Nepali Number Plate Recognition System Achieves 93% Accuracy

Researchers have developed a new Automatic Number Plate Recognition (ANPR) system specifically designed for Nepali license plates, which use the Devanagari script. The system employs a pipeline that first uses YOLO-based models for detecting license plates and characters, followed by a Convolutional Neural Network (CNN) classifier trained on 34 Devanagari characters. This approach achieved up to 93% recognition accuracy, demonstrating its effectiveness in real-world conditions and offering a scalable solution for traffic management in Nepal. AI

IMPACT This specialized ANPR system could improve traffic management and enforcement in regions using non-Latin scripts.

RANK_REASON The cluster contains an academic paper detailing a new computer vision model for a specific application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• CNN
• Devanagari
• Nepali
• YOLO

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →