Half-integrality based algorithms for cosegmentation of images

We study the cosegmentation problem where the objective is to segment the same object (i.e., region) from a pair of images. The segmentation for each image can be cast using a partitioning/segmentation function with an additional constraint that seeks to make the histograms of the segmented regions (based on intensity and texture features) similar. Using Markov random field (MRF) energy terms for the simultaneous segmentation of the images together with histogram consistency requirements using the squared L2 (rather than L1) distance, after linearization and adjustments, yields an optimization model with some interesting combinatorial properties. We discuss these properties which are closely related to certain relaxation strategies recently introduced in computer vision. Finally, we show experimental results of the proposed approach.

[1]  Endre Boros,et al.  Pseudo-Boolean optimization , 2002, Discret. Appl. Math..

[2]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[3]  James Ze Wang,et al.  SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture LIbraries , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Gurmeet Singh,et al.  MRF's forMRI's: Bayesian Reconstruction of MR Images via Graph Cuts , 2006, CVPR.

[5]  Andrew Blake,et al.  Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[6]  Jianbo Shi,et al.  Image Matching via Saliency Region Correspondences , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Nebojsa Jojic,et al.  LOCUS: learning object classes with unsupervised segmentation , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[8]  Shimon Ullman,et al.  Learning to Segment , 2004, ECCV.

[9]  Davi Geiger,et al.  Segmentation by grouping junctions , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[10]  Dorit S. Hochbaum,et al.  Efficient bounds for the stable set, vertex cover and set packing problems , 1983, Discret. Appl. Math..

[11]  Jens Vygen,et al.  The Book Review Column1 , 2020, SIGACT News.

[12]  Peter Schlattmann,et al.  Theory and Algorithms , 2009 .

[13]  Fei-Fei Li,et al.  Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[14]  Pierre Hansen,et al.  Roof duality, complementation and persistency in quadratic 0–1 optimization , 1984, Math. Program..

[15]  Harry Shum,et al.  Flash Cut: Foreground Extraction with Flash and No-flash Image Pairs , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Vladimir Kolmogorov,et al.  On partial optimality in multi-label MRFs , 2008, ICML '08.

[17]  Shimon Ullman,et al.  Combining Top-Down and Bottom-Up Segmentation , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[18]  Mário A. T. Figueiredo,et al.  Cosegmentation for Image Sequences , 2007, 14th International Conference on Image Analysis and Processing (ICIAP 2007).

[19]  Ralph Gross,et al.  Concurrent Object Recognition and Segmentation by Graph Partitioning , 2002, NIPS.

[20]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Nahum Kiryati,et al.  Prior-based segmentation by projective registration and level sets , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[22]  Didier Henrion,et al.  Globally Optimal Estimates for Geometric Reconstruction Problems , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[23]  Endre Boros,et al.  Preprocessing of unconstrained quadratic binary optimization , 2006 .

[24]  Joseph Naor,et al.  Tight bounds and 2-approximation algorithms for integer programs with two variables per inequality , 1993, Math. Program..

[25]  B. Kotnyek.  A generalization of totally unimodular and network matrices , 2002 .

[26]  Vladimir Kolmogorov,et al.  Optimizing Binary MRFs via Extended Roof Duality , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.