Improved accuracy of superpixel segmentation by region merging method

Abstract

Superpixel as an important pre-processing technique has been successfully used in many vision applications. In this paper, we proposed a region merging method to improve superpixel segmentation accuracy with low computational cost. We first segmented the image into many accurate small regions, and then progressively agglomerated them until the desired region number was reached. The region merging weight was derived from a novel energy function, which encourages the superpixel with color consistency and similar size. Experimental results on the Berkeley BSDS500 data set showed that our region merging method can significantly improve the accuracy of superpixel segmentation. Moreover, the region merging method only need 50 ms to process a 481 × 321 image on a single Intel i3 CPU at 2.5 GHz.

Keywords

image processing / image segmentation / superpixels / region merging

References

[1] Ren X, Malik J. Learning a classification model for segmentation. In: Proceedings of IEEE International Conference on Computer Vision. 2003, 10–17

[2] Kohli P, Ladický L, Torr P H S. Robust higher order potentials for enforcing label consistency. International Journal of Computer Vision, 2009, 82(3): 302–324

[3] Pantofaru C, Schmid C, Hebert M. Object recognition by integrating multiple image segmentations. In: Proceedings of European Conference on Computer Vision. 2008, 5304: 481–494

[4] Fulkerson B, Vedaldi A, Soatto S. Class segmentation and object localization with superpixel neighborhoods. In: Proceedings of IEEE International Conference on Computer Vision. 2009, 670–677

[5] Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274–2282

[6] Levinshtein A, Stere A, Kutulakos K N, Fleet D J, Dickinson S J, Siddiqi K. TurboPixels: fast superpixels using geometric flows. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(12): 2290–2297

[7] Veksler O, Boykov Y, Mehrani P. Superpixels and supervoxels in an energy optimization framework. In: Proceedings of European Conference on Computer Vision. 2010, 6315: 211–224

[8] Liu M Y, Tuzel O, Ramalingam S, Chellappa R. Entropy-rate clustering: cluster analysis via maximizing a submodular function subject to a matroid constraint. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(1): 99–112

[9] Haris K, Efstratiadis S N, Maglaveras N, Katsaggelos A K. Hybrid image segmentation using watersheds and fast region merging. IEEE Transactions on Image Processing, 1998, 7(12): 1684–1699

[10] Salembier P, Garrido L. Binary partition tree as an efficient representation for image processing, segmentation, and information retrieval. IEEE Transactions on Image Processing, 2000, 9(4): 561–576

[11] Nock R, Nielsen F. Statistical region merging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(11): 1452–1458

[12] Calderero F, Marques F. Region merging techniques using information theory statistical measures. IEEE Transactions on Image Processing, 2010, 19(6): 1567–1586

[13] Moscheni F, Bhattacharjee S, Kunt M. Spatio-temporal segmentation based on region merging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(9): 897–915

[14] Ben Ayed I, Mitiche A. A region merging prior for variational level set image segmentation. IEEE Transactions on Image Processing, 2008, 17(12): 2301–2311

[15] Beaulieu J M, Goldberg M. Hierarchy in picture segmentation: a stepwise optimization approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(2): 150–163

[16] Wikipedia. Diversity index, 2014, http://en.wikipedia.org/wiki/Diversity_index

[17] Cormen T H, Leiserson C E. Rivest R L, Stein C. Introduction to Algorithms. 2nd ed. Cambridge, Mass: MIT Press, 2001

RIGHTS & PERMISSIONS

2015 Higher Education Press and Springer-Verlag Berlin Heidelberg