Cue Integration for Figure/Ground Labeling

We present a model of edge and region grouping using a conditional random field built over a scale-invariant representation of images to integrate multiple cues. Our model includes potentials that capture low-level similarity, mid-level curvilinear continuity and high-level object shape. Maximum likelihood parameters for the model are learned from human labeled groundtruth on a large collection of horse images using belief propagation. Using held out test data, we quantify the information gained by incorporating generic mid-level cues and high-level shape.

[1]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  B. Gibson,et al.  Object recognition contributions to figure-ground organization: Operations on outlines and subjective contours , 1994, Perception & psychophysics.

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

[4]  Jitendra Malik,et al.  Textons, contours and regions: cue integration in image segmentation , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

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

[6]  Jitendra Malik,et al.  Geometric blur for template matching , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

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

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

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

[10]  Zhuowen Tu,et al.  Image Parsing: Unifying Segmentation, Detection, and Recognition , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

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

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

[13]  Tomer Hertz,et al.  Pairwise Clustering and Graphical Models , 2003, NIPS.

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

[15]  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..

[16]  Laurence Commissaire divisionnaire,et al.  Mid-level Cues Improve Boundary Detection , 2005 .

[17]  Andrew Zisserman,et al.  OBJ CUT , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).