In the world of artificial intelligence and advancement in technologies, big companies like Tesla, Uber, Google, etc. are operating on independent vehicles and self-riding cars. The content or image identification and acknowledgment from traffic boards is a difficult issue. The quantity of significant application zones is reliant upon text discovery and acknowledgment, including progressed driver help frameworks, street looking over, and self-sufficient vehicles. In this proposed work, a framework for programmed discovery and acknowledgment of text and image in rush hour traffic signs is proposed. The present work uses a German traffic sign recognition dataset that contains diverse traffic signs composed of arbitrary roadsides. This dataset contains more than 50,000 images of 43 different classes of traffic signs. The work can be divided into two stages; the first stage is the observation of the area and the second is character identification. For textual content observation in signboard and recollection reason, the optical individual identification technique is used. The experimental results show that the proposed system achieved a better accuracy for text detection and text extraction.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Optical Character Recognition-Based Signboard Detection


    Additional title:

    Lect. Notes Electrical Eng.




    Publication date :

    2022-08-02


    Size :

    9 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    OPTICAL FIBER SIGNBOARD

    PARK JAE WOO | European Patent Office | 2023

    Free access

    Signboard

    SHIN CHANG SU | European Patent Office | 2020

    Free access

    Emergency traffic signboard

    WANG ZHIFENG | European Patent Office | 2015

    Free access

    Folding type signboard

    European Patent Office | 2022

    Free access

    Traffic warning signboard

    WANG LIN / LIN XIANGXIANG / WEI QIBIN et al. | European Patent Office | 2022

    Free access