Texture segmentation by statistical deformable models

Oriol Pujol, Petia Radeva

    Research output: Contribution to journalArticleResearchpeer-review

    18 Citations (Scopus)


    © 2004 World Scientific Publishing Company. Deformable models have received much popularity due to their ability to include high-level knowledge on the application domain into low-level image processing. Still, most proposed active contour models do not sufficiently profit from the application information and they are too generalized, leading to non-optimal final results of segmentation, tracking or 3D reconstruction processes. In this paper we propose a new deformable model defined in a statistical framework to segment objects of natural scenes. We perform a supervised learning of local appearance of the textured objects and construct a feature space using a set of co-occurrence matrix measures. Linear Discriminant Analysis allows us to obtain an optimal reduced feature space where a mixture model is applied to construct a likelihood map. Instead of using a heuristic potential field, our active model is deformed on a regularized version of the likelihood map in order to segment objects characterized by the same texture pattern. Different tests on synthetic images, natural scene and medical images show the advantages of our statistic deformable model.
    Original languageEnglish
    Pages (from-to)433-452
    JournalInternational Journal of Image and Graphics
    Issue number3
    Publication statusPublished - 1 Jul 2004


    • parametric active contours
    • statistic snakes
    • Texture segmentation


    Dive into the research topics of 'Texture segmentation by statistical deformable models'. Together they form a unique fingerprint.

    Cite this