This paper presents a novel approach to recognize traffic signs using Invariant features and Support Vector Machines (SVM). Images of traffic signs are collected by a digital camera mounted in a vehicle. They are color segmented and all objects which represent signs are extracted and normalized to 36x36 pixels images. Invariant features of sign rims and speed-limit sign interiors of 350 and 250 images are computed and the SVM classifier is trained with these features. Two stages of SVM are trained; the first stage determines the shape of sign rim and the second determines the pictogram of the sign. Training and testing of both SVM classifiers are done using still images. The best performance achieved is 98% for sign rims and 93% for speed limit signs.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Traffic sign classification using invariant features and Support Vector Machines


    Contributors:


    Publication date :

    2008-06-01


    Size :

    441971 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Traffic Sign Classification Using Invariant Features and Support Vector Machines

    Fleyeh, H. / Dougherty, M. | British Library Conference Proceedings | 2008


    Shape classification algorithm using support vector machines for traffic sign recognition

    Gil-Jimenez, P. / Lafuente-Arroyo, S. / Maldonado-Bascon, S. et al. | Tema Archive | 2005


    Traffic Sign Array Decomposition Using Support Vector Machines

    Jimenez, P.G. / Moreno, H.G. / Siegmann, P. et al. | British Library Conference Proceedings | 2008


    Traffic sign array decomposition using support vector machines

    Gil-Jimenez, P. / Gomez-Moreno, H. / Siegmann, P. et al. | IEEE | 2008


    Training invariant support vector machines

    Decoste, D. / Scholkopf, B. | NTRS | 2002