README.md 13.3 KB
Newer Older
W
WenmuZhou 已提交
1 2 3
English | [简体中文](README_ch.md)

## Introduction
L
LDOUBLEV 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.
W
WenmuZhou 已提交
5

G
grasswolfs 已提交
6 7
## Notice
PaddleOCR supports both dynamic graph and static graph programming paradigm
8
- Dynamic graph: dygraph branch (default), **supported by paddle 2.0.0 ([installation](./doc/doc_en/installation_en.md))**
G
grasswolfs 已提交
9 10
- Static graph: develop branch

W
WenmuZhou 已提交
11
**Recent updates**
D
Daniel Yang 已提交
12
- 2021.4.8 release end-to-end text recognition algorithm [PGNet](https://www.aaai.org/AAAI21Papers/AAAI-2885.WangP.pdf) which is published in AAAI 2021. Find tutorial [here](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/pgnet_en.md);release multi language recognition model, support more than 80 languages recognition[here](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md); especically, the performance of [English recognition model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/models_list_en.md#English) is Optimized.
D
Daniel Yang 已提交
13
- 2021.1.21 update more than 25+ multilingual recognition models [models list](./doc/doc_en/models_list_en.md), including:English, Chinese, German, French, Japanese,Spanish,Portuguese Russia Arabic and so on.  Models for more languages will continue to be updated [Develop Plan](https://github.com/PaddlePaddle/PaddleOCR/issues/1048).
M
MissPenguin 已提交
14
- 2020.12.15 update Data synthesis tool, i.e., [Style-Text](./StyleText/README.md),easy to synthesize a large number of images which are similar to the target scene image.
G
grasswolfs 已提交
15
- 2020.11.25 Update a new data annotation tool, i.e., [PPOCRLabel](./PPOCRLabel/README.md), which is helpful to improve the labeling efficiency. Moreover, the labeling results can be used in training of the PP-OCR system directly.
W
WenmuZhou 已提交
16 17 18 19 20
- 2020.9.22 Update the PP-OCR technical article, https://arxiv.org/abs/2009.09941
- [more](./doc/doc_en/update_en.md)

## Features
- PPOCR series of high-quality pre-trained models, comparable to commercial effects
G
grasswolfs 已提交
21 22 23 24
    - 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
G
grasswolfs 已提交
25
- Rich toolkits related to the OCR areas
G
grasswolfs 已提交
26 27
    - 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
W
WenmuZhou 已提交
28 29 30 31 32
- Support user-defined training, provides rich predictive inference deployment solutions
- Support PIP installation, easy to use
- Support Linux, Windows, MacOS and other systems

## Visualization
33

W
WenmuZhou 已提交
34
<div align="center">
L
LDOUBLEV 已提交
35
    <img src="doc/imgs_results/ch_ppocr_mobile_v2.0/test_add_91.jpg" width="800">
T
tink2123 已提交
36 37
    <img src="doc/imgs_results/multi_lang/img_01.jpg" width="800">
    <img src="doc/imgs_results/multi_lang/img_02.jpg" width="800">
W
WenmuZhou 已提交
38 39 40
</div>

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).
D
dyning 已提交
41

L
LDOUBLEV 已提交
42 43 44 45 46
<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">
D
Daniel Yang 已提交
47
<img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/dygraph/doc/joinus.PNG"  width = "200" height = "200" />
L
LDOUBLEV 已提交
48 49 50
</div>


W
WenmuZhou 已提交
51
## Quick Experience
D
dyning 已提交
52

W
WenmuZhou 已提交
53
You can also quickly experience the ultra-lightweight OCR : [Online Experience](https://www.paddlepaddle.org.cn/hub/scene/ocr)
D
dyning 已提交
54

W
WenmuZhou 已提交
55
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)
T
tink2123 已提交
56

W
WenmuZhou 已提交
57
 Also, you can scan the QR code below to install the App (**Android support only**)
L
LDOUBLEV 已提交
58

G
grasswolfs 已提交
59
<div align="center">
W
WenmuZhou 已提交
60
<img src="./doc/ocr-android-easyedge.png"  width = "200" height = "200" />
G
grasswolfs 已提交
61
</div>
D
dyning 已提交
62

W
WenmuZhou 已提交
63 64 65 66
- [**OCR Quick Start**](./doc/doc_en/quickstart_en.md)

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

L
LDOUBLEV 已提交
67

T
tink2123 已提交
68
## PP-OCR 2.0 series model list(Update on Dec 15)
M
MissPenguin 已提交
69
**Note** : Compared with [models 1.1](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/models_list_en.md), which are trained with static graph programming paradigm, models 2.0 are the dynamic graph trained version and achieve close performance.
W
WenmuZhou 已提交
70 71 72

| Model introduction                                           | Model name                   | Recommended scene | Detection model                                              | Direction classifier                                         | Recognition model                                            |
| ------------------------------------------------------------ | ---------------------------- | ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
G
grasswolfs 已提交
73 74
| Chinese and English ultra-lightweight OCR model (9.4M)       | ch_ppocr_mobile_v2.0_xx      | Mobile & server   |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar)      |
| Chinese and English general OCR model (143.4M)               | ch_ppocr_server_v2.0_xx      | Server            |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_traingit.tar)    |[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar)  |  
L
LDOUBLEV 已提交
75

W
WenmuZhou 已提交
76

L
LDOUBLEV 已提交
77
For more model downloads (including multiple languages), please refer to [PP-OCR v2.0 series model downloads](./doc/doc_en/models_list_en.md).
W
WenmuZhou 已提交
78

L
LDOUBLEV 已提交
79
For a new language request, please refer to [Guideline for new language_requests](#language_requests).
W
WenmuZhou 已提交
80 81 82 83 84

## Tutorials
- [Installation](./doc/doc_en/installation_en.md)
- [Quick Start](./doc/doc_en/quickstart_en.md)
- [Code Structure](./doc/doc_en/tree_en.md)
L
LDOUBLEV 已提交
85
- Algorithm Introduction
W
WenmuZhou 已提交
86 87
    - [Text Detection Algorithm](./doc/doc_en/algorithm_overview_en.md)
    - [Text Recognition Algorithm](./doc/doc_en/algorithm_overview_en.md)
L
LDOUBLEV 已提交
88 89
    - [PP-OCR Pipeline](#PP-OCR-Pipeline)
- Model Training/Evaluation
W
WenmuZhou 已提交
90 91 92 93 94
    - [Text Detection](./doc/doc_en/detection_en.md)
    - [Text Recognition](./doc/doc_en/recognition_en.md)
    - [Direction Classification](./doc/doc_en/angle_class_en.md)
    - [Yml Configuration](./doc/doc_en/config_en.md)
- Inference and Deployment
L
LDOUBLEV 已提交
95
    - [Quick Inference Based on PIP](./doc/doc_en/whl_en.md)
W
WenmuZhou 已提交
96 97
    - [Python Inference](./doc/doc_en/inference_en.md)
    - [C++ Inference](./deploy/cpp_infer/readme_en.md)
M
MissPenguin 已提交
98
    - [Serving](./deploy/pdserving/README.md)
L
LDOUBLEV 已提交
99 100 101
    - [Mobile](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/deploy/lite/readme_en.md)
    - [Benchmark](./doc/doc_en/benchmark_en.md)  
- Data Annotation and Synthesis
G
grasswolfs 已提交
102
    - [Semi-automatic Annotation Tool: PPOCRLabel](./PPOCRLabel/README.md)
D
dyning 已提交
103
    - [Data Synthesis Tool: Style-Text](./StyleText/README.md)
G
grasswolfs 已提交
104 105
    - [Other Data Annotation Tools](./doc/doc_en/data_annotation_en.md)
    - [Other Data Synthesis Tools](./doc/doc_en/data_synthesis_en.md)
W
WenmuZhou 已提交
106 107 108 109 110
- 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)
L
LDOUBLEV 已提交
111
- [New language requests](#language_requests)
W
WenmuZhou 已提交
112 113 114 115 116 117 118
- [FAQ](./doc/doc_en/FAQ_en.md)
- [Community](#Community)
- [References](./doc/doc_en/reference_en.md)
- [License](#LICENSE)
- [Contribution](#CONTRIBUTION)


L
LDOUBLEV 已提交
119 120 121 122

<a name="PP-OCR-Pipeline"></a>

## PP-OCR Pipeline
D
dyning 已提交
123 124

<div align="center">
W
WenmuZhou 已提交
125
    <img src="./doc/ppocr_framework.png" width="800">
D
dyning 已提交
126 127
</div>

D
dyning 已提交
128
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](https://github.com/PaddlePaddle/PaddleSlim).
D
dyning 已提交
129

T
tink2123 已提交
130

W
WenmuZhou 已提交
131 132
## Visualization [more](./doc/doc_en/visualization_en.md)
- Chinese OCR model
D
dyning 已提交
133
<div align="center">
L
LDOUBLEV 已提交
134
    <img src="./doc/imgs_results/ch_ppocr_mobile_v2.0/test_add_91.jpg" width="800">
L
LDOUBLEV 已提交
135 136
    <img src="./doc/imgs_results/ch_ppocr_mobile_v2.0/00015504.jpg" width="800">
    <img src="./doc/imgs_results/ch_ppocr_mobile_v2.0/00056221.jpg" width="800">
L
LDOUBLEV 已提交
137
    <img src="./doc/imgs_results/ch_ppocr_mobile_v2.0/rotate_00052204.jpg" width="800">
D
dyning 已提交
138
</div>
T
tink2123 已提交
139

W
WenmuZhou 已提交
140
- English OCR model
D
dyning 已提交
141
<div align="center">
L
LDOUBLEV 已提交
142
    <img src="./doc/imgs_results/ch_ppocr_mobile_v2.0/img_12.jpg" width="800">
D
dyning 已提交
143
</div>
144

W
WenmuZhou 已提交
145
- Multilingual OCR model
D
dyning 已提交
146
<div align="center">
L
LDOUBLEV 已提交
147
    <img src="./doc/imgs_results/french_0.jpg" width="800">
L
LDOUBLEV 已提交
148
    <img src="./doc/imgs_results/korean.jpg" width="800">
D
dyning 已提交
149
</div>
T
tink2123 已提交
150

D
dyning 已提交
151

L
LDOUBLEV 已提交
152 153 154 155 156
<a name="language_requests"></a>
## Guideline for new language requests

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

G
grasswolfs 已提交
157
1. In folder [ppocr/utils/dict](./ppocr/utils/dict),
L
LDOUBLEV 已提交
158 159
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
160
2. In folder [ppocr/utils/corpus](./ppocr/utils/corpus),
L
LDOUBLEV 已提交
161 162 163 164 165 166 167 168
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](https://github.com/PaddlePaddle/PaddleOCR/issues/1048).

M
MissPenguin 已提交
169

W
WenmuZhou 已提交
170 171 172 173 174 175 176 177 178
<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.
L
littletomatodonkey 已提交
179
- Many thanks to [zhangxin](https://github.com/ZhangXinNan) for contributing the new visualize function、add .gitignore and discard set PYTHONPATH manually.
W
WenmuZhou 已提交
180 181 182 183 184
- 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.
L
LDOUBLEV 已提交
185 186 187 188
- 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.
- 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) and [1084667371](https://github.com/1084667371) for contributing a new data annotation tool, i.e., PPOCRLabel。