- Release [PP-Structurev2](./ppstructure/)，with functions and performance fully upgraded, adapted to Chinese scenes, and new support for [Layout Recovery](./ppstructure/recovery) and **one line command to convert PDF to Word**;
-[Layout Analysis](./ppstructure/layout) optimization: model storage reduced by 95%, while speed increased by 11 times, and the average CPU time-cost is only 41ms;
-[Table Recognition](./ppstructure/table) optimization: 3 optimization strategies are designed, and the model accuracy is improved by 6% under comparable time consumption;
-[Key Information Extraction](./ppstructure/kie) optimization：a visual-independent model structure is designed, the accuracy of semantic entity recognition is increased by 2.8%, and the accuracy of relation extraction is increased by 9.1%.
-**🔥2022.7 Release [OCR scene application collection](./applications/README_en.md)**
- Release **9 vertical models** such as digital tube, LCD screen, license plate, handwriting recognition model, high-precision SVTR model, etc, covering the main OCR vertical applications in general, manufacturing, finance, and transportation industries.
- Release [PP-OCRv3](./doc/doc_en/ppocr_introduction_en.md#pp-ocrv3): With comparable speed, the effect of Chinese scene is further improved by 5% compared with PP-OCRv2, the effect of English scene is improved by 11%, and the average recognition accuracy of 80 language multilingual models is improved by more than 5%.
- Release [PPOCRLabelv2](./PPOCRLabel): Add the annotation function for table recognition task, key information extraction task and irregular text image.
- Release interactive e-book [*"Dive into OCR"*](./doc/doc_en/ocr_book_en.md), covers the cutting-edge theory and code practice of OCR full stack technology.
-[more](./doc/doc_en/update_en.md)
## 🌟 Features
PaddleOCR support a variety of cutting-edge algorithms related to OCR, and developed industrial featured models/solution [PP-OCR](./doc/doc_en/ppocr_introduction_en.md) and [PP-Structure](./ppstructure/README.md) on this basis, and get through the whole process of data production, model training, compression, inference and deployment.
pip3 install paddlepaddle # for gpu user please install paddlepaddle-gpu
pip3 install paddleocr
paddleocr --image_dir ./doc/imgs_en/254.jpg --lang=en # change for i18n abbr
```
> If you don't have Python environment, please follow [Environment Preparation](./doc/doc_en/environment_en.md). We recommend you starting with [Tutorials](#Tutorials).
<aname="book"></a>
## 📚 E-book: *Dive Into OCR*
-[Dive Into OCR ](./doc/doc_en/ocr_book_en.md)
<aname="Community"></a>
## 👫 Community
For international developers, we regard [PaddleOCR Discussions](https://github.com/PaddlePaddle/PaddleOCR/discussions) as our international community platform. All ideas and questions can be discussed here in English.
<aname="Supported-Chinese-model-list"></a>
## 🛠️ PP-OCR Series Model List
| Model introduction | Model name | Recommended scene | Detection model | Direction classifier | Recognition model |
-[Key Information Extraction](doc/doc_en/dataset/kie_datasets_en.md)
-[Code Structure](./doc/doc_en/tree_en.md)
-[Visualization](#Visualization)
-[Community](#Community)
-[New language requests](#language_requests)
-[FAQ](./doc/doc_en/FAQ_en.md)
-[References](./doc/doc_en/reference_en.md)
-[License](#LICENSE)
<aname="language_requests"></a>
## 🇺🇳 Guideline for New Language Requests
If you want to **request a new language model**, please vote in [Vote for Multilingual Model Upgrades](https://github.com/PaddlePaddle/PaddleOCR/discussions/7253). We will upgrade model according to the result regularly. **Invite your friends to vote together!**
If you need to **train a new language model** based on your scenario, the tutorial in [Multilingual Model Training Project](https://github.com/PaddlePaddle/PaddleOCR/discussions/7252) will help you prepare dataset and show you the whole process step by step.
The original [Multilingual OCR Development Plan](https://github.com/PaddlePaddle/PaddleOCR/issues/1048) still shows you a lot of useful corpus and dictionaries
