We propose a general framework for parsing images into regions and objects. In this framework, the detection and recognition of objects proceed simultaneously with image segmentation in a competitive and cooperative manner. We illustrate our approach on natural images of complex city scenes where the objects of primary interest are faces and text. This method makes use of bottom-up proposals combined with top-down generative models using the data driven Markov chain Monte Carlo (DDMCMC) algorithm, which is guaranteed to converge to the optimal estimate asymptotically. More precisely, we define generative models for faces, text, and generic regions- e.g. shading, texture, and clutter. These models are activated by bottom-up proposals. The proposals for faces and text are learnt using a probabilistic version of AdaBoost. The DDMCMC combines reversible jump and diffusion dynamics to enable the generative models to explain the input images in a competitive and cooperative manner. Our experiments illustrate the advantages and importance of combining bottom-up and top-down models and of performing segmentation and object detection/recognition simultaneously.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Image parsing: unifying segmentation, detection, and recognition


    Beteiligte:
    Zhuowen Tu, (Autor:in) / Xiangrong Chen, (Autor:in) / Yuille, (Autor:in) / Zhu, (Autor:in)


    Erscheinungsdatum :

    2003-01-01


    Format / Umfang :

    969761 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Image Parsing: Unifying Segmentation, Detection and Recognition

    Chen, X. / Tu, Z. / Yuille, A. et al. | British Library Conference Proceedings | 2003


    Image Parsing: Unifying Segmentation, Detection, and Recognition

    Tu, Z. / Chen, X. / Yuille, A. L. et al. | British Library Online Contents | 2005


    Unifying terrain awareness through real-time semantic segmentation

    Yang, Kailun / Bergasa, Luis M. / Romera, Eduardo et al. | IEEE | 2018


    Region Competition: Unifying Snakes, Region Growing, Energy/Bayes/MDL for Multi-band Image Segmentation

    Zhu, S. / Yuille, A. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995