International Journal of Computer Vision

, Volume 77, Issue 1, pp 47-63

First online:

Learning Probabilistic Models for Contour Completion in Natural Images

  • Xiaofeng RenAffiliated withToyota Technological Institute at Chicago Email author 
  • , Charless C. FowlkesAffiliated withSchool of Information and Computer Science, University of California
  • , Jitendra MalikAffiliated withComputer Science Division, University of California at Berkeley

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access


Using a large set of human segmented natural images, we study the statistics of region boundaries. We observe several power law distributions which likely arise from both multi-scale structure within individual objects and from arbitrary viewing distance. Accordingly, we develop a scale-invariant representation of images from the bottom up, using a piecewise linear approximation of contours and constrained Delaunay triangulation to complete gaps. We model curvilinear grouping on top of this graphical/geometric structure using a conditional random field to capture the statistics of continuity and different junction types. Quantitative evaluations on several large datasets show that our contour grouping algorithm consistently dominates and significantly improves on local edge detection.


Grouping Natural images Boundary detection Scale invariance Conditional random fields Machine learning