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.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Ren X, Malik J. Learning a classification model for segmentation. In: Proceedings of IEEE International Conference on Computer Vision. 2003, 10–17
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
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
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
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
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
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
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
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
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
Nock R, Nielsen F. Statistical region merging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(11): 1452–1458
Calderero F, Marques F. Region merging techniques using information theory statistical measures. IEEE Transactions on Image Processing, 2010, 19(6): 1567–1586
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
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
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
Wikipedia. Diversity index, 2014, http://en.wikipedia.org/wiki/Diversity_index
Cormen T H, Leiserson C E. Rivest R L, Stein C. Introduction to Algorithms. 2nd ed. Cambridge, Mass: MIT Press, 2001
Author information
Authors and Affiliations
Corresponding author
Additional information
Song Zhu is a Ph.D. candidate in the School of Optical and Electronic Information, Huazhong University of Science and Technology (HUST). He received his B.E. degree in the School of Optical and Electronic Information, HUST, 2010. His research interests include 3D computer vision, image segment and pattern recognition.
Danhua Cao is a professor in the School of Optical and Electronic Information, Huazhong University of Science and Technology. She received her Ph.D. degree in electronic physics and devices, HUST, 1993; B.E. degree in measuring and control technology and instrumentations, HUST, 1987. She is the permanent member of the Professional Committee of Opto-Electronic Technology in the Chinese Optical Society. Her research interests include optoelectronic sensing and signal processing, machine vision algorithm and systems.
Yubin Wu is an associate professor in the School of Optical and Electronic Information, Huazhong University of Science and Technology (HUST). He received his M.E. degree in optical engineering from Institute of Optics and Electronics of the Chinese Academy of Sciences, 1987; B.E. degree in optical instruments, HUST, 1984. His research interests include optoelectronic sensing and signal processing, machine vision, and the development of high-tech products.
Yubin Wu is an associate professor in the School of Optical and Electronic Information, Huazhong University of Science and Technology (HUST). He received his M.E. degree in optical engineering from Institute of Optics and Electronics of the Chinese Academy of Sciences, 1987; B.E. degree in optical instruments, HUST, 1984. His research interests include optoelectronic sensing and signal processing, machine vision, and the development of high-tech products.
Shixiong Jiang is a Ph.D. candidate in the School of Optical and Electronic Information, Huazhong University of Science and Technology (HUST). He received his B.E. degree in the School of Optical and Electronic Information, HUST, 2011. His research interests include machine vision, 3D reconstruction and pattern recognition.
Rights and permissions
About this article
Cite this article
Zhu, S., Cao, D., Wu, Y. et al. Improved accuracy of superpixel segmentation by region merging method. Front. Optoelectron. 9, 633–639 (2016). https://doi.org/10.1007/s12200-015-0482-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12200-015-0482-2