README.md 13 KB
Newer Older
WenmuZhou's avatar
WenmuZhou committed
1
2
3
English | [简体中文](README_ch.md)

## Introduction
LDOUBLEV's avatar
LDOUBLEV committed
4
PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools that help users train better models and apply them into practice.
WenmuZhou's avatar
WenmuZhou committed
5

grasswolfs's avatar
grasswolfs committed
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))**
grasswolfs's avatar
grasswolfs committed
9
10
- Static graph: develop branch

WenmuZhou's avatar
WenmuZhou committed
11
**Recent updates**
Leif's avatar
Leif committed
12

Daniel Yang's avatar
Daniel Yang committed
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).
MissPenguin's avatar
MissPenguin committed
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.
grasswolfs's avatar
grasswolfs committed
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.
WenmuZhou's avatar
WenmuZhou committed
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
grasswolfs's avatar
grasswolfs committed
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
grasswolfs's avatar
grasswolfs committed
25
- Rich toolkits related to the OCR areas
grasswolfs's avatar
grasswolfs committed
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
WenmuZhou's avatar
WenmuZhou committed
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

WenmuZhou's avatar
WenmuZhou committed
34
<div align="center">
LDOUBLEV's avatar
LDOUBLEV committed
35
    <img src="doc/imgs_results/ch_ppocr_mobile_v2.0/test_add_91.jpg" width="800">
tink2123's avatar
tink2123 committed
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">
WenmuZhou's avatar
WenmuZhou committed
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).
dyning's avatar
dyning committed
41

LDOUBLEV's avatar
LDOUBLEV committed
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">
Daniel Yang's avatar
Daniel Yang committed
47
<img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/dygraph/doc/joinus.PNG"  width = "200" height = "200" />
LDOUBLEV's avatar
LDOUBLEV committed
48
49
50
</div>


WenmuZhou's avatar
WenmuZhou committed
51
## Quick Experience
dyning's avatar
dyning committed
52

WenmuZhou's avatar
WenmuZhou committed
53
You can also quickly experience the ultra-lightweight OCR : [Online Experience](https://www.paddlepaddle.org.cn/hub/scene/ocr)
dyning's avatar
dyning committed
54

WenmuZhou's avatar
WenmuZhou committed
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)
tink2123's avatar
tink2123 committed
56

WenmuZhou's avatar
WenmuZhou committed
57
 Also, you can scan the QR code below to install the App (**Android support only**)
LDOUBLEV's avatar
LDOUBLEV committed
58

grasswolfs's avatar
grasswolfs committed
59
<div align="center">
WenmuZhou's avatar
WenmuZhou committed
60
<img src="./doc/ocr-android-easyedge.png"  width = "200" height = "200" />
grasswolfs's avatar
grasswolfs committed
61
</div>
dyning's avatar
dyning committed
62

WenmuZhou's avatar
WenmuZhou committed
63
64
65
66
- [**OCR Quick Start**](./doc/doc_en/quickstart_en.md)

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

LDOUBLEV's avatar
LDOUBLEV committed
67

tink2123's avatar
tink2123 committed
68
## PP-OCR 2.0 series model list(Update on Dec 15)
MissPenguin's avatar
MissPenguin committed
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.
WenmuZhou's avatar
WenmuZhou committed
70
71
72

| Model introduction                                           | Model name                   | Recommended scene | Detection model                                              | Direction classifier                                         | Recognition model                                            |
| ------------------------------------------------------------ | ---------------------------- | ----------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
grasswolfs's avatar
grasswolfs committed
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)  |  
LDOUBLEV's avatar
LDOUBLEV committed
75

WenmuZhou's avatar
WenmuZhou committed
76

LDOUBLEV's avatar
LDOUBLEV committed
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).
WenmuZhou's avatar
WenmuZhou committed
78

LDOUBLEV's avatar
LDOUBLEV committed
79
For a new language request, please refer to [Guideline for new language_requests](#language_requests).
WenmuZhou's avatar
WenmuZhou committed
80
81
82

## Tutorials
- [Quick Start](./doc/doc_en/quickstart_en.md)
Leif's avatar
Leif committed
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
- [PaddleOCR Overview and Installation](./doc/doc_en/paddleOCR_overview.md)
- PP-OCR Industry Landing: from Training to Deployment
    - [PP-OCR Model and Configuration](./doc/doc_en/models_and_config_en.md)
        - [PP-OCR Model Download](./doc/doc_en/models_list_en.md)
        - [Yml Configuration](./doc/doc_en/config_en.md)
        - [Python Inference](./doc/doc_en/inference_en.md)
    - [PP-OCR Training](./doc/doc_en/training.md)
        - [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)
    - Inference and Deployment
        - [Python Inference](./doc/doc_en/inference_en.md)
        - [C++ Inference](./deploy/cpp_infer/readme_en.md)
        - [Serving](./deploy/pdserving/README.md)
        - [Mobile](./deploy/lite/readme_en.md)
        - [Benchmark](./doc/doc_en/benchmark_en.md)  
- [PP-Structure: Information Extraction](./ppstructure/README.md)
    - [Layout Parser](./ppstructure/layout/README.md)
    - [Table Recognition](./ppstructure/table/README.md)
- Academic Circles
    - [Two-stage Algorithm](./doc/doc_en/algorithm_overview_en.md)
    - [PGNet Algorithm](./doc/doc_en/algorithm_overview_en.md)
LDOUBLEV's avatar
LDOUBLEV committed
105
- Data Annotation and Synthesis
grasswolfs's avatar
grasswolfs committed
106
    - [Semi-automatic Annotation Tool: PPOCRLabel](./PPOCRLabel/README.md)
dyning's avatar
dyning committed
107
    - [Data Synthesis Tool: Style-Text](./StyleText/README.md)
grasswolfs's avatar
grasswolfs committed
108
109
    - [Other Data Annotation Tools](./doc/doc_en/data_annotation_en.md)
    - [Other Data Synthesis Tools](./doc/doc_en/data_synthesis_en.md)
WenmuZhou's avatar
WenmuZhou committed
110
111
112
113
114
- 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)
LDOUBLEV's avatar
LDOUBLEV committed
115
- [New language requests](#language_requests)
WenmuZhou's avatar
WenmuZhou committed
116
117
118
119
120
121
122
- [FAQ](./doc/doc_en/FAQ_en.md)
- [Community](#Community)
- [References](./doc/doc_en/reference_en.md)
- [License](#LICENSE)
- [Contribution](#CONTRIBUTION)


LDOUBLEV's avatar
LDOUBLEV committed
123
124
125
126

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

## PP-OCR Pipeline
dyning's avatar
dyning committed
127
128

<div align="center">
WenmuZhou's avatar
WenmuZhou committed
129
    <img src="./doc/ppocr_framework.png" width="800">
dyning's avatar
dyning committed
130
131
</div>

dyning's avatar
dyning committed
132
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).
dyning's avatar
dyning committed
133

tink2123's avatar
tink2123 committed
134

WenmuZhou's avatar
WenmuZhou committed
135
136
## Visualization [more](./doc/doc_en/visualization_en.md)
- Chinese OCR model
dyning's avatar
dyning committed
137
<div align="center">
LDOUBLEV's avatar
LDOUBLEV committed
138
    <img src="./doc/imgs_results/ch_ppocr_mobile_v2.0/test_add_91.jpg" width="800">
LDOUBLEV's avatar
LDOUBLEV committed
139
140
    <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">
LDOUBLEV's avatar
LDOUBLEV committed
141
    <img src="./doc/imgs_results/ch_ppocr_mobile_v2.0/rotate_00052204.jpg" width="800">
dyning's avatar
dyning committed
142
</div>
tink2123's avatar
tink2123 committed
143

WenmuZhou's avatar
WenmuZhou committed
144
- English OCR model
dyning's avatar
dyning committed
145
<div align="center">
LDOUBLEV's avatar
LDOUBLEV committed
146
    <img src="./doc/imgs_results/ch_ppocr_mobile_v2.0/img_12.jpg" width="800">
dyning's avatar
dyning committed
147
</div>
148

WenmuZhou's avatar
WenmuZhou committed
149
- Multilingual OCR model
dyning's avatar
dyning committed
150
<div align="center">
LDOUBLEV's avatar
LDOUBLEV committed
151
    <img src="./doc/imgs_results/french_0.jpg" width="800">
LDOUBLEV's avatar
LDOUBLEV committed
152
    <img src="./doc/imgs_results/korean.jpg" width="800">
dyning's avatar
dyning committed
153
</div>
tink2123's avatar
tink2123 committed
154

dyning's avatar
dyning committed
155

LDOUBLEV's avatar
LDOUBLEV committed
156
157
158
159
160
<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:

grasswolfs's avatar
grasswolfs committed
161
1. In folder [ppocr/utils/dict](./ppocr/utils/dict),
LDOUBLEV's avatar
LDOUBLEV committed
162
163
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.

grasswolfs's avatar
grasswolfs committed
164
2. In folder [ppocr/utils/corpus](./ppocr/utils/corpus),
LDOUBLEV's avatar
LDOUBLEV committed
165
166
167
168
169
170
171
172
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).

MissPenguin's avatar
MissPenguin committed
173

WenmuZhou's avatar
WenmuZhou committed
174
175
176
177
178
179
180
181
182
<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.
littletomatodonkey's avatar
littletomatodonkey committed
183
- Many thanks to [zhangxin](https://github.com/ZhangXinNan) for contributing the new visualize function、add .gitignore and discard set PYTHONPATH manually.
WenmuZhou's avatar
WenmuZhou committed
184
185
186
187
188
- 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.
LDOUBLEV's avatar
LDOUBLEV committed
189
190
191
192
- 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。