Skip to content

priyanshu596/license_plate_recognition_using_yolov8_and_easyocr

Repository files navigation

license_plate_recognition_using_yolov8_and_easyocr

Screenshot 2024-12-22 211149

Workflow

1. Object Detection

  • Used YOLOv8 (yolov8n.pt) for detecting number plates.
  • Integrated a custom-trained model tailored for Indian number plates.

2. Text Recognition

  • Incorporated EasyOCR for extracting text from detected plates.
  • Modified the logic in EasyOCR to improve recognition accuracy for region-specific number plates.

3. Bounding Box Stability

  • Interpolated results from CSV outputs to ensure stable bounding boxes across frames.
  • Selected number plate predictions based on the highest confidence score.

4. Future Improvements

  • Plan to train EasyOCR on a customized dataset to enhance recognition accuracy for Indian number plates.

Tools and Technologies

  • YOLOv8: For object detection.
  • EasyOCR: For text recognition.
  • Python: For implementation.
  • CSV Interpolation: To stabilize bounding boxes.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages