Skip to content

ANPR Automatic Number-Plate Recognition with YOLOX object detection and Deepsort object tracking using Tesseract OCR

License

Notifications You must be signed in to change notification settings

ZZIDZZ/YOLOX-DeepSort-ANPR

Repository files navigation

YOLOX-DeepSort-ANPR

tokyo

Overview

ANPR utilizing YOLOX object detection from a custom trained dataset to detect license plates, and deepsort object tracking. The detection frames then pipelined to Tesseract OCR to detect characters (TODO)

How to Use

YOLOX

Don't forget to install yolox first, guide can be found on the official YOLOX repository: Megvii-BaseDetection YOLOX or you can just simply python3 ./setup.py

PyTesseract

Detailed PyTesseract installation guide can be read here: www.projectpro.io, Install PyTesseract

Example

to run detection on a video: python3 ./demo.py --path ./path/to/video

Datasets Used

Original dataset (VOC2017 format) that is used can be found at andrewmd - Car License Plate Detection However, training is done on COCO JSON Format dataset that could be found here: COCO ANPR - Google Drive

Future Improvements

  • Optimize model accuracy
  • Optimize OCR detection
  • Restructure project
  • Optimize engine efficiency

About

ANPR Automatic Number-Plate Recognition with YOLOX object detection and Deepsort object tracking using Tesseract OCR

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published