Fastanpr

Abstract

1. Introduction

A fast automatic number-plate recognition (ANPR) library. This package employs YOLOv8, a lightweight model, for detection, and Paddle OCR, a lightweight optical character recognition (OCR) library, for recognizing text in detected number plates.

2. Objective

A fast automatic number-plate recognition (ANPR) library

This project demonstrates how Python, YOLO can be applied to a real-world AI & Machine Learning problem.

4. Technology Stack

5. System Requirements

General requirements for this technology stack — check the README for exact versions.

• Python 3.8 or later
• pip / virtualenv for dependencies
• VS Code, PyCharm or Jupyter Notebook
• Git (to clone the repository)

6. Installation & Setup

git clone https://github.com/arvindrajan92/fastanpr.git
cd fastanpr

pip install fastanpr

import cv2
from fastanpr import FastANPR

# Create an instance of FastANPR
fast_anpr = FastANPR()

# Load images (images should be of type numpy ndarray)
files = [...]
images = [cv2.cvtColor(cv2.imread(file), cv2.COLOR_BGR2RGB) for file in files]

# Run ANPR on the images
number_plates = await fast_anpr.run(images)

# Print out results
for file, plates in zip(files, number_plates):
    print(file)
    for plate in plates:
        print("Plate Attributes:")
        print("Detection bounding box:", plate.det_box)
        print("Detection confidence:", plate.det_conf)
        print("Recognition text:", plate.rec_text)
        print("Recognition polygon:", plate.rec_poly)
        print("Recognition confidence:", plate.rec_conf)
        print()
    print()

import base64
import requests

# Step 1: Read the image file
image_path = 'tests/images/image001.jpg'
with open(image_path, 'rb') as image_file:
    image_data = image_file.read()

# Step 2: Convert the image to a base64 encoded string
base64_image_str = base64.b64encode(image_data).decode('utf-8')

# Prepare the data for the POST request (assuming the API expects JSON)
data = {'image': base64_image_str}

# Step 3: Send a POST request
response = requests.post(url='http://127.0.0.1:8000/recognise', json=data)

# Check the response
if response.status_code == 200:
    # 'number_plates': [
    #       {
    #           'det_box': [682, 414, 779, 455],
    #           'det_conf': 0.29964497685432434,
    #           'rec_poly': [[688, 420], [775, 420], [775, 451], [688, 451]],
    #           'rec_text': 'BVH826',
    #           'rec_conf': 0.940690815448761
    #       }
    # ]
    print(response.json())
else:
    print(f"Request failed with status code {response.status_code}.")

Full setup instructions are in the project README.

7. Future Enhancements

Suggested extensions you can add to make this your own project.

• Deploy the model as a web app with Streamlit, Flask or FastAPI
• Compare against an additional model and report the metric difference
• Add explainability (SHAP / Grad-CAM)

8. Viva / Review Questions

Common questions examiners ask for projects in this domain.

1. What dataset does the project use and how was it pre-processed?
2. Which algorithm / model architecture is used and why was it chosen over alternatives?
3. How are training and testing data split, and how is overfitting avoided?
4. Which evaluation metrics (accuracy, precision, recall, F1) are reported and what do they mean here?
5. How would you deploy this model for real users?

9. Source Code & License

This project is developed by arvindrajan92 and published on GitHub under the GNU Affero General Public License v3.0. Please follow the license terms and credit the original author when you use or modify this code.