Described is a system that can recognize novel objects that the system has never before seen. The system uses a training image set to learn a model that maps visual features from known images to semantic attributes. The learned model is used to map visual features of an unseen input image to semantic attributes. The unseen input image is classified as belonging to an image class with a class label. A device is controlled based on the class label.


    Access

    Download


    Export, share and cite



    Title :

    ZERO SHOT MACHINE VISION SYSTEM VIA JOINT SPARSE REPRESENTATIONS


    Additional title:

    ZERO-SHOT-MASCHINENSICHTSYSTEM ÜBER GEMEINSAME SPARSE-REPRESENTATION
    SYSTÈME DE VISION DE MACHINE SANS DONNÉE DE RÉFÉRENCE PAR L'INTERMÉDIAIRE DE REPRÉSENTATIONS ÉPARSES COMMUNES


    Contributors:

    Publication date :

    2021-01-20


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    G06K Erkennen von Daten , RECOGNITION OF DATA / B60R Fahrzeuge, Fahrzeugausstattung oder Fahrzeugteile, soweit nicht anderweitig vorgesehen , VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    ZERO SHOT MACHINE VISION SYSTEM VIA JOINT SPARSE REPRESENTATIONS

    KOLOURI SOHEIL / RAO SHANKAR / KIM KYUNGNAM | European Patent Office | 2019

    Free access

    Zero shot machine vision system via joint sparse representations

    KOLOURI SOHEIL / RAO SHANKAR R / KIM KYUNGNAM | European Patent Office | 2020

    Free access

    Sparse Representations for Medium Level Vision

    Forssen, P.-E. | British Library Online Contents | 2002


    Sparse Representations for Image Decompositions

    Geiger, D. / Liu, T.-L. / Donahue, M. J. | British Library Online Contents | 1999


    Zero-VIRUS*: Zero-shot Vehicle Route Understanding System for Intelligent Transportation

    Yu, Lijun / Feng, Qianyu / Qian, Yijun et al. | IEEE | 2020