https://github.com/dmlc/mxnet/blob/master/example/dec/dec.py)
* [ The minimum OCR server by Golang The minimum OCR server by Golang, and a tiny sample application of gosseract.](https://github.com/otiai10/ocrserver)
* [ A comparasion among diffe
_A_curated_list_of_promising_OCR_resources_awesome-ocr.zip （63个子文件） 
DataXujing-awesome-ocr-b621bc5 
ocr-engines.md 0B .github workflows greetings.yml 359B resources 
3754个常用汉字列表.txt 11KB 汉语拼音码表-二级汉字拼音对照对照表.txt 25KB 6039.txt 15KB cid2code.txt 1.95MB 汉语拼音码表-一级汉字拼音对照对照表.txt 31KB chinese_5039.txt 15KB special-character.txt 28KB image-acquiistion.md 235B LICENSE 1KB preprocessing.md 0B papers 
深度神经网络结构以及Pre-Training的理解 - cyq0122的专栏 - 博客频道 - CSDN.NET.pdf 4.06MB ijsrp-p3021.pdf 395KB Sequence prediction using recurrent neural networks(LSTM) with TensorFlow — Mourad Mourafiq.pdf 987KB 刘知远. 基于文档主题结构的关键词抽取方法研究.pdf 3.11MB
Figure 2.1- Illustration of basic template matching..png 165KB HOCR specification.pdf 199KB Long-Short Memory Network(LSTM长短期记忆网络) - Physcal - 博客园.pdf 308KB Figure 2.4- Illustration of how RNNs are used for the OCR task.png 251KB V3I3-0224.pdf 432KB Generic Text Recognition using Long Short-Term Memory Networks-PhD_Thesis_Ul-Hasan.pdf 21.76MB The Neural Turing Machine.pdf 2.79MB WEB SCHEMA DETECTION AND DATA EXTRACTION SYSTEM-17_chapter 7.pdf 773KB Relation Schema Induction using Tensor Factorization with Side Information.pdf 465KB Figure 3.3- Example of Fraktur script. Ersch-Gruber is an encyclopedia written in the.png 310KB InfoQ-JHipster-mini-book.pdf 0B A Sequence Learning Approach for Multiple Script Identification.pdf 1.6MB Figure 3.4- Shape confusion in Fraktur script. Many characters in Fraktur resemble.png 164KB Figure 3.6- Word formation in Devanagari script.png 239KB jucs_20_02_0169_0192_grigalis.pdf 411KB Figure 3.7- Reading direction in Nastaleeq script.Nastaleeq script is read from right-.png 169KB Document-Image-Analysis-process.png 303KB Towards a Robust OCR System for Indic Scripts.pdf 1.03MB 1610.01178v1.pdf 480KB 自然语言处理的神经网络入门学习笔记.pdf 13.52MB synthetic text-line image generation process.png 639KB Figure 2.2- Illustration of segmentation process using over-segmentation method..png 270KB Universum Prescription- Regularization Using Unlabeled Data1511.03719v7.pdf 400KB 语义分析的一些方法(一) | 火光摇曳.pdf 764KB
DCA-lecture06.pptx 2.27MB Figure 3.5- Document quality degradation caused during preprocessing..png 113KB Figure 2.3- Figure showing the basic unit in HMM-based OCR. .png 150KB pdf_24.pdf 867KB Schema Extraction for Tabular Data on the Web-p421-adelfio.pdf 378KB
Instructions.doc 22KB
全家桶.jpg 330KB Page - Level Web Data Extraction f rom Template Pages-Chang_FiVaTech.pdf 232KB Representation Learning -A Review and New Perspectives-TPAMISI-2012-04-0260-1.pdf 919KB Statistical Language Modeling for Historical Documents using Weighted Finite-State Transducers and Long Short-Term Memory.pdf 34.26MB Adaptive document image binarization.pdf 867KB UNSUPERVISED APPROACH TO DEDUCE SCHEMA AND EXTRACT DATA FROM TEMPLATE WEB PAGES.pdf 272KB Review paper on “Optimized approaches for web data harvesting.pdf 268KB 文章结构.png 269KB y-derivative of a Gaussian kernel (p. 42).pdf 2.93MB Brian Lott. Survey of Keyword Extraction Techniques.pdf 82KB 1610.05567v1.pdf 5.99MB 车牌识别.md 909B trainning-data-preparing.md 1KB challenge-methods.md 0B .gitignore 10B README.md 26KB post-processing.md 0B资源评论
