A Bangladeshi License Plate Detection System Based on Extracted Color Features

Nooruddin, Sheikh; Sharna, Falguni Ahmed; Ahsan, Sk. Md. Masudul

doi:10.1109/iccit51783.2020.9392672

Cited by 5 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This meticulous segmentation produced a new dataset specifically tailored for character recognition. The dataset was further enriched by incorporating additional character block samples from other datasets, namely BLPDB[20,21], Poribohon-BD [22], and LPDB-A [23]. This strategic amalgamation not only diversified the dataset but also significantly expanded the training data.…”

mentioning

confidence: 99%

Real-Time Vehicle License Plate Recognition (VLPR) Using Deep CNN

2024

IJFMR

View full text Add to dashboard Cite

This research introduces a dual-component Vehicle License Plate Recognition (VLPR) system designed to improve the accuracy and efficiency of automated traffic monitoring systems. The first component employs YOLOv8 for real-time detection of vehicle license plates, capitalizing on its advanced capabilities to effectively manage variations in environmental conditions and plate obfuscation. The second component, a custom Convolutional Neural Network (CNN), is optimized for high-precision character recognition from the detected plates. Trained on a dataset of over 33,000 images, the system achieves a detection accuracy of 97.30% and a character recognition accuracy of 98.10%, demonstrating its robustness and effectiveness. This integrated approach not only enhances the reliability of automated traffic monitoring but also holds significant promise for applications requiring high accuracy and real-time data processing across various operational settings.

show abstract

mentioning

confidence: 99%