The paper presents an algorithm allowing for automatic detection of squat flaws in railway rails. These flaws can pose a threat to the safety of railway traffic. A Gabor filter bank along with SVM classifier were used in the detection process. The optimal number of features used to discriminate between squat and the area without squat as well as the parameters for classifier were selected with the help of Genetic Algorithm. Overall classification rate for the system was 95%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Squat detection in railway rails using Gabor filter bank, SVM classifier and Genetic Algorithms


    Contributors:


    Publication date :

    2017-05-01


    Size :

    13573641 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    LASER SCATTEROMETRY FOR DETECTION OF SQUAT DEFECTS IN RAILWAY RAILS

    Piotr Lesiak / Tadeusz Szumiata / Marek Wlazło | DOAJ | 2015

    Free access

    Squat formation on train rails: Origination

    Steerenbergen, M.J.M.M. | Tema Archive | 2012


    Squat formation on train rails: Growth

    Steenbergen, M.J.M.M. | Tema Archive | 2012


    Studs: a squat-type defect in rails

    Grassie, S L / Fletcher, D I / Gallardo Hernandez, E A et al. | SAGE Publications | 2012