github/ocr_api_server
5
0
Fork 0
mirror of https://github.com/sml2h3/ocr_api_server.git synced 2025-05-02 20:00:03 +08:00
Code Issues Projects Releases Wiki Activity

整体项目重构

Browse Source
This commit is contained in:
sml2h3 2024-07-25 10:25:15 +08:00
parent 7f37543ffb
commit de0afe7a4c
18 changed files with 482 additions and 511 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
Dockerfile
View File

@ -1,17 +1,17 @@
FROM python:3.8-slim-buster
RUN mkdir /app
COPY ./*.txt ./*.py ./*.sh ./*.onnx /app/
RUN cd /app \
&& python3 -m pip install --upgrade pip -i https://pypi.douban.com/simple/\
&& pip3 install --no-cache-dir -r requirements.txt --extra-index-url https://pypi.douban.com/simple/ \
&& rm -rf /tmp/* && rm -rf /root/.cache/* \
&& sed -i 's#http://deb.debian.org#http://mirrors.aliyun.com/#g' /etc/apt/sources.list\
&& apt-get --allow-releaseinfo-change update && apt install libgl1-mesa-glx libglib2.0-0 -y
# 使用官方 Python 运行时作为父镜像
FROM python:3.9-slim
# 设置工作目录
WORKDIR /app
CMD ["python3", "ocr_server.py", "--port", "9898", "--ocr", "--det"]
# 将当前目录内容复制到容器的 /app 中
COPY . /app
# 安装项目依赖
RUN pip install --no-cache-dir -r requirements.txt
# 暴露端口 8000
EXPOSE 8000
# 运行应用
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

201
LICENSE
View File

@ -1,201 +0,0 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

368
README.md
View File

@ -1,85 +1,339 @@
# ocr_api_server
使用ddddocr的最简api搭建项目，支持docker
# 🚀 DdddOcr API
**建议python版本3.7-3.9 64位**
![DdddOcr Logo](https://cdn.wenanzhe.com/img/logo.png!/crop/700x500a400a500)
再有不好好看文档的我就不管了啊！！！
> 基于 FastAPI 和 DdddOcr 的高性能 OCR API 服务，提供图像文字识别、滑动验证码匹配和目标检测功能。
>
> [自营各类GPT聚合平台](https://juxiangyun.com)
# 运行方式
## 📋 目录
## 最简单运行方式
- [系统要求](#-系统要求)
- [安装和启动](#-安装和启动)
- [API 端点](#-api-端点)
- [API 调用示例](#-api-调用示例)
- [注意事项](#-注意事项)
- [故障排除](#-故障排除)
- [许可证](#-许可证)
```shell
# 安装依赖
pip install -r requirements.txt -i https://pypi.douban.com/simple
## 💻 系统要求
# 运行 可选参数如下
# --port 9898 指定端口,默认为9898
# --ocr 开启ocr模块 默认开启
# --old 只有ocr模块开启的情况下生效 默认不开启
# --det 开启目标检测模式
| 组件 | 版本 |
|------|------|
| 操作系统 | Linux（推荐 Ubuntu 20.04 LTS 或更高版本）|
| Docker | 20.10 或更高 |
| Docker Compose | 1.29 或更高 |
# 最简单运行方式，只开启ocr模块并以新模型计算
python ocr_server.py --port 9898 --ocr
## 🚀 安装和启动
# 开启ocr模块并使用旧模型计算
python ocr_server.py --port 9898 --ocr --old
1. **克隆仓库**
```bash
git clone https://github.com/your-repo/ddddocr-api.git
cd ddddocr-api
```
# 只开启目标检测模块
python ocr_server.py --port 9898 --det
2. **构建 Docker 镜像 [一键docker环境服务器购买，可一元试用](https://app.rainyun.com/apps/rcs/buy) **
```bash
docker build -t ddddocr-api .
```
# 同时开启ocr模块以及目标检测模块
python ocr_server.py --port 9898 --ocr --det
3. **启动服务**
```bash
docker run -d -p 8000:8000 --name ddddocr-api-container ddddocr-api
```
# 同时开启ocr模块并使用旧模型计算以及目标检测模块
python ocr_server.py --port 9898 --ocr --old --det
4. **验证服务**
```bash
curl http://localhost:8000/docs
```
> 如果成功，您将看到 Swagger UI 文档页面。
```
5. **停止服务**
## docker运行方式(目测只能在Linux下部署)
- 如果使用 Docker：
```bash
docker stop ddddocr-api-container
```
```shell
git clone https://github.com/sml2h3/ocr_api_server.git
# docker怎么安装？百度吧
- 如果使用 Docker Compose：
```bash
docker-compose down
```
cd ocr_api_server
6. **查看日志**
# 修改entrypoint.sh中的参数，具体参数往上翻，默认9898端口，同时开启ocr模块以及目标检测模块
- 如果使用 Docker：
```bash
docker logs ddddocr-api-container
```
# 编译镜像
docker build -t ocr_server:v1 .
- 如果使用 Docker Compose：
```bash
docker-compose logs
```
# 运行镜像
docker run -p 9898:9898 -d ocr_server:v1
## 🔌 API 端点
```
### 1. OCR 识别
# 接口
🔗 **端点**：`POST /ocr`
**具体请看test_api.py文件**
| 参数 | 类型 | 描述 |
|------|------|------|
| `file` | File | 图片文件（可选） |
| `image` | String | Base64 编码的图片字符串（可选） |
| `probability` | Boolean | 是否返回概率（默认：false） |
| `charsets` | String | 字符集（可选） |
| `png_fix` | Boolean | 是否进行 PNG 修复（默认：false） |
### 2. 滑动验证码匹配
🔗 **端点**：`POST /slide_match`
| 参数 | 类型 | 描述 |
|------|------|------|
| `target_file` | File | 目标图片文件（可选） |
| `background_file` | File | 背景图片文件（可选） |
| `target` | String | Base64 编码的目标图片字符串（可选） |
| `background` | String | Base64 编码的背景图片字符串（可选） |
| `simple_target` | Boolean | 是否使用简单目标（默认：false） |
### 3. 目标检测
🔗 **端点**：`POST /detection`
| 参数 | 类型 | 描述 |
|------|------|------|
| `file` | File | 图片文件（可选） |
| `image` | String | Base64 编码的图片字符串（可选） |
## 📘 API 调用示例
<details>
<summary>Python</summary>
```python
# 1、测试是否启动成功，可以通过直接GET访问http://{host}:{port}/ping来测试，如果返回pong则启动成功
import requests
import base64
# 2、OCR/目标检测请求接口格式：
url = "http://localhost:8000/ocr"
image_path = "path/to/your/image.jpg"
# http://{host}:{port}/{opt}/{img_type}/{ret_type}
# opt：操作类型 ocr=OCR det=目标检测 slide=滑块（match和compare两种算法，默认为compare)
# img_type: 数据类型 file=文件上传方式 b64=base64(imgbyte)方式 默认为file方式
# ret_type: 返回类型 json=返回json（识别出错会在msg里返回错误信息） text=返回文本格式（识别出错时回直接返回空文本）
with open(image_path, "rb") as image_file:
encoded_string = base64.b64encode(image_file.read()).decode('utf-8')
# 例子：
data = {
"image": encoded_string,
"probability": False,
"png_fix": False
}
# OCR请求
# resp = requests.post("http://{host}:{port}/ocr/file", files={'image': image_bytes})
# resp = requests.post("http://{host}:{port}/ocr/b64/text", data=base64.b64encode(file).decode())
# 目标检测请求
# resp = requests.post("http://{host}:{port}/det/file", files={'image': image_bytes})
# resp = requests.post("http://{host}:{port}/det/b64/json", data=base64.b64encode(file).decode())
# 滑块识别请求
# resp = requests.post("http://{host}:{port}/slide/match/file", files={'target_img': target_bytes, 'bg_img': bg_bytes})
# jsonstr = json.dumps({'target_img': target_b64str, 'bg_img': bg_b64str})
# resp = requests.post("http://{host}:{port}/slide/compare/b64", files=base64.b64encode(jsonstr.encode()).decode())
response = requests.post(url, data=data)
print(response.json())
```
</details>
<details>
<summary>Node.js</summary>
```javascript
const axios = require('axios');
const fs = require('fs');
const url = 'http://localhost:8000/ocr';
const imagePath = 'path/to/your/image.jpg';
const imageBuffer = fs.readFileSync(imagePath);
const base64Image = imageBuffer.toString('base64');
const data = {
image: base64Image,
probability: false,
png_fix: false
};
axios.post(url, data)
.then(response => {
console.log(response.data);
})
.catch(error => {
console.error('Error:', error);
});
```
</details>
<details>
<summary>C#</summary>
```csharp
using System;
using System.Net.Http;
using System.IO;
using System.Threading.Tasks;
class Program
{
static async Task Main(string[] args)
{
var url = "http://localhost:8000/ocr";
var imagePath = "path/to/your/image.jpg";
var imageBytes = File.ReadAllBytes(imagePath);
var base64Image = Convert.ToBase64String(imageBytes);
var client = new HttpClient();
var content = new MultipartFormDataContent();
content.Add(new StringContent(base64Image), "image");
content.Add(new StringContent("false"), "probability");
content.Add(new StringContent("false"), "png_fix");
var response = await client.PostAsync(url, content);
var result = await response.Content.ReadAsStringAsync();
Console.WriteLine(result);
}
}
```
</details>
<details>
<summary>PHP</summary>
```php
<?php
$url = 'http://localhost:8000/ocr';
$imagePath = 'path/to/your/image.jpg';
$imageData = base64_encode(file_get_contents($imagePath));
$data = array(
'image' => $imageData,
'probability' => 'false',
'png_fix' => 'false'
);
$options = array(
'http' => array(
'header' => "Content-type: application/x-www-form-urlencoded\r\n",
'method' => 'POST',
'content' => http_build_query($data)
)
);
$context = stream_context_create($options);
$result = file_get_contents($url, false, $context);
echo $result;
?>
```
</details>
<details>
<summary>Go</summary>
```go
package main
import (
"bytes"
"encoding/base64"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
"net/url"
)
func main() {
apiURL := "http://localhost:8000/ocr"
imagePath := "path/to/your/image.jpg"
imageData, err := ioutil.ReadFile(imagePath)
if err != nil {
panic(err)
}
base64Image := base64.StdEncoding.EncodeToString(imageData)
data := url.Values{}
data.Set("image", base64Image)
data.Set("probability", "false")
data.Set("png_fix", "false")
resp, err := http.PostForm(apiURL, data)
if err != nil {
panic(err)
}
defer resp.Body.Close()
body, err := ioutil.ReadAll(resp.Body)
if err != nil {
panic(err)
}
fmt.Println(string(body))
}
```
</details>
<details>
<summary>易语言</summary>
```易语言
.版本 2
.程序集 调用OCR接口
.子程序 主函数, 整数型
.局部变量 请求头, QQ.HttpHeaders
.局部变量 请求内容, QQ.HttpMultiData
.局部变量 图片路径, 文本型
.局部变量 图片数据, 字节集
.局部变量 HTTP, QQ.Http
图片路径 ＝ "path/to/your/image.jpg"
图片数据 ＝ 读入文件 (图片路径)
请求头.添加 ("Content-Type", "application/x-www-form-urlencoded")
请求内容.添加文本 ("image", 到Base64 (图片数据))
请求内容.添加文本 ("probability", "false")
请求内容.添加文本 ("png_fix", "false")
HTTP.发送POST请求 ("http://localhost:8000/ocr", 请求内容, 请求头)
调试输出 (HTTP.获取返回文本())
返回 (0)
```
</details>
> **注意**：使用示例前，请确保安装了必要的依赖库，并根据实际环境修改服务器地址和图片路径。
## ⚠️ 注意事项
- 确保防火墙允许访问 8000 端口。
- 生产环境建议配置 HTTPS 和适当的身份验证机制。
- 定期更新 Docker 镜像以获取最新的安全补丁和功能更新。
## 🔧 故障排除
遇到问题？请检查以下几点：
1. 确保 Docker 服务正在运行。
2. 检查容器日志：
```bash
docker logs ddddocr-api-container
```
3. 确保没有其他服务占用 8000 端口。
> 如果问题仍然存在，请提交 issue 到本项目的 GitHub 仓库。
## 📄 许可证
本项目采用 MIT 许可证。详情请参见 [LICENSE](LICENSE) 文件。
---
<p align="center">
Made with ❤️ by sml2h3
</p>

0
app/__init__.py Normal file
View File

77
app/main.py Normal file
View File

@ -0,0 +1,77 @@
from fastapi import FastAPI, File, UploadFile, HTTPException, Form
from fastapi.responses import JSONResponse
from typing import Optional, Union
import base64
from .models import OCRRequest, SlideMatchRequest, DetectionRequest, APIResponse
from .services import ocr_service
app = FastAPI()
def decode_image(image: Union[UploadFile, str, None]) -> bytes:
if isinstance(image, UploadFile):
return image.file.read()
elif isinstance(image, str):
try:
return base64.b64decode(image)
except:
raise HTTPException(status_code=400, detail="Invalid base64 string")
elif image is None:
raise HTTPException(status_code=400, detail="No image provided")
else:
raise HTTPException(status_code=400, detail="Invalid image input")
@app.post("/ocr", response_model=APIResponse)
async def ocr_endpoint(
file: Optional[UploadFile] = File(None),
image: Optional[str] = Form(None),
probability: bool = Form(False),
charsets: Optional[str] = Form(None),
png_fix: bool = Form(False)
):
try:
if file is None and image is None:
return APIResponse(code=400, message="Either file or image must be provided")
image_bytes = decode_image(file or image)
result = ocr_service.ocr_classification(image_bytes, probability, charsets, png_fix)
return APIResponse(code=200, message="Success", data=result)
except Exception as e:
return APIResponse(code=500, message=str(e))
@app.post("/slide_match", response_model=APIResponse)
async def slide_match_endpoint(
target_file: Optional[UploadFile] = File(None),
background_file: Optional[UploadFile] = File(None),
target: Optional[str] = Form(None),
background: Optional[str] = Form(None),
simple_target: bool = Form(False)
):
try:
if (target_file is None and target is None) or (background_file is None and background is None):
return APIResponse(code=400, message="Both target and background must be provided")
target_bytes = decode_image(target_file or target)
background_bytes = decode_image(background_file or background)
result = ocr_service.slide_match(target_bytes, background_bytes, simple_target)
return APIResponse(code=200, message="Success", data=result)
except Exception as e:
return APIResponse(code=500, message=str(e))
@app.post("/detection", response_model=APIResponse)
async def detection_endpoint(
file: Optional[UploadFile] = File(None),
image: Optional[str] = Form(None)
):
try:
if file is None and image is None:
return APIResponse(code=400, message="Either file or image must be provided")
image_bytes = decode_image(file or image)
bboxes = ocr_service.detection(image_bytes)
return APIResponse(code=200, message="Success", data=bboxes)
except Exception as e:
return APIResponse(code=500, message=str(e))

40
app/models.py Normal file
View File

@ -0,0 +1,40 @@
from pydantic import BaseModel
from typing import Optional, List, Union, Any
class ImageInput(BaseModel):
image: Optional[str] = None # For base64 string
class OCRRequest(ImageInput):
probability: bool = False
charsets: Optional[str] = None
png_fix: bool = False
class OCRResponse(BaseModel):
result: Union[str, dict]
class SlideMatchRequest(BaseModel):
target: Optional[str] = None # For base64 string
background: Optional[str] = None # For base64 string
simple_target: bool = False
class SlideMatchResponse(BaseModel):
result: List[int]
class DetectionRequest(ImageInput):
pass
class DetectionResponse(BaseModel):
bboxes: List[List[int]]
class APIResponse(BaseModel):
code: int
message: str
data: Optional[Any] = None

24
app/services.py Normal file
View File

@ -0,0 +1,24 @@
import ddddocr
from typing import Union, List, Optional
class OCRService:
def __init__(self):
self.ocr = ddddocr.DdddOcr()
self.det = ddddocr.DdddOcr(det=True)
self.slide = ddddocr.DdddOcr(det=False, ocr=False)
def ocr_classification(self, image: bytes, probability: bool = False, charsets: Optional[str] = None, png_fix: bool = False) -> Union[str, dict]:
if charsets:
self.ocr.set_ranges(charsets)
result = self.ocr.classification(image, probability=probability, png_fix=png_fix)
return result
def slide_match(self, target: bytes, background: bytes, simple_target: bool = False) -> List[int]:
result = self.slide.slide_match(target, background, simple_target=simple_target)
return result
def detection(self, image: bytes) -> List[List[int]]:
bboxes = self.det.detection(image)
return bboxes
ocr_service = OCRService()

BIN
compare_bg.jpg
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 8.3 KiB

BIN
compare_target.jpg
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 8.0 KiB

12
docker-compose.yml Normal file
View File

@ -0,0 +1,12 @@
version: '3.8'
services:
ddddocr-api:
build: .
ports:
- "8000:8000"
volumes:
- .:/app
environment:
- DEBUG=1
restart: always

BIN
match_bg.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 94 KiB

BIN
match_target.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 4.1 KiB

126
ocr_server.py
View File

@ -1,126 +0,0 @@
# encoding=utf-8
import argparse
import base64
import json
import ddddocr
from flask import Flask, request
parser = argparse.ArgumentParser(description="使用ddddocr搭建的最简api服务")
parser.add_argument("-p", "--port", type=int, default=9898)
parser.add_argument("--ocr", action="store_true", help="开启ocr识别")
parser.add_argument("--old", action="store_true", help="OCR是否启动旧模型")
parser.add_argument("--det", action="store_true", help="开启目标检测")
args = parser.parse_args()
app = Flask(__name__)
class Server(object):
def __init__(self, ocr=True, det=False, old=False):
self.ocr_option = ocr
self.det_option = det
self.old_option = old
self.ocr = None
self.det = None
if self.ocr_option:
print("ocr模块开启")
if self.old_option:
print("使用OCR旧模型启动")
self.ocr = ddddocr.DdddOcr(old=True)
else:
print("使用OCR新模型启动，如需要使用旧模型，请额外添加参数 --old开启")
self.ocr = ddddocr.DdddOcr()
else:
print("ocr模块未开启，如需要使用，请使用参数 --ocr开启")
if self.det_option:
print("目标检测模块开启")
self.det = ddddocr.DdddOcr(det=True)
else:
print("目标检测模块未开启，如需要使用，请使用参数 --det开启")
def classification(self, img: bytes):
if self.ocr_option:
return self.ocr.classification(img)
else:
raise Exception("ocr模块未开启")
def detection(self, img: bytes):
if self.det_option:
return self.det.detection(img)
else:
raise Exception("目标检测模块模块未开启")
def slide(self, target_img: bytes, bg_img: bytes, algo_type: str):
dddd = self.ocr or self.det or ddddocr.DdddOcr(ocr=False)
if algo_type == 'match':
return dddd.slide_match(target_img, bg_img)
elif algo_type == 'compare':
return dddd.slide_comparison(target_img, bg_img)
else:
raise Exception(f"不支持的滑块算法类型: {algo_type}")
server = Server(ocr=args.ocr, det=args.det, old=args.old)
def get_img(request, img_type='file', img_name='image'):
if img_type == 'b64':
img = base64.b64decode(request.get_data()) #
try: # json str of multiple images
dic = json.loads(img)
img = base64.b64decode(dic.get(img_name).encode())
except Exception as e: # just base64 of single image
pass
else:
img = request.files.get(img_name).read()
return img
def set_ret(result, ret_type='text'):
if ret_type == 'json':
if isinstance(result, Exception):
return json.dumps({"status": 200, "result": "", "msg": str(result)})
else:
return json.dumps({"status": 200, "result": result, "msg": ""})
# return json.dumps({"succ": isinstance(result, str), "result": str(result)})
else:
if isinstance(result, Exception):
return ''
else:
return str(result).strip()
@app.route('/<opt>/<img_type>', methods=['POST'])
@app.route('/<opt>/<img_type>/<ret_type>', methods=['POST'])
def ocr(opt, img_type='file', ret_type='text'):
try:
img = get_img(request, img_type)
if opt == 'ocr':
result = server.classification(img)
elif opt == 'det':
result = server.detection(img)
else:
raise f"<opt={opt}> is invalid"
return set_ret(result, ret_type)
except Exception as e:
return set_ret(e, ret_type)
@app.route('/slide/<algo_type>/<img_type>', methods=['POST'])
@app.route('/slide/<algo_type>/<img_type>/<ret_type>', methods=['POST'])
def slide(algo_type='compare', img_type='file', ret_type='text'):
try:
target_img = get_img(request, img_type, 'target_img')
bg_img = get_img(request, img_type, 'bg_img')
result = server.slide(target_img, bg_img, algo_type)
return set_ret(result, ret_type)
except Exception as e:
return set_ret(e, ret_type)
@app.route('/ping', methods=['GET'])
def ping():
return "pong"
if __name__ == '__main__':
app.run(host="0.0.0.0", port=args.port)

6
requirements.txt
View File

@ -1,2 +1,4 @@
ddddocr>=1.3.1
flask
fastapi==0.68.0
uvicorn==0.15.0
ddddocr==1.5.5
python-multipart==0.0.5

BIN
test.jpg
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 2.7 KiB

111
test_api.py
View File

@ -1,111 +0,0 @@
#!/usr/bin/python3.6
# -*- coding: utf-8 -*-
#
# Copyright (C) 2021 #
# @Time : 2022/1/6 23:28
# @Author : sml2h3
# @Email : sml2h3@gmail.com
# @File : test_api.py
# @Software: PyCharm
import base64
import json
import requests
print(' ')
# ******************OCR识别部分开始******************
host = "http://127.0.0.1:9898"
# 目标检测就把ocr改成det,其他相同
# 方式一
file = open(r'test.jpg', 'rb').read()
# file = open(r'test_calc.png', 'rb').read()
api_url = f"{host}/ocr/file"
resp = requests.post(api_url, files={'image': file})
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/ocr/file/json"
resp = requests.post(api_url, files={'image': file})
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/ocr/b64"
resp = requests.post(api_url, data=base64.b64encode(file).decode())
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/ocr/b64/json"
resp = requests.post(api_url, data=base64.b64encode(file).decode())
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/det/file"
resp = requests.post(api_url, files={'image': file})
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/det/file/json"
resp = requests.post(api_url, files={'image': file})
print(f"{api_url=}, {resp.text=}")
# 滑块识别
target_file = open(r'match_target.png', 'rb').read()
bg_file = open(r'match_bg.png', 'rb').read()
api_url = f"{host}/slide/match/file"
resp = requests.post(api_url, files={'target_img': target_file, 'bg_img': bg_file})
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/slide/match/file/json"
resp = requests.post(api_url, files={'target_img': target_file, 'bg_img': bg_file})
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/slide/match/b64"
target_b64str = base64.b64encode(target_file).decode()
bg_b64str = base64.b64encode(bg_file).decode()
jsonstr = json.dumps({'target_img': target_b64str, 'bg_img': bg_b64str})
resp = requests.post(api_url, data=base64.b64encode(jsonstr.encode()).decode())
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/slide/match/b64/json"
resp = requests.post(api_url, data=base64.b64encode(jsonstr.encode()).decode())
print(f"{api_url=}, {resp.text=}")
target_file = open(r'compare_target.jpg', 'rb').read()
bg_file = open(r'compare_bg.jpg', 'rb').read()
api_url = f"{host}/slide/compare/file"
resp = requests.post(api_url, files={'target_img': target_file, 'bg_img': bg_file})
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/slide/compare/file/json"
resp = requests.post(api_url, files={'target_img': target_file, 'bg_img': bg_file})
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/slide/compare/b64"
target_b64str = base64.b64encode(target_file).decode()
bg_b64str = base64.b64encode(bg_file).decode()
jsonstr = json.dumps({'target_img': target_b64str, 'bg_img': bg_b64str})
resp = requests.post(api_url, data=base64.b64encode(jsonstr.encode()).decode())
print(f"{api_url=}, {resp.text=}")
api_url = f"{host}/slide/compare/b64/json"
resp = requests.post(api_url, data=base64.b64encode(jsonstr.encode()).decode())
print(f"{api_url=}, {resp.text=}")
# 方式二
# 获取验证码图片
# headers = {
# "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
# "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4195.1 Safari/537.36"
# }
# resp = requests.get('https://data.gdcic.net/Dop/CheckCode.aspx?codemark=408.15173910730016', headers=headers, verify=False)
# captcha_img = resp.content
#
# 识别
# resp = requests.post(api_url, files={'image': captcha_img})
# print('验证码结果', resp.text)
#
# # 保存验证码图片以供验证
# with open('captcha.jpg', 'wb') as f:
# f.write(captcha_img)
# ******************OCR识别部分开始******************

BIN
test_calc.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 13 KiB

0
tests/test_main.py Normal file
View File