Applying advanced technologies in road sign recognition becomes one of the best usages for the safety driving utilizing awareness of road sign. ADAS systems facilitate the self-driving vehicles and drivers in driving and parking functions. It is inevitable that TSR becomes a crucial part for advanced driver-assistance systems. Intelligent driver-assistance system support drivers in stepping aside of conceivable risk and threat. CNN architecture is an extensively applied to solve the potential problems encountered in road sign recognition. To gain more precise recognition, an optimal performer model is essential for automatically recognizing road sign along the road. This paper aims to compare and do performance analysis among three different models. AlexNet, GoogLeNet and HOG-SVM models are built and their performance are analyzed using the road signs data from Myanmar. The experimented result obtained the maximal classification accuracy of GoogLeNet is 98.32% when compared with other two models, AlexNet and HOG-SVM.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Comparing Performance for Myanmar Road Signs Recognition


    Contributors:


    Publication date :

    2023-02-27


    Size :

    1803280 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Real Time Road Signs Recognition

    Broggi, A. / Cerri, P. / Medici, P. et al. | British Library Conference Proceedings | 2007


    Real Time Road Signs Recognition

    Broggi, Alberto / Cerri, Pietro / Medici, Paolo et al. | IEEE | 2007


    Automatic Recognition of Road Signs

    Inoue, Yasuo / Kohashi, Yuuichirou / Ishikawa, Naoto et al. | SPIE | 2002


    Road-signs recognition system for intelligent vehicles

    Cyganek, Boguslaw | Tema Archive | 2008


    ROAD SIGNS

    AGAJANIAN SARKIS | European Patent Office | 2018

    Free access