Automatic Vehicle License Plate Recognition Using Optimal Deep Learning Model
作者机构:College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Computer Science&EngineeringIcfaiTechICFAI Foundation for Higher EducationHyderabadIndia Assistant professor ResearchResearch CenterLebanese French UniversityErbil44001Iraq Department of Entrepreneurship and LogisticsPlekhanov Russian University of EconomicsMoscow117997Russia Department of LogisticsState University of ManagementMoscow109542Russia Department of Computer ApplicationsAlagappa UniversityKaraikudiIndia
出 版 物:《Computers, Materials & Continua》 (计算机、材料和连续体(英文))
年 卷 期:2021年第67卷第5期
页 面:1881-1897页
核心收录:
学科分类:08[工学] 0812[工学-计算机科学与技术(可授工学、理学学位)]
主 题:Deep learning license plate recognition intelligent transportation segmentation
摘 要:The latest advancements in highway research domain and increase in the number of vehicles everyday led to wider exposure and attention towards the development of efficient Intelligent Transportation System(ITS).One of the popular research areas i.e.,Vehicle License Plate Recognition(VLPR)aims at determining the characters that exist in the license plate of the *** VLPR process is a difficult one due to the differences in viewpoint,shapes,colors,patterns,and non-uniform illumination at the time of capturing *** current study develops a robust Deep Learning(DL)-based VLPR model using Squirrel Search Algorithm(SSA)-based Convolutional Neural Network(CNN),called the SSA-CNN *** presented technique has a total of four major processes namely preprocessing,License Plate(LP)localization and detection,character segmentation,and *** Transform(HT)is applied as a feature extractor and SSA-CNN algorithm is applied for character recognition in *** SSA-CNN method effectively recognizes the characters that exist in the segmented image by optimal tuning of CNN *** HT-SSA-CNN model was experimentally validated using the Stanford Car,FZU Car,and HumAIn 2019 Challenge *** experimentation outcome verified that the presented method was better under several *** projected HT-SSA-CNN model implied the best performance with optimal overall accuracy of 0.983%.