Image Segmentation by Discounted Cumulative Ranking on Maximal Cliques

We propose a mid-level image segmentation framework that combines multiple figure-ground hypothesis (FG) constrained at different locations and scales, into interpretations that tile the entire image. The problem is cast as optimization over sets of maximal cliques sampled from the graph connecting non-overlapping, putative figure-ground segment hypotheses. Potential functions over cliques combine unary Gestalt-based figure quality scores and pairwise compatibilities among spatially neighboring segments, constrained by T-junctions and the boundary interface statistics resulting from projections of real 3d scenes. Learning the model parameters is formulated as rank optimization, alternating between sampling image tilings and optimizing their potential function parameters. State of the art results are reported on both the Berkeley and the VOC2009 segmentation dataset, where a 28% improvement was achieved.

[1]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  P. Pardalos,et al.  Handbook of Combinatorial Optimization , 1998 .

[3]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[4]  Steven W. Zucker,et al.  Finding folds: on the appearance and identification of occlusion , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[5]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Jaana Kekäläinen,et al.  Cumulated gain-based evaluation of IR techniques , 2002, TOIS.

[7]  Jitendra Malik,et al.  Learning a classification model for segmentation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[8]  Josh H. McDermott,et al.  Psychophysics with junctions in real images. , 2010, Perception.

[9]  Daniel P. Huttenlocher,et al.  Efficient Graph-Based Image Segmentation , 2004, International Journal of Computer Vision.

[10]  Jianbo Shi,et al.  Learning spectral graph segmentation , 2005, AISTATS.

[11]  S. Palmer,et al.  Surface convexity and extremal edges in depth and figure-ground perception , 2005 .

[12]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[13]  Alexei A. Efros,et al.  Recovering Surface Layout from an Image , 2007, International Journal of Computer Vision.

[14]  Jitendra Malik,et al.  Figure/Ground Assignment in Natural Images , 2006, ECCV.

[15]  Ronen Basri,et al.  Hierarchy and adaptivity in segmenting visual scenes , 2006, Nature.

[16]  Alexei A. Efros,et al.  Recovering Occlusion Boundaries from a Single Image , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[17]  Alexei A. Efros,et al.  Improving Spatial Support for Objects via Multiple Segmentations , 2007, BMVC.

[18]  Michal Irani,et al.  What Is a Good Image Segment? A Unified Approach to Segment Extraction , 2008, ECCV.

[19]  Jitendra Malik,et al.  From contours to regions: An empirical evaluation , 2009, CVPR.

[20]  Michael Lindenbaum,et al.  Boundary ownership by lifting to 2.1D , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[21]  Cristian Sminchisescu,et al.  Constrained parametric min-cuts for automatic object segmentation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.