$L_p$ -Norm-Based Sparse Regularization Model for License Plate Deblurring

Chenping Zhao,Jingben Yin,Yingjun Wang,Hongwei Jiao,Xuezhi Li

doi:10.1109/access.2020.2969675

Abstract

We propose an $L_{p}$ -norm-based sparse regularization model for license plate deblurring, which is motivated by distinctive properties of license plate images. For the blurred images, general deblurring methods may restore a good overall visual effect. However, in real-life traffic surveillance system, the deblurring results may be not good for license plates. The main reason lies in that general deblurring methods do not give sufficient thought to the features of license plate, which could be important priors for deblurring. Focusing on this issue, analysis on the statistical distribution characteristics of the license plates are launched, based on which an $L_{p}$ -norm-based regularization model is proposed. Furthermore, alternating direction method of multipliers are introduced to solve the model. Experimental results demonstrate that the proposed model performs favorably against the state-of-the-art license plate image deblurring methods.

Highlights

With the increasing number of vehicles, traffic violations such as running the red light and hit-and-run increase rapidly
We mainly report the experimental results under the mixture form of the defocus and motion blur
COMPARISONS OF DEBLURRING RESULTS We evaluate the performance of the proposed method, and compare it with state-of-the-art methods: the L0-norm based regularization model, i.e. the work in [10], the L1-norm based regularization model, the license plate deblurring method in [11] and the license plate deblurring method for fast moving vehicle in [20]

Summary

Introduction

With the increasing number of vehicles, traffic violations such as running the red light and hit-and-run increase rapidly. The drive recorders or surveillance cameras perform much better than before, the license plates of vehicles are often blurred due to various reasons. As a result, this brings great challenges to LPR. License plate deblurring is very important in the traffic surveillance system. There are several factors that give rise to the blurring corruption on the license plate images. The second factor comes from the movements of the vehicle. When the vehicles run a red light, they are often in a very fast speed, the captured images

Objectives

Results

Conclusion