All Projects → Raymondhhh90 → Idcardocr

Raymondhhh90 / Idcardocr

Licence: gpl-3.0
离线环境下第二代居民身份证信息识别

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Idcardocr

Stb Tester
Automated Testing for Set-Top Boxes and Smart TVs
Stars: ✭ 148 (-54.88%)
Mutual labels:  opencv, ocr
ocreval
Update of the ISRI Analytic Tools for OCR Evaluation with UTF-8 support
Stars: ✭ 48 (-85.37%)
Mutual labels:  ocr, tesseract-ocr
Ocrtable
Recognize tables and text from scanned images that contain tables. 从包含表格的扫描图片中识别表格和文字
Stars: ✭ 155 (-52.74%)
Mutual labels:  opencv, ocr
Robin
RObust document image BINarization
Stars: ✭ 131 (-60.06%)
Mutual labels:  opencv, ocr
TesseractStudio.Net
A free Windows graphical interface to the Tesseract 4.0 OCR engine.
Stars: ✭ 38 (-88.41%)
Mutual labels:  ocr, tesseract-ocr
Spacextract
Extraction and analysis of telemetry from rocket launch webcasts (from SpaceX and RocketLab)
Stars: ✭ 131 (-60.06%)
Mutual labels:  opencv, ocr
receipt-manager-app
Receipt parser application written in dart.
Stars: ✭ 140 (-57.32%)
Mutual labels:  ocr, tesseract-ocr
Idmatch
Match faces on id cards with OCR capabilities.
Stars: ✭ 52 (-84.15%)
Mutual labels:  opencv, ocr
Nkocr
🔎📝 This is a module to make specifics OCRs at food products and nutritional tables.
Stars: ✭ 15 (-95.43%)
Mutual labels:  ocr, tesseract-ocr
How-to-use-tesseract-ocr-4.0-with-csharp
How to use Tesseract OCR 4.0 with C#
Stars: ✭ 60 (-81.71%)
Mutual labels:  ocr, tesseract-ocr
Cpp Image Analysis
DataCore bot image analysis component
Stars: ✭ 125 (-61.89%)
Mutual labels:  opencv, ocr
BasicArabicOCR
A very basic Arabic OCR based on tesseract OCR engine written in Java.
Stars: ✭ 19 (-94.21%)
Mutual labels:  ocr, tesseract-ocr
Gaspumpocr
Python and OpenCV scripts to detect digits on a Gas Pump
Stars: ✭ 116 (-64.63%)
Mutual labels:  opencv, ocr
Scene Text Recognition
Scene text detection and recognition based on Extremal Region(ER)
Stars: ✭ 146 (-55.49%)
Mutual labels:  opencv, ocr
Faceai
一款入门级的人脸、视频、文字检测以及识别的项目.
Stars: ✭ 9,207 (+2707.01%)
Mutual labels:  opencv, tesseract-ocr
Opencv
📷 Computer-Vision Demos
Stars: ✭ 244 (-25.61%)
Mutual labels:  opencv, ocr
Pytesseractid
使用 pytesseract ocr 识别 18 位身份证号
Stars: ✭ 23 (-92.99%)
Mutual labels:  opencv, ocr
Sikulix1
SikuliX version 2.0.0+ (2019+)
Stars: ✭ 1,007 (+207.01%)
Mutual labels:  opencv, tesseract-ocr
NLP-image-to-text
code to extract text from images
Stars: ✭ 28 (-91.46%)
Mutual labels:  ocr, tesseract-ocr
breach-protocol-autosolver
Solve breach protocol minigame in second(s). Windows/Linux/GeForce Now/Google Stadia. Every language.
Stars: ✭ 28 (-91.46%)
Mutual labels:  ocr, tesseract-ocr

第二代身份证信息识别

可识别身份证上所有信息:姓名,性别,民族,出生日期,住址,身份证号码。提供Docker镜像部署方式

  • 2018/8/21 更新,应该较大提升了准确率
  • 2018/11/8 更新,优化算法,更新至tesseract4.0, 单张图片识别时间降低到3s以下

依赖:

本项目在Ubuntu 18.10基于tesseract 4.0 rc3,OpenCV2; 使用Python3.6进行开发
apt依赖安装:
sudo apt install python3 python3-pip tesseract-ocr tesseract-ocr-chi-sim tzdata libsm6 libxext6 python3-tk -y

Python依赖安装:
sudo pip3 install -r idcardocr/requirements.txt

tessdata配置:
sudo cp tessdata/* /usr/share/tesseract-ocr/tessdata

使用方法:

识别本地图片
import idcard_recognize;print idcard_recognize.process('testimages/3.jpg')

http_server远程接收图片
python3 idcard_recognize.py
默认监听端口为8080

Docker运行http_server:
docker pull raymondwong/idcardocr;docker run -d -p 8080:8080 raymondwong/idcardocr

测试:

使用curl向服务器发送图片:
curl --request POST \ --url http://127.0.0.1:8080 \ --header 'content-type: multipart/form-data; boundary=----WebKitFormBoundary7MA4YWxkTrZu0gW' \ --form '[email protected]/testimages/3.jpg'

使用Postman:
avatar

性能

平台: I5 8259u + 16g macOS 13.14 关闭OpenCL
处理单张图片时间在2.5秒左右(单张图片只能使用单核心)
处理4张图片时间也是4秒左右(4核心)
关于OPENCL: 开启并不会使单张图片处理速度加快,但是能让你在同时间处理更多图片(譬如I5 6500每秒能处理4张图片,开启OPENCL后每秒能处理6张图片)
开启OPENCL: 默认关闭,可以自行修改idcard_recognize.http_server中的cv2.ocl.setUseOpenCL(False)开启

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].