We seek to discover the object categories depicted in a set of unlabelled images. We achieve this using a model developed in the statistical text literature: probabilistic latent semantic analysis (pLSA). In text analysis, this is used to discover topics in a corpus using the bag-of-words document representation. Here we treat object categories as topics, so that an image containing instances of several categories is modeled as a mixture of topics. The model is applied to images by using a visual analogue of a word, formed by vector quantizing SIFT-like region descriptors. The topic discovery approach successfully translates to the visual domain: for a small set of objects, we show that both the object categories and their approximate spatial layout are found without supervision. Performance of this unsupervised method is compared to the supervised approach of Fergus et al. (2003) on a set of unseen images containing only one object per image. We also extend the bag-of-words vocabulary to include 'doublets' which encode spatially local co-occurring regions. It is demonstrated that this extended vocabulary gives a cleaner image segmentation. Finally, the classification and segmentation methods are applied to a set of images containing multiple objects per image. These results demonstrate that we can successfully build object class models from an unsupervised analysis of images.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Discovering objects and their location in images


    Contributors:
    Sivic, J. (author) / Russell, B.C. (author) / Efros, A.A. (author) / Zisserman, A. (author) / Freeman, W.T. (author)


    Publication date :

    2005-01-01


    Size :

    5892354 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Discovering Objects and their Localization in Images

    Sivic, J. / Russell, B. / Efros, A. et al. | British Library Conference Proceedings | 2005


    CORRESPONDENCE - On discovering maritime objects

    Ambler, Mike | Online Contents | 2007


    Discovering hierarchical object models from captioned images

    Jamieson, M. / Eskin, Y. / Fazly, A. et al. | British Library Online Contents | 2012


    ITOHealth: A Multimodal Location-Based System for Discovering Medical Entities

    Sánchez-Cervantes, José Luis / Alor-Hernández, Giner / Juárez-Martínez, Ulises | IEEE | 2010


    Location prediction for dynamic objects

    VELKEY GEZA / KIS KORNEL ISTVAN / KIS LEVENTE et al. | European Patent Office | 2023

    Free access