README.md 15.4 KB
Newer Older
1
English | [简体中文](README_ch.md)
2

3
## Introduction
G
grasswolfs 已提交
4
PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools that help users train better models and apply them into practice.
D
dyning 已提交
5

6
**Recent updates**
G
grasswolfs 已提交
7
- 2020.11.25 Update a new data annotation tool, i.e., [PPOCRLabel](./PPOCRLabel/README_en.md),which is helpful to improve the labeling efficiency. Moreover, the labeling results can be used in training of the PP-OCR system directly.
D
dyning 已提交
8
- 2020.9.22 Update the PP-OCR technical article, https://arxiv.org/abs/2009.09941
D
Daniel Yang 已提交
9
- 2020.9.19 Update the ultra lightweight compressed ppocr_mobile_slim series models, the overall model size is 3.5M (see [PP-OCR Pipeline](#PP-OCR-Pipeline)), suitable for mobile deployment. [Model Downloads](#Supported-Chinese-model-list)
10
- 2020.9.17 Update the ultra lightweight ppocr_mobile series and general ppocr_server series Chinese and English ocr models, which are comparable to commercial effects. [Model Downloads](#Supported-Chinese-model-list)
G
grasswolfs 已提交
11
- 2020.9.17 update [English recognition model](./doc/doc_en/models_list_en.md#english-recognition-model) and [Multilingual recognition model](doc/doc_en/models_list_en.md#english-recognition-model), `English`, `Chinese`, `German`, `French`, `Japanese` and `Korean` have been supported. Models for more languages will continue to be updated.
D
Daniel Yang 已提交
12
- 2020.8.24 Support the use of PaddleOCR through whl package installation,please refer  [PaddleOCR Package](./doc/doc_en/whl_en.md)
13 14
- 2020.8.21 Update the replay and PPT of the live lesson at Bilibili on August 18, lesson 2, easy to learn and use OCR tool spree. [Get Address](https://aistudio.baidu.com/aistudio/education/group/info/1519)
- [more](./doc/doc_en/update_en.md)
D
dyning 已提交
15

16 17 18 19 20 21 22 23 24 25
## Features
- PPOCR series of high-quality pre-trained models, comparable to commercial effects
    - Ultra lightweight ppocr_mobile series models: detection (2.6M) + direction classifier (0.9M) + recognition (4.6M) = 8.1M
    - General ppocr_server series models: detection (47.2M) + direction classifier (0.9M) + recognition (107M) = 155.1M
    - Ultra lightweight compression ppocr_mobile_slim series models: detection (1.4M) + direction classifier (0.5M) + recognition (1.6M) = 3.5M
- Support Chinese, English, and digit recognition, vertical text recognition, and long text recognition
- Support multi-language recognition: Korean, Japanese, German, French
- Support user-defined training, provides rich predictive inference deployment solutions
- Support PIP installation, easy to use
- Support Linux, Windows, MacOS and other systems
G
grasswolfs 已提交
26

27
## Visualization
L
LDOUBLEV 已提交
28

G
grasswolfs 已提交
29
<div align="center">
G
grasswolfs 已提交
30
    <img src="doc/imgs_results/1101.jpg" width="800">
D
Daniel Yang 已提交
31
    <img src="doc/imgs_results/1103.jpg" width="800">
G
grasswolfs 已提交
32
</div>
D
dyning 已提交
33

D
Daniel Yang 已提交
34
The above pictures are the visualizations of the general ppocr_server model. For more effect pictures, please see [More visualizations](./doc/doc_en/visualization_en.md).
35

G
grasswolfs 已提交
36 37 38 39 40 41 42 43 44
<a name="Community"></a>
## Community
- Scan the QR code below with your Wechat, you can access to official technical exchange group. Look forward to your participation.

<div align="center">
<img src="./doc/joinus.PNG"  width = "200" height = "200" />
</div>


45
## Quick Experience
D
dyning 已提交
46

47
You can also quickly experience the ultra-lightweight OCR : [Online Experience](https://www.paddlepaddle.org.cn/hub/scene/ocr)
G
grasswolfs 已提交
48

49
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](https://ai.baidu.com/easyedge/app/openSource?from=paddlelite)
D
dyning 已提交
50

51
 Also, you can scan the QR code below to install the App (**Android support only**)
D
dyning 已提交
52 53 54 55 56

<div align="center">
<img src="./doc/ocr-android-easyedge.png"  width = "200" height = "200" />
</div>

57 58 59 60 61 62
- [**OCR Quick Start**](./doc/doc_en/quickstart_en.md)

<a name="Supported-Chinese-model-list"></a>

## PP-OCR 1.1 series model list(Update on Sep 17)

L
LDOUBLEV 已提交
63 64 65 66
| Model introduction                                           | Model name                   | Recommended scene | Detection model                                              | Direction classifier                                         | Recognition model                                            |
| ------------------------------------------------------------ | ---------------------------- | ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| Chinese and English ultra-lightweight OCR model (8.1M)       | ch_ppocr_mobile_v1.1_xx      | Mobile & server   | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/cls/ch_ppocr_mobile_v1.1_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/cls/ch_ppocr_mobile_v1.1_cls_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_pre.tar) |  
| Chinese and English general OCR model (155.1M)               | ch_ppocr_server_v1.1_xx      | Server            | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/cls/ch_ppocr_mobile_v1.1_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/cls/ch_ppocr_mobile_v1.1_cls_train.tar) | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_pre.tar) |  
L
LDOUBLEV 已提交
67
| Chinese and English ultra-lightweight compressed OCR model (3.5M) | ch_ppocr_mobile_slim_v1.1_xx | Mobile            | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_infer.tar) / [slim model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/lite/ch_ppocr_mobile_v1.1_det_prune_opt.nb) | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/cls/ch_ppocr_mobile_v1.1_cls_quant_infer.tar) / [slim model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/lite/ch_ppocr_mobile_v1.1_cls_quant_opt.nb) |    [inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_infer.tar) / [slim model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/lite/ch_ppocr_mobile_v1.1_rec_quant_opt.nb) |
G
grasswolfs 已提交
68 69 70 71
| French ultra-lightweight OCR model (4.6M)       | french_ppocr_mobile_v1.1_xx      | Mobile & server   | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_train.tar) | - | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/fr/french_ppocr_mobile_v1.1_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/fr/french_ppocr_mobile_v1.1_rec_train.tar)  |
| German ultra-lightweight OCR model (4.6M)       | german_ppocr_mobile_v1.1_xx      | Mobile & server   | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_train.tar) | - |[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/ge/german_ppocr_mobile_v1.1_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/ge/german_ppocr_mobile_v1.1_rec_train.tar) |
| Korean ultra-lightweight OCR model (5.9M)       | korean_ppocr_mobile_v1.1_xx      | Mobile & server   | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_train.tar) | - |[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/kr/korean_ppocr_mobile_v1.1_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/kr/korean_ppocr_mobile_v1.1_rec_train.tar)|
| Japan ultra-lightweight OCR model (6.2M)       | japan_ppocr_mobile_v1.1_xx      | Mobile & server   | [inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_train.tar) | - |[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/jp/japan_ppocr_mobile_v1.1_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/jp/japan_ppocr_mobile_v1.1_rec_train.tar)  |
72

G
grasswolfs 已提交
73
For more model downloads (including multiple languages), please refer to [PP-OCR v1.1 series model downloads](./doc/doc_en/models_list_en.md).
74

G
grasswolfs 已提交
75
For a new language request, please refer to [Guideline for new language_requests](#language_requests).
76 77 78 79 80 81 82 83

## Tutorials
- [Installation](./doc/doc_en/installation_en.md)
- [Quick Start](./doc/doc_en/quickstart_en.md)
- [Code Structure](./doc/doc_en/tree_en.md)
- Algorithm introduction
    - [Text Detection Algorithm](./doc/doc_en/algorithm_overview_en.md)
    - [Text Recognition Algorithm](./doc/doc_en/algorithm_overview_en.md)
D
Daniel Yang 已提交
84
    - [PP-OCR Pipeline](#PP-OCR-Pipeline)
85 86 87
- Model training/evaluation
    - [Text Detection](./doc/doc_en/detection_en.md)
    - [Text Recognition](./doc/doc_en/recognition_en.md)
T
tink2123 已提交
88
    - [Direction Classification](./doc/doc_en/angle_class_en.md)
89 90 91 92 93 94 95 96 97
    - [Yml Configuration](./doc/doc_en/config_en.md)
- Inference and Deployment
    - [Quick inference based on pip](./doc/doc_en/whl_en.md)
    - [Python Inference](./doc/doc_en/inference_en.md)
    - [C++ Inference](./deploy/cpp_infer/readme_en.md)
    - [Serving](./deploy/hubserving/readme_en.md)
    - [Mobile](./deploy/lite/readme_en.md)
    - [Model Quantization](./deploy/slim/quantization/README_en.md)
    - [Model Compression](./deploy/slim/prune/README_en.md)
G
grasswolfs 已提交
98 99 100 101 102
    - [Benchmark](./doc/doc_en/benchmark_en.md)  
- Data annotation and Synthesis
    - [Semi-automatic Annotation Tool](./PPOCRLabel/README_en.md)
    - [Data Annotation Tools](./doc/doc_en/data_annotation_en.md)
    - [Data Synthesis Tools](./doc/doc_en/data_synthesis_en.md)
103 104 105 106 107
- Datasets
    - [General OCR Datasets(Chinese/English)](./doc/doc_en/datasets_en.md)
    - [HandWritten_OCR_Datasets(Chinese)](./doc/doc_en/handwritten_datasets_en.md)
    - [Various OCR Datasets(multilingual)](./doc/doc_en/vertical_and_multilingual_datasets_en.md)
- [Visualization](#Visualization)
G
grasswolfs 已提交
108
- [New language requests](#language_requests)
D
dyning 已提交
109
- [FAQ](./doc/doc_en/FAQ_en.md)
110 111 112 113 114
- [Community](#Community)
- [References](./doc/doc_en/reference_en.md)
- [License](#LICENSE)
- [Contribution](#CONTRIBUTION)

D
Daniel Yang 已提交
115
<a name="PP-OCR-Pipeline"></a>
116

D
Daniel Yang 已提交
117
## PP-OCR Pipeline
118

G
grasswolfs 已提交
119 120 121 122
<div align="center">
    <img src="./doc/ppocr_framework.png" width="800">
</div>

G
grasswolfs 已提交
123
PP-OCR is a practical ultra-lightweight OCR system. It is mainly composed of three parts: DB text detection, detection frame correction and CRNN text recognition. 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 and PACT quantization is based on [PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim).
D
dyning 已提交
124 125


D
dyning 已提交
126

127
## Visualization [more](./doc/doc_en/visualization_en.md)
M
MissPenguin 已提交
128
- Chinese OCR model
G
grasswolfs 已提交
129
<div align="center">
D
Daniel Yang 已提交
130
    <img src="./doc/imgs_results/1102.jpg" width="800">
G
grasswolfs 已提交
131
    <img src="./doc/imgs_results/1104.jpg" width="800">
G
grasswolfs 已提交
132
    <img src="./doc/imgs_results/1106.jpg" width="800">
G
grasswolfs 已提交
133
    <img src="./doc/imgs_results/1105.jpg" width="800">
M
MissPenguin 已提交
134 135 136 137 138 139 140 141 142
</div>

- English OCR model
<div align="center">
    <img src="./doc/imgs_results/img_12.jpg" width="800">
</div>

- Multilingual OCR model
<div align="center">
G
grasswolfs 已提交
143 144
    <img src="./doc/imgs_results/1110.jpg" width="800">
    <img src="./doc/imgs_results/1112.jpg" width="800">
G
grasswolfs 已提交
145
</div>
T
tink2123 已提交
146

D
dyning 已提交
147

G
grasswolfs 已提交
148 149
<a name="language_requests"></a>
## Guideline for new language requests
G
grasswolfs 已提交
150 151 152

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

G
grasswolfs 已提交
153 154
1. In folder [ppocr/utils/dict](https://github.com/PaddlePaddle/PaddleOCR/tree/develop/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.
G
grasswolfs 已提交
155

G
grasswolfs 已提交
156 157
2. In folder [ppocr/utils/corpus](https://github.com/PaddlePaddle/PaddleOCR/tree/develop/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.
G
grasswolfs 已提交
158 159 160 161 162
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.

G
grasswolfs 已提交
163
More details, please refer to [Multilingual OCR Development Plan](https://github.com/PaddlePaddle/PaddleOCR/issues/1048).
G
grasswolfs 已提交
164

M
MissPenguin 已提交
165

166 167 168 169 170 171 172 173 174 175 176 177 178 179 180
<a name="LICENSE"></a>
## License
This project is released under <a href="https://github.com/PaddlePaddle/PaddleOCR/blob/master/LICENSE">Apache 2.0 license</a>

<a name="CONTRIBUTION"></a>
## Contribution
We welcome all the contributions to PaddleOCR and appreciate for your feedback very much.

- Many thanks to [Khanh Tran](https://github.com/xxxpsyduck) and [Karl Horky](https://github.com/karlhorky) for contributing and revising the English documentation.
- Many thanks to [zhangxin](https://github.com/ZhangXinNan) for contributing the new visualize function、add .gitgnore and discard set PYTHONPATH manually.
- Many thanks to [lyl120117](https://github.com/lyl120117) for contributing the code for printing the network structure.
- Thanks [xiangyubo](https://github.com/xiangyubo) for contributing the handwritten Chinese OCR datasets.
- Thanks [authorfu](https://github.com/authorfu) for contributing Android demo  and [xiadeye](https://github.com/xiadeye) contributing iOS demo, respectively.
- Thanks [BeyondYourself](https://github.com/BeyondYourself) for contributing many great suggestions and simplifying part of the code style.
- Thanks [tangmq](https://gitee.com/tangmq) for contributing Dockerized deployment services to PaddleOCR and supporting the rapid release of callable Restful API services.
G
grasswolfs 已提交
181 182
- Thanks [lijinhan](https://github.com/lijinhan) for contributing a new way, i.e., java SpringBoot, to achieve the request for the Hubserving deployment.
- Thanks [Mejans](https://github.com/Mejans) for contributing the Occitan corpus and character set.
G
grasswolfs 已提交
183 184
- Thanks [LKKlein](https://github.com/LKKlein) for contributing a new deploying package with the Golang program language.
- Thanks [Evezerest](https://github.com/Evezerest)[ninetailskim](https://github.com/ninetailskim)[edencfc](https://github.com/edencfc)[BeyondYourself](https://github.com/BeyondYourself)[1084667371](https://github.com/1084667371) for contributing a new data annotation tool, i.e., PPOCRLabel。