PSO-ACSC: a large-scale evolutionary algorithm for image matting

Abstract

Image matting is an essential image processing technology due to its wide range of applications. Samplingbased image matting is one of the main branches of image matting research that estimates alpha mattes by selecting the best pixel pairs. It is essentially a large-scale multi-peak optimization problem of pixel pairs. Previous study shows that particle swarm optimization (PSO) can effectively optimize the pixel pairs. However, it still suffers from premature convergence problem which often occurs in pixel pair optimization that involves a large number of local optima. To address this problem, this work presents a parameter-free strategy for PSO called adaptive convergence speed controller (ACSC). ACSC monitors and conditionally controls the particles by competitive pixel pair recombination operator (CPPRO) and pixel pair reset operator (PPRO) during the iteration. ACSC performs CPPRO to improve the competitiveness of a particle when the performance of most of the pixel pairs is worse than that of the best-so-far solution. PPRO is performed to avoid premature convergence when the alpha mattes regarding two selected particles are highly similar. Experimental results show that ACSC significantly enhances the performance of PSO for image matting and provides competitive alpha mattes comparing with state-of-the-art evolutionary algorithms.

Keywords

evolutionary computing / particle swarm optimization / large-scale optimization / image matting

References

[1] Levin A, Lischinski D, Weiss Y. A closed-form solution to natural image matting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(2): 228–242

[2] Lee P, Wu Y. Nonlocal matting. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2011, 2193–2200

[3] Chen Q, Li D, Tang C K. KNN matting. IEEE Transactions on Pattern Analysis and Machine Antelligence, 2013, 35(9): 2175–2188

[4] Aksoy Y, Ozan Aydin T, Pollefeys M. Designing effective inter-pixel information flow for natural image matting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017, 29–37

[5] Wang J, Cohen M F. Optimized color sampling for robust matting. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2007, 1–8

[6] Rhemann C, Rother C, Gelautz M. Improving color modeling for alpha matting. In: Proceedings of British Machine Vision Conference. 2008, 1155–1164

[7] Gastal E S, Oliveira M M. Shared sampling for real-time alpha matting. In: Proceedings of Computer Graphics Forum. 2010, 575–584

[8] He K, Rhemann C, Rother C, Tang X, Sun J. A global sampling method for alpha matting. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2011, 2049–2056

[9] Shahrian E, Rajan D. Weighted color and texture sample selection for image matting. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2012, 718–725

[10] Shahrian E, Rajan D, Price B, Cohen S. Improving image matting using comprehensive sampling sets. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2013, 636–643

[11] Karacan L, Erdem A, Erdem E. Image matting with KL-divergence based sparse sampling. In: Proceedings of the IEEE International Conference on Computer Vision. 2015, 424–432

[12] Liang L, Han H, Zhaoquan C, Hui H. Using particle swarm large-scale optimization to improve sampling-based image matting. In: Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation. 2015, 957–961

[13] Cai Z Q, Lv L, Huang H, Hu H, Liang Y H. Improving sampling-based image matting with cooperative coevolution differential evolution algorithm. Soft Computing, 2017, 21(15): 4417–4430

[14] Eberhart R, Kennedy J. A new optimizer using particle swarm theory. In: Proceedings of the 6th International Symposium on Micro Machine and Human Science. 1995, 39–43

[15] Zhang G, Li Y, Shi Y. Distributed learning particle swarm optimizer for global optimization of multimodal problems. Frontiers of Computer Science, 2018, 12(1): 122–134

[16] Huang H, Lv L, Ye S, Hao Z. Particle swarm optimization with convergence speed controller for large-scale numerical optimization. Soft Computing, 2019, 23(12): 4421–4437

[17] Chen W N, Tan D Z. Set-based discrete particle swarm optimization and its applications: a survey. Frontiers of Computer Science, 2018, 12(2): 203–216

[18] Rhemann C, Rother C, Wang J, Gelautz M, Kohli P, Rott P. A perceptually motivated online benchmark for image matting. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2009, 1826–1833

[19] Chen H C, Wang S J. The use of visible color difference in the quantitative evaluation of color image segmentation. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. 2004, iii–593

[20] Li X, Yao X. Cooperatively coevolving particle swarms for large scale optimization. IEEE Transactions on Evolutionary Computation, 2012, 16(2): 210–224

[21] Haynes W. Wilcoxon rank sum test. In: Dubitzky W, Wolkenhauer O, Cho K H, Yokota H, eds. Encyclopedia of Systems Biology. Springer, New York, 2013, 2354–2355

[22] Qian C, Li G, Feng C, Tang K. Distributed pareto optimization for subset selection. In: Proceedings of International Joint Conference on Artificial Intelligence. 2018, 1492–1498

[23] Qian C, Shi J C, Yu Y, Tang K, Zhou Z H. Parallel pareto optimization for subset selection. In: Proceedings of International Joint Conference on Artificial Intelligence. 2016, 1939–1945

RIGHTS & PERMISSIONS

2020 Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature