Go to file
LDOUBLEV fe43fc3e0b fix bug 2021-08-19 12:26:00 +00:00
PPOCRLabel update Shortcut Keys 2021-07-06 11:19:22 +08:00
StyleText dbg (#3236) 2021-07-02 10:38:04 +08:00
configs update 2.2 2021-08-03 08:34:26 +00:00
deploy fix cpp 2021-08-09 12:44:14 +00:00
doc Add new visualization results 2021-08-08 13:21:47 +08:00
ppocr return None when no boxes found 2021-08-03 06:55:21 +00:00
ppstructure Update README_ch.md 2021-08-16 17:45:19 +08:00
tools fix bug 2021-08-19 12:26:00 +00:00
.clang_format.hook upload lite demo and clang-fomat 2020-07-07 07:40:39 +00:00
.gitignore update 180.jpg 2021-04-09 15:31:51 +08:00
.pre-commit-config.yaml upload PaddleOCR code 2020-05-10 16:26:57 +08:00
.style.yapf upload PaddleOCR code 2020-05-10 16:26:57 +08:00
LICENSE Initial commit 2020-05-08 18:38:17 +08:00
MANIFEST.in merge paddlestructure whl to paddleocr whl 2021-08-02 15:28:07 +08:00
README.md Update README.md 2021-08-16 15:10:05 +08:00
README_ch.md Update README_ch.md 2021-08-16 15:05:36 +08:00
__init__.py fix bug when inference with network img 2021-08-03 15:37:32 +08:00
paddleocr.py update paddleocr version 2 2.2.0.1 2021-08-06 11:23:00 +08:00
requirements.txt cp 3523 2021-08-09 11:07:45 +08:00
setup.py merge paddlestructure whl to paddleocr whl 2021-08-02 15:28:07 +08:00
train.sh opt deploy doc 2021-02-02 21:08:13 +08:00

README.md

English | 简体中文


Introduction

PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools that help users train better models and apply them into practice.

Notice

PaddleOCR supports both dynamic graph and static graph programming paradigm

  • Dynamic graph: V2.2 branch (default), supported by paddle 2.1.1 (installation)
  • Static graph: develop branch

Recent updates

  • PaddleOCR R&D team would like to share the released tools with developers, at 20:15 pm on August 4th, Live Address.
  • 2021.8.3 released PaddleOCR v2.2, add a new structured documents analysis toolkit, i.e., PP-Structure, support layout analysis and table recognition (One-key to export chart images to Excel files).
  • 2021.4.8 release end-to-end text recognition algorithm PGNet which is published in AAAI 2021. Find tutorial hererelease multi language recognition models, support more than 80 languages recognition; especically, the performance of English recognition model is Optimized.
  • 2021.1.21 update more than 25+ multilingual recognition models models list, includingEnglish, Chinese, German, French, JapaneseSpanishPortuguese Russia Arabic and so on. Models for more languages will continue to be updated Develop Plan.
  • 2020.12.15 update Data synthesis tool, i.e., Style-Texteasy to synthesize a large number of images which are similar to the target scene image.
  • 2020.11.25 Update a new data annotation tool, i.e., PPOCRLabel, which is helpful to improve the labeling efficiency. Moreover, the labeling results can be used in training of the PP-OCR system directly.
  • 2020.9.22 Update the PP-OCR technical article, https://arxiv.org/abs/2009.09941
  • more

Features

  • PPOCR series of high-quality pre-trained models, comparable to commercial effects
    • Ultra lightweight ppocr_mobile series models: detection (3.0M) + direction classifier (1.4M) + recognition (5.0M) = 9.4M
    • General ppocr_server series models: detection (47.1M) + direction classifier (1.4M) + recognition (94.9M) = 143.4M
    • Support Chinese, English, and digit recognition, vertical text recognition, and long text recognition
    • Support multi-language recognition: Korean, Japanese, German, French
  • Rich toolkits related to the OCR areas
    • Semi-automatic data annotation tool, i.e., PPOCRLabel: support fast and efficient data annotation
    • Data synthesis tool, i.e., Style-Text: easy to synthesize a large number of images which are similar to the target scene image
  • Support user-defined training, provides rich predictive inference deployment solutions
  • Support PIP installation, easy to use
  • Support Linux, Windows, MacOS and other systems

Visualization

The above pictures are the visualizations of the general ppocr_server model. For more effect pictures, please see More visualizations.

Community

  • Scan the QR code below with your Wechat, you can access to official technical exchange group. Look forward to your participation.

Quick Experience

You can also quickly experience the ultra-lightweight OCR : Online Experience

Mobile DEMO experience (based on EasyEdge and Paddle-Lite, supports iOS and Android systems): Sign in to the website to obtain the QR code for installing the App

Also, you can scan the QR code below to install the App (Android support only)

PP-OCR 2.0 series model listUpdate on Dec 15

Note : Compared with models 1.1, which are trained with static graph programming paradigm, models 2.0 are the dynamic graph trained version and achieve close performance.

Model introduction Model name Recommended scene Detection model Direction classifier Recognition model
Chinese and English ultra-lightweight OCR model (9.4M) ch_ppocr_mobile_v2.0_xx Mobile & server inference model / pre-trained model inference model / pre-trained model inference model / pre-trained model
Chinese and English general OCR model (143.4M) ch_ppocr_server_v2.0_xx Server inference model / pre-trained model inference model / pre-trained model inference model / pre-trained model

For more model downloads (including multiple languages), please refer to PP-OCR v2.0 series model downloads.

For a new language request, please refer to Guideline for new language_requests.

Tutorials

PP-OCR Pipeline

PP-OCR is a practical ultra-lightweight OCR system. It is mainly composed of three parts: DB text detection[2], detection frame correction and CRNN text recognition[7]. The system adopts 19 effective strategies from 8 aspects including backbone network selection and adjustment, prediction head design, data augmentation, learning rate transformation strategy, regularization parameter selection, pre-training model use, and automatic model tailoring and quantization to optimize and slim down the models of each module. The final results are an ultra-lightweight Chinese and English OCR model with an overall size of 3.5M and a 2.8M English digital OCR model. For more details, please refer to the PP-OCR technical article (https://arxiv.org/abs/2009.09941). Besides, The implementation of the FPGM Pruner [8] and PACT quantization [9] is based on PaddleSlim.

Visualization more

  • Chinese OCR model
  • English OCR model
  • Multilingual OCR model

Guideline for new language requests

If you want to request a new language support, a PR with 2 following files are needed

  1. In folder ppocr/utils/dict, it is necessary to submit the dict text to this path and name it with {language}_dict.txt that contains a list of all characters. Please see the format example from other files in that folder.

  2. In folder ppocr/utils/corpus, it is necessary to submit the corpus to this path and name it with {language}_corpus.txt that contains a list of words in your language. Maybe, 50000 words per language is necessary at least. Of course, the more, the better.

If your language has unique elements, please tell me in advance within any way, such as useful links, wikipedia and so on.

More details, please refer to Multilingual OCR Development Plan.

License

This project is released under Apache 2.0 license

Contribution

We welcome all the contributions to PaddleOCR and appreciate for your feedback very much.

  • Many thanks to Khanh Tran and Karl Horky for contributing and revising the English documentation.
  • Many thanks to zhangxin for contributing the new visualize function、add .gitignore and discard set PYTHONPATH manually.
  • Many thanks to lyl120117 for contributing the code for printing the network structure.
  • Thanks xiangyubo for contributing the handwritten Chinese OCR datasets.
  • Thanks authorfu for contributing Android demo and xiadeye contributing iOS demo, respectively.
  • Thanks BeyondYourself for contributing many great suggestions and simplifying part of the code style.
  • Thanks tangmq for contributing Dockerized deployment services to PaddleOCR and supporting the rapid release of callable Restful API services.
  • Thanks lijinhan for contributing a new way, i.e., java SpringBoot, to achieve the request for the Hubserving deployment.
  • Thanks Mejans for contributing the Occitan corpus and character set.
  • Thanks LKKlein for contributing a new deploying package with the Golang program language.
  • Thanks Evezerest, ninetailskim, edencfc, BeyondYourself and 1084667371 for contributing a new data annotation tool, i.e., PPOCRLabel。