This paper presents a generative model based approach to man-made structure detection in 2D (two-dimensional) natural images. The proposed approach uses a causal multiscale random field suggested by Bouman and Shapiro (1994) as a prior model on the class labels on the image sites. However, instead of assuming the conditional independence of the observed data, we propose to capture the local dependencies in the data using a multiscale feature vector. The distribution of the multiscale feature vectors is modeled as mixture of Gaussians. A set of robust multi-scale features is presented that captures the general statistical properties of man-made structures at multiple scales without relying on explicit edge detection. The proposed approach was validated on real-world images from the Corel data set, and a performance comparison with other techniques is presented.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Man-made structure detection in natural images using a causal multiscale random field


    Beteiligte:
    Kumar, S. (Autor:in) / Hebert, M. (Autor:in)


    Erscheinungsdatum :

    2003-01-01


    Format / Umfang :

    528950 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Man-Made Structure Detection in Natural Images Using a Causal Multiscale Random Field

    Kumar, S. / Hebert, M. / IEEE | British Library Conference Proceedings | 2003


    Segmentation of Range and Intensity Images Using Multiscale Markov Random Field Representations

    Gunsel, B. / Panayirci, E. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1994



    Results Using Random Field Models for the Segmentation of Color Images of Natural Scenes

    Panjwani, D. / Healey, G. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995