We describe a novel technique for identifying semantically equivalent parts in images belonging to the same object class, (e.g. eyes, license plates, aircraft wings etc.). The visual appearance of such object parts can differ substantially, and therefore, traditional image similarity-based methods are inappropriate for this task. The technique we propose is based on the use of common context. We first retrieve context fragments, which consistently appear together with a given input fragment in a stable geometric relation. We then use the context fragments in new images to infer the most likely position of equivalent parts. Given a set of image examples of objects in a class, the method can automatically learn the part structure of the domain - identify the main parts, and how their appearance changes across objects in the class. Two applications of the proposed algorithm are shown: the detection and identification of object parts and object recognition.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Identifying semantically equivalent object fragments


    Contributors:
    Epshtein, B. (author) / Ullman, S. (author)


    Publication date :

    2005-01-01


    Size :

    369612 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Semantically-driven automatic creation of training sets for object recognition

    Cheng, D. S. / Setti, F. / Zeni, N. et al. | British Library Online Contents | 2015


    Semantically Enriched Multi-Modal Routing

    Eiter, Thomas / Krennwallner, Thomas / Prandtstetter, Matthias et al. | Springer Verlag | 2014


    LOCALIZATION USING SEMANTICALLY SEGMENTED IMAGES

    ADAMS DEREK / KAISER NATHANIEL JON / BOSSE MICHAEL CARSTEN | European Patent Office | 2020

    Free access

    Towards a semantically enhanced control architecture

    Milis, Georgios / Panayiotou, Christos / Polycarpou, Marios | BASE | 2012

    Free access

    Towards a Semantically Enriched Local Dynamic Map

    Eiter, Thomas / Füreder, Herbert / Kasslatter, Fritz et al. | Springer Verlag | 2018

    Free access