Scale-invariant contour completion using conditional random fields
Xiaofeng Ren
Fowlkes, C.C.
Malik, J.
Div. of Comput. Sci., California Univ., Berkeley, CA;
This paper appears in: Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on
Publication Date: 17-21 Oct. 2005
Volume: 2,
On page(s): 1214-1221 Vol. 2
Location: Beijing,
ISSN: 1550-5499
ISBN: 0-7695-2334-X
INSPEC Accession Number: 8824308
Digital Object Identifier: 10.1109/ICCV.2005.213
Current Version Published: 2005-12-05
Abstract
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
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
