📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
Update api
SWHL7d53acda81fb
diff --git a/README.md b/README.mdindex c188ca7..67681cd 100755--- a/README.md+++ b/README.md@@ -32,9 +32,9 @@- [简介](#简介)- [文档导航](#文档导航)- [近期更新(more)](#近期更新more)+ - [🍜2023-05-22 api update:](#2023-05-22-api-update)- [❤2023-05-20 ocrweb update:](#2023-05-20-ocrweb-update)- [🌹2023-05-14 ocrweb v0.1.5 update:](#2023-05-14-ocrweb-v015-update)- - [🏸2023-04-16 ocrweb v0.1.1 update:](#2023-04-16-ocrweb-v011-update)- [生态框架](#生态框架)- [在线demo](#在线demo)- [TODO以及任务认领](#todo以及任务认领)@@ -83,6 +83,7 @@- [网页版OCR](https://github.com/RapidAI/RapidOCR/blob/main/ocrweb/README.md)- [Nuitka打包rapdocr_web](https://github.com/RapidAI/RapidOCR/wiki/Nuitka%E6%89%93%E5%8C%85rapidocr_web%E6%93%8D%E4%BD%9C%E6%96%87%E6%A1%A3)- [多语言网页版OCR](https://github.com/RapidAI/RapidOCR/blob/main/ocrweb_multi/README.md)+- [API版](https://github.com/RapidAI/RapidOCR/tree/main/api)- [版面结构化-RapidStructure](https://github.com/RapidAI/RapidStructure)- [含文本的图像方向分类](https://github.com/RapidAI/RapidStructure/blob/main/docs/README_Orientation.md)- [版面分析](https://github.com/RapidAI/RapidStructure/blob/main/docs/README_Layout.md)@@ -100,6 +101,9 @@## 近期更新([more](https://github.com/RapidAI/RapidOCR/wiki/%E6%9B%B4%E6%96%B0%E6%97%A5%E5%BF%97))+#### 🍜2023-05-22 api update:+- 将API从ocrweb中解耦出来,作为单独模块维护,详情参见[API](https://github.com/RapidAI/RapidOCR/tree/main/api)+- `rapidocr_web>0.1.6`之后,将不支持`pip install rapidocr_web[api]`方式安装,可直接`pip install rapidocr_api`安装使用。#### ❤2023-05-20 ocrweb update:- 增加桌面版RapidOCRWeb,详情可参见[RapidOCRWeb桌面版使用教程](https://github.com/RapidAI/RapidOCR/wiki/%5BRapidOCRWeb%5D-%E6%A1%8C%E9%9D%A2%E7%89%88%E4%BD%BF%E7%94%A8%E6%95%99%E7%A8%8B)- 对仓库文档做了整理,大部分文档放到了[Wiki](https://github.com/RapidAI/RapidOCR/wiki)@@ -107,10 +111,6 @@- 增加界面版返回坐标框的返回值([issue #85](https://github.com/RapidAI/RapidOCR/issues/85))- API模式增加base64格式传入- 详情参见:[link](https://github.com/RapidAI/RapidOCR/blob/main/ocrweb/README.md)-#### 🏸2023-04-16 ocrweb v0.1.1 update:-- API部署改为FastAPI库支持-- 将API模式与Web解耦合,可通过`pip install rapidocr_web[api]`来选择性安装-- 详情参见:[link](https://github.com/RapidAI/RapidOCR/blob/main/ocrweb/README.md)## 生态框架```mermaiddiff --git a/api/README.md b/api/README.mdindex 86adfa7..3157bf1 100644--- a/api/README.md+++ b/api/README.md@@ -7,12 +7,19 @@<a href="https://pepy.tech/project/rapidocr_api"><img src="https://static.pepy.tech/personalized-badge/rapidocr_api?period=total&units=abbreviation&left_color=grey&right_color=blue&left_text=Downloads"></a></p>+- ⚠️ 由于[pypi网站处于维护之中](https://status.python.org/),暂时不能上传whl包,后续如恢复,会再次上传。- 采用FastAPI+uvicorn实现。+- 该模块定位是一个快速搭建示例的demo,没有考虑多进程处理并发请求,如果有这需求的小伙伴,可以看看gunicorn等。### 使用步骤1. 安装`rapidocr_api````bash$ pip install rapidocr_api++ # 源码安装+ $ python setup.py bdist_wheel v0.0.1+ $ cd dist+ $ pip install rapidocr_*.whl```2. 运行- 用法:@@ -29,36 +36,42 @@```bash$ rapidocr_api -ip 0.0.0.0 -p 9003```-3. 使用(本质就是发送一个POST请求,其他语言同理)- - 以文件的方式发送请求- ```python- import requests+3. 使用+ - ⚠️:本质就是发送一个POST请求,其他语言同理+ - curl调用+ ```bash+ $ curl -F [email protected] http://0.0.0.0:9003/ocr+ ```+ - python调用+ - 以文件的方式发送请求+ ```python+ import requests- url = 'http://localhost:9003/ocr'- img_path = '../python/tests/test_files/ch_en_num.jpg'+ url = 'http://localhost:9003/ocr'+ img_path = '../python/tests/test_files/ch_en_num.jpg'- with open(img_path, 'rb') as f:- file_dict = {'image_file': (img_path, f, 'image/png')}- response = requests.post(url, files=file_dict, timeout=60)+ with open(img_path, 'rb') as f:+ file_dict = {'image_file': (img_path, f, 'image/png')}+ response = requests.post(url, files=file_dict, timeout=60)- print(response.json())- ```- - 以`base64`方式发送post请求- ```python- import base64- import requests+ print(response.json())+ ```+ - 以`base64`方式发送post请求+ ```python+ import base64+ import requests- url = 'http://localhost:9003/ocr'- img_path = '../python/tests/test_files/ch_en_num.jpg'+ url = 'http://localhost:9003/ocr'+ img_path = '../python/tests/test_files/ch_en_num.jpg'- with open(img_path, 'rb') as fa:- img_str = base64.b64encode(fa.read())+ with open(img_path, 'rb') as fa:+ img_str = base64.b64encode(fa.read())- payload = {'image_data': img_str}- resp = requests.post(url, data=payload)+ payload = {'image_data': img_str}+ resp = requests.post(url, data=payload)- print(resp.json())- ```+ print(resp.json())+ ```4. API输出- 示例结果:<details>@@ -67,71 +80,51 @@```json{"0": {- "rec_txt": "香港深圳抽血,",+ "rec_txt": "8月26日!","dt_boxes": [- [265, 18],- [472, 231],- [431, 271],- [223, 59]+ [333.0, 72.0],+ [545.0, 40.0],+ [552.0, 90.0],+ [341.0, 122.0]],- "score": "0.8175641223788261"+ "score": "0.7342076812471662"},"1": {- "rec_txt": "专业查性别",+ "rec_txt": "澳洲名校招生信息","dt_boxes": [- [388, 15],- [636, 257],- [587, 307],- [339, 65]+ [266.0, 163.0],+ [612.0, 116.0],+ [619.0, 163.0],+ [272.0, 210.0]],- "score": "0.8293875356515249"+ "score": "0.8261737492349412"},"2": {- "rec_txt": "专业鉴定B超单",+ "rec_txt": "解读!!","dt_boxes": [- [215, 84],- [509, 413],- [453, 463],- [159, 134]+ [341.0, 187.0],+ [595.0, 179.0],+ [598.0, 288.0],+ [344.0, 296.0]],- "score": "0.8626169338822365"+ "score": "0.6152311325073242"},"3": {- "rec_txt": "b超仪器查性别",- "dt_boxes": [- [128, 135],- [430, 478],- [366, 534],- [64, 192]- ],- "score": "0.8449362441897392"- },- "4": {- "rec_txt": "加微信eee",- "dt_boxes": [- [58, 189],- [268, 450],- [209, 498],- [0, 236]- ],- "score": "0.8176911813872201"- },- "5": {- "rec_txt": "可邮寄",+ "rec_txt": "Rules...","dt_boxes": [- [493, 261],- [617, 384],- [577, 423],- [454, 300]+ [446.0, 321.0],+ [560.0, 326.0],+ [559.0, 352.0],+ [445.0, 347.0]],- "score": "0.7494261413812637"+ "score": "0.8704230123096042"}}```</details>- 输出结果说明:- - 如果图像中存在文字,则会输出json格式,具体格式介绍如下:+ - 如果图像中存在文字,则会输出字典格式,具体介绍如下:```python{"0": {diff --git a/api/demo.py b/api/demo.pyindex d65442d..0dddf98 100644--- a/api/demo.py+++ b/api/demo.py@@ -11,4 +11,4 @@ with open(img_path, 'rb') as f:file_dict = {'image_file': (img_path, f, 'image/png')}response = requests.post(url, files=file_dict, timeout=60)-print(response.json())+print(response.text)diff --git a/api/rapidocr_api/api.py b/api/rapidocr_api/api.pyindex c2d7fa4..c599092 100644--- a/api/rapidocr_api/api.py+++ b/api/rapidocr_api/api.py@@ -35,7 +35,7 @@ class OCRAPIUtils():'dt_boxes': dt_box,'score': score}for i, (dt_box, rec, score) in enumerate(ocr_res)}- return json.dumps(out_dict, indent=2, ensure_ascii=False)+ return out_dictapp = FastAPI()diff --git a/docs/README_en.md b/docs/README_en.mdindex 3324992..1f5c346 100644--- a/docs/README_en.md+++ b/docs/README_en.md@@ -28,10 +28,9 @@- [Introduction](#introduction)- [Navigation](#navigation)- [Recently updates(more)](#recently-updatesmore)+ - [🍜2023-05-22 api update:](#2023-05-22-api-update)- [❤2023-05-20 ocrweb update:](#2023-05-20-ocrweb-update)- [🌹 2023-05-14 ocrweb v0.1.5 update:](#-2023-05-14-ocrweb-v015-update)- - [🏸2023-04-16 ocrweb v0.1.1 update:](#2023-04-16-ocrweb-v011-update)- - [🎮2023-03-11 v1.2.2 update:](#2023-03-11-v122-update)- [Overall Framework](#overall-framework)- [Demo](#demo)- [TODO and Task Claim](#todo-and-task-claim)@@ -71,6 +70,7 @@- [RapidOcrNcnnJvm](https://github.com/RapidAI/RapidOcrNcnnJvm)- [.Net demo(C#)](https://github.com/RapidAI/RapidOCRCSharp)- [Android demo](https://github.com/RapidAI/RapidOcrAndroidOnnx)+- [API](https://github.com/RapidAI/RapidOCR/tree/main/api)- Web demo:- [Web OCR](https://github.com/RapidAI/RapidOCR/blob/main/ocrweb/README.md)- [Nuitka package rapdocr_web](https://github.com/RapidAI/RapidOCR/wiki/Nuitka%E6%89%93%E5%8C%85rapidocr_web%E6%93%8D%E4%BD%9C%E6%96%87%E6%A1%A3)@@ -97,18 +97,15 @@- [FAQ](https://github.com/RapidAI/RapidOCR/blob/main/docs/FAQ.md)## Recently updates([more](https://github.com/RapidAI/RapidOCR/wiki/Changelog))+#### 🍜2023-05-22 api update:+- Decouple the API from ocrweb and maintain it as a separate module. For details, see [API](https://github.com/RapidAI/RapidOCR/tree/main/api)+- After `rapidocr_web>0.1.6`, `pip install rapidocr_web[api]` will not be supported for installation, you can directly install and use `pip install rapidocr_api`.#### ❤2023-05-20 ocrweb update:- Add desktop version of RapidOCRWeb, for details, please refer to [RapidOCRWeb desktop version tutorial](https://github.com/RapidAI/RapidOCR/wiki/%5BRapidOCRWeb%5D-%E6%A1%8C%E9%9D%A2%E7%89%88%E4%BD%BF%E7%94%A8%E6%95%99%E7%A8%8B)#### 🌹 2023-05-14 ocrweb v0.1.5 update:- Add the return value of the interface version's return coordinate box ([issue #85](https://github.com/RapidAI/RapidOCR/issues/85))- API mode adds base64 format input- For details, please refer to: [link](https://github.com/RapidAI/RapidOCR/blob/main/ocrweb/README.md)-#### 🏸2023-04-16 ocrweb v0.1.1 update:-- API deployment changed to FastAPI library support.-- Decouple the API mode from the Web, which can be installed selectively through `pip install rapidocr_web[api]`.-- See details for [link](https://github.com/RapidAI/RapidOCR/blob/main/ocrweb/README.md).-#### 🎮2023-03-11 v1.2.2 update:-- Fix the incoming parameter error of RapidOCR class in instantiation python## Overall Framework```mermaiddiff --git a/docs/doc_whl_rapidocr_api.md b/docs/doc_whl_rapidocr_api.mdindex 08966db..9655c14 100644--- a/docs/doc_whl_rapidocr_api.md+++ b/docs/doc_whl_rapidocr_api.md@@ -27,35 +27,40 @@$ rapidocr_api -ip 0.0.0.0 -p 9003```3. Use- - Send image data by file format.- ```python- import requests+ - with curl+ ```bash+ $ curl -F [email protected] http://0.0.0.0:9003/ocr+ ```+ - with python+ - Send image data by file format.+ ```python+ import requests- url = 'http://localhost:9003/ocr'- img_path = '../python/tests/test_files/ch_en_num.jpg'+ url = 'http://localhost:9003/ocr'+ img_path = '../python/tests/test_files/ch_en_num.jpg'- with open(img_path, 'rb') as f:- file_dict = {'image_file': (img_path, f, 'image/png')}- response = requests.post(url, files=file_dict, timeout=60)+ with open(img_path, 'rb') as f:+ file_dict = {'image_file': (img_path, f, 'image/png')}+ response = requests.post(url, files=file_dict, timeout=60)- print(response.json())- ```- - Send image data by base64 format.- ```python- import base64- import requests+ print(response.json())+ ```+ - Send image data by base64 format.+ ```python+ import base64+ import requests- url = 'http://localhost:9003/ocr'- img_path = '../python/tests/test_files/ch_en_num.jpg'+ url = 'http://localhost:9003/ocr'+ img_path = '../python/tests/test_files/ch_en_num.jpg'- with open(img_path, 'rb') as fa:- img_str = base64.b64encode(fa.read())+ with open(img_path, 'rb') as fa:+ img_str = base64.b64encode(fa.read())- payload = {'image_data': img_str}- resp = requests.post(url, data=payload)+ payload = {'image_data': img_str}+ resp = requests.post(url, data=payload)- print(resp.json())- ```+ print(resp.json())+ ```4. Output<details><summary>Click to expand</summary>diff --git a/ocrweb/README.md b/ocrweb/README.mdindex e810662..c90712c 100755--- a/ocrweb/README.md+++ b/ocrweb/README.md@@ -15,7 +15,6 @@### 简要说明-- 该模块定位是一个快速搭建示例的demo,没有考虑多进程处理并发请求,如果有这需求的小伙伴,可以看看gunicorn等。- 该模块依赖`rapidocr_onnxruntime`库。- 如果想要离线部署,可以先手动下载[`rapidocr_onnxruntime`](https://pypi.org/project/rapidocr-onnxruntime/#files) whl包,再手动安装[`rapidocr_web`](https://pypi.org/project/rapidocr-web/#files) whl包来使用。- 所用模型组合(最优组合)为: