An easy-to-use Chinese license plate recognition system.
Project description
AgentCLPR
简介
- 一个基于 ONNXRuntime、AgentOCR 和 License-Plate-Detector 项目开发的中国车牌检测识别系统。
车牌识别效果
-
支持多种车牌的检测和识别(其中单层车牌识别效果较好):
-
单层车牌:
[[[[373, 282], [69, 284], [73, 188], [377, 185]], ['苏E05EV8', 0.9923506379127502]]] [[[[393, 278], [318, 279], [318, 257], [393, 255]], ['VA30093', 0.7386096119880676]]] [[[[[487, 366], [359, 372], [361, 331], [488, 324]], ['皖K66666', 0.9409016370773315]]]] [[[[304, 500], [198, 498], [199, 467], [305, 468]], ['鲁QF02599', 0.995299220085144]]] [[[[309, 219], [162, 223], [160, 181], [306, 177]], ['使198476', 0.9938704371452332]]] [[[[957, 918], [772, 920], [771, 862], [956, 860]], ['陕A06725D', 0.9791222810745239]]]
-
双层车牌:
[[[[399, 298], [256, 301], [256, 232], [400, 230]], ['浙G66666', 0.8870148431461757]]] [[[[398, 308], [228, 305], [227, 227], [398, 230]], ['陕A00087', 0.9578166644088313]]] [[[[352, 234], [190, 244], [190, 171], [352, 161]], ['宁A66666', 0.9958433652812175]]]
-
快速使用
-
快速安装
# 安装 AgentCLPR $ pip install agentclpr # 根据设备平台安装合适版本的 ONNXRuntime # CPU 版本(推荐非 win10 系统,无 CUDA 支持的设备安装) $ pip install onnxruntime # GPU 版本(推荐有 CUDA 支持的设备安装) $ pip install onnxruntime-gpu # DirectML 版本(推荐 win10 系统的设备安装,可实现通用的显卡加速) $ pip install onnxruntime-directml # 更多版本的安装详情请参考 ONNXRuntime 官网
-
简单调用:
# 导入 CLPSystem 模块 from agentclpr import CLPSystem # 初始化车牌识别模型 clp = CLPSystem() # 使用模型对图像进行车牌识别 results = clp('test.jpg')
-
服务器部署:
-
启动 AgentCLPR Server 服务
$ agentclpr server
-
Python 调用
import cv2 import json import base64 import requests # 图片 Base64 编码 def cv2_to_base64(image): data = cv2.imencode('.jpg', image)[1] image_base64 = base64.b64encode(data.tobytes()).decode('UTF-8') return image_base64 # 读取图片 image = cv2.imread('test.jpg') image_base64 = cv2_to_base64(image) # 构建请求数据 data = { 'image': image_base64 } # 发送请求 url = "http://127.0.0.1:5000/ocr" r = requests.post(url=url, data=json.dumps(data)) # 打印预测结果 print(r.json())
-
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
agentclpr-1.1.0.tar.gz
(9.6 MB
view details)
Built Distribution
File details
Details for the file agentclpr-1.1.0.tar.gz
.
File metadata
- Download URL: agentclpr-1.1.0.tar.gz
- Upload date:
- Size: 9.6 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.6.4 pkginfo/1.7.1 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.1
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | a7cf329c3f4f13ff8bb96775206fe32cb69c6aa17c3ee4c7c7aea00e4cf4878c |
|
MD5 | 01d129de5f78f2bd484326d041633d0a |
|
BLAKE2b-256 | 9695de0856c39a77e13871ae94c55fe2777e8eb9f2ede86509361e3e5f8994ea |
File details
Details for the file agentclpr-1.1.0-py3-none-any.whl
.
File metadata
- Download URL: agentclpr-1.1.0-py3-none-any.whl
- Upload date:
- Size: 9.6 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.2 importlib_metadata/4.6.4 pkginfo/1.7.1 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.1
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0b5f86d9599692156a997a17be3a6536a8ba07c285f634cc9af7c982c8cee4d3 |
|
MD5 | cc0b249c5deb07d77f0f7bceb276a92b |
|
BLAKE2b-256 | 51116cbc13b449f29b4f008bb7427cfd2f5e60959cd722aec31d5b184e5bedf7 |