An advanced combination of semi-supervised Normalizing Flow & Yolo (YoloNF) to detect and recognize vehicle license plates

TL;DR

This paper introduces a robust ALPR system combining YOLO and Normalizing Flows, utilizing multi-scale transformations and a new dataset to improve license plate detection and recognition in realistic scenarios.

Contribution

The paper proposes a novel two-stage ALPR model integrating YOLO and normalization flows, along with multi-scale transformations and a new Moroccan license plate dataset.

Findings

Effective detection and recognition on small sample sizes

Robust performance in noisy and complex backgrounds

Public availability of the new dataset

Abstract

Fully Automatic License Plate Recognition (ALPR) has been a frequent research topic due to several practical applications. However, many of the current solutions are still not robust enough in real situations, commonly depending on many constraints. This paper presents a robust and efficient ALPR system based on the state-of-the-art YOLO object detector and Normalizing flows. The model uses two new strategies. Firstly, a two-stage network using YOLO and a normalization flow-based model for normalization to detect Licenses Plates (LP) and recognize the LP with numbers and Arabic characters. Secondly, Multi-scale image transformations are implemented to provide a solution to the problem of the YOLO cropped LP detection including significant background noise. Furthermore, extensive experiments are led on a new dataset with realistic scenarios, we introduce a larger public annotated dataset collected from Moroccan plates. We demonstrate that our proposed model can learn on a small number of samples free of single or multiple characters. The dataset will also be made publicly available to encourage further studies and research on plate detection and recognition.