Scale-invariant contour completion using conditional random fields

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

[1]  Gunilla Borgefors,et al.  Hierarchical Chamfer Matching: A Parametric Edge Matching Algorithm , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Shimon Ullman,et al.  Structural Saliency: The Detection Of Globally Salient Structures using A Locally Connected Network , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[3]  Steven W. Zucker,et al.  Trace Inference, Curvature Consistency, and Curve Detection , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Daniel P. Huttenlocher,et al.  A multi-resolution technique for comparing images using the Hausdorff distance , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  D. Mumford.  Elastica and Computer Vision , 1994 .

[7]  Lance R. Williams,et al.  Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience , 1995, Neural Computation.

[8]  Steven W. Zucker,et al.  Computing Contour Closure , 1996, ECCV.

[9]  Jonathan Richard Shewchuk,et al.  Triangle: Engineering a 2D Quality Mesh Generator and Delaunay Triangulator , 1996, WACG.

[10]  Lance R. Williams,et al.  A Comparison of Measures for Detecting Natural Shapes in Cluttered Backgrounds , 1998, ECCV.

[11]  S. Palmer.  Vision Science : Photons to Phenomenology , 1999 .

[12]  Kaleem Siddiqi,et al.  Contour Fragment Grouping and Shared, Simple Occluders , 1999, Comput. Vis. Image Underst..

[13]  Yair Weiss,et al.  Correctness of Local Probability Propagation in Graphical Models with Loops , 2000, Neural Computation.

[14]  Serge J. Belongie,et al.  Matching shapes , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[15]  Jeffrey S. Perry,et al.  Edge co-occurrence in natural images predicts contour grouping performance , 2001, Vision Research.

[16]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[17]  Shimon Ullman,et al.  Class-Specific, Top-Down Segmentation , 2002, ECCV.

[18]  J. Elder,et al.  Ecological statistics of Gestalt laws for the perceptual organization of contours. , 2002, Journal of vision.

[19]  Jitendra Malik,et al.  A Probabilistic Multi-scale Model for Contour Completion Based on Image Statistics , 2002, ECCV.

[20]  Jitendra Malik,et al.  Learning to Detect Natural Image Boundaries Using Brightness and Texture , 2002, NIPS.

[21]  Tomer Hertz,et al.  Learning and inferring image segmentations using the GBP typical cut algorithm , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[22]  Yizhou Yu,et al.  Two-Level Image Segmentation Based on Region and Edge Integration , 2003, DICTA.

[23]  Lance R. Williams,et al.  Segmentation of Multiple Salient Closed Contours from Real Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  Zhuowen Tu,et al.  Image Parsing: Segmentation, Detection, and Recognition , 2003 .

[25]  Martial Hebert,et al.  Discriminative random fields: a discriminative framework for contextual interaction in classification , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[26]  R. Zemel,et al.  Multiscale conditional random fields for image labeling , 2004, CVPR 2004.

[27]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Miguel Á. Carreira-Perpiñán,et al.  Multiscale conditional random fields for image labeling , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[29]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[30]  Jitendra Malik,et al.  Recovering human body configurations: combining segmentation and recognition , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..