We present a model of curvilinear grouping using piece-wise linear representations of contours and a conditional random field to capture continuity and the frequency of different junction types. Potential completions are generated by building a constrained Delaunay triangulation (CDT) over the set of contours found by a local edge detector. Maximum likelihood parameters for the model are learned from human labeled ground truth. Using held out test data, we measure how the model, by incorporating continuity structure, improves boundary detection over the local edge detector. We also compare performance with a baseline local classifier that operates on pairs of edgels. Both algorithms consistently dominate the low-level boundary detector at all thresholds. To our knowledge, this is the first time that curvilinear continuity has been shown quantitatively useful for a large variety of natural images. Better boundary detection has immediate application in the problem of object detection and recognition.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Scale-invariant contour completion using conditional random fields


    Contributors:
    Xiaofeng Ren, (author) / Fowlkes, C.C. (author) / Malik, J. (author)


    Publication date :

    2005-01-01


    Size :

    721317 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Scale-Invariant Contour Completion Using Conditional Random Fields

    Ren, X. / Fowlkes, C. / Malik, J. et al. | British Library Conference Proceedings | 2005


    Scale-invariant contour segment context in object detection

    Xiao, J. / Wei, H. | British Library Online Contents | 2014


    Perceptual Grouping of Contour Segments Using Markov Random Fields

    Ackermann, F. / Massmann, A. / Posch, S. et al. | British Library Online Contents | 1997


    Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience

    Williams, L. / Jacobs, D. / IEEE Computer Society et al. | British Library Conference Proceedings | 1995