The mammalian visual cortex has presented unique visual processing algorithms,. The system rely on spiking neural networks that are coupled leaky-integrators. It has been proposed that the visual system converts 2D images into 1D signatures. So far, efforts to create digital algorithms have been thwarted by interference amongst objects in the input space. Here the marriage of curvature flow with pulse image processing creates a new system in which the expanding autowaves of individual objects in an input scene do not interfere. Thus, it becomes possible to identify multiple objects in a scene solely through the 1D signature.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pulse image processing using centripetal autowaves


    Contributors:

    Conference:

    Signal Processing, Sensor Fusion, and Target Recognition IX ; 2000 ; Orlando,FL,United States


    Published in:

    Publication date :

    2000-08-04





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    CENTRIPETAL AERODYNAMIC PLATFORM SPACECRAFT

    WILLIAMS SR LAWRENCE ELLIS | European Patent Office | 2017

    Free access

    Centripetal aerodynamic platform spacecraft

    WILLIAMS SR LAWRENCE ELLIS | European Patent Office | 2019

    Free access


    Centripetal Force and Resulting Trajectories

    Hahn, Alexander J. | Springer Verlag | 2020


    Automotive active centripetal adjusting empennage and using method thereof

    ZHA YUNFEI / WU HAO / MA FANGWU et al. | European Patent Office | 2020

    Free access