Skip to content

Vehicle number plate detection using YOLO and OCR text extraction

Notifications You must be signed in to change notification settings

NandhaKishorM/labelReader

 
 

Repository files navigation

vehicle number plate detection and ocr using YOLO .

Demonstration

Demonstration

The Approach

The identifier's approach is straightforward:

  1. Determine if a number plate is in the picture
  2. Identify where that number plate is
  3. Crop out the relevant asset
  4. Read characters in the cropped picture

Details

  1. LabelReader uses the Yolov3 algorithm for object detection.
  1. A pretrained model can be downloaded
  2. Link : "https://drive.google.com/open?id=1-48BHxaXTEZv3nwZEN7jAbdPLi2x40v7".
  3. Download the model and copy it to the directory
  4. For custom training follows this tutorial "https://medium.com/@manivannan_data/how-to-train-yolov2-to-detect-custom-objects-9010df784f36"

Setup

  1. If you are already installed Anaconda python you can skip this step https://www.anaconda.com/distribution/

  2. conda create -n yolo pip python=3.7

  3. conda activate yolo

  4. pip install -r requirements.txt

  5. apt-get install tesseract-ocr

  6. ./darknet

Getting Started

Run the main script

  1. python app.py

About

Vehicle number plate detection using YOLO and OCR text extraction

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 74.4%
  • JavaScript 18.2%
  • HTML 4.3%
  • Dockerfile 1.6%
  • CSS 1.5%