ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

A SURVEY ON LICENSICLESE PLATE DEBLURRING OF FAST MOVING VEHICLES

Journal: International Journal of Engineering Sciences & Research Technology (IJESRT) (Vol.6, No. 6)

Publication Date:

Authors : ; ;

Page : 348-351

Keywords : Kernel parameter estimation; license plate deblurring; linear motion blur; sparse representation;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Vehicle license plate recognition (LPR) is one of the important fields in Intelligent Transportation Systems (ITS). LPR systems aim to locate, segment and recognize the license plate from captured car image. As the remarkable recognizable proof of a vehicle, license plate is a key piece of information to reveal over-speed vehicles or the ones included in attempt at manslaughter hit-and-run accidents. Be that as it may, the preview of over-speed vehicle caught by reconnaissance camera is every now and again obscured because of quick movement, which is even unrecognizable by human. Those watched plate pictures are more often than not in low determination and endure serious loss of edge data, which cast extraordinary test to existing visually impaired deblurring techniques. For license plate picture obscuring created by quick movement, the obscure bit can be seen as direct uniform convolution and parametrically demonstrated with edge and length. In this paper, we propose a novel plan based on sparse representation to recognize the obscure portion. By examining the sparse representation coefficients of the recuperated picture, we decide the edge of the portion in light of the perception that the recuperated picture has the most sparse representation when the portion edge compares to the bona fide movement point. At that point, we assess the length of the movement portion with Radon change in Fourier space. Our scheme can well handle large motion blur even when the license plate is unrecognizable by human. We evaluate our approach on real-world images and compare with several popular state-of-the-art blind image deblurring algorithms.

Last modified: 2017-06-15 20:28:17