The Importance of Object-based Seed Sampling for Superpixel Segmentation
Resumo
Superpixel segmentation can be defined as an image partition into connected regions, such that image objects may be represented by the union of their superpixels. In this context, multiple iterations of superpixel segmentation from improved seed sets is a strategy exploited by several algorithms. The Iterative Spanning Forest (ISF) framework divides this strategy into three independent components: a seed sampling method, a superpixel delineation algorithm based on strength of connectedness between seeds and pixels, and a seed recomputation procedure. A recent work shows that object information can be added to each component of ISF such that the user can control the number of seeds inside the objects and so improve superpixel segmentation. However, no study has been conducted to evaluate the impact of object information in each component. In this work, we fulfill this gap with respect to the seed sampling component of ISF. We also propose a novel seed sampling approach, named Object Saliency Map sampling by Ordered Extraction (OSMOX), and demonstrate the results for supervised and unsupervised object information. The experiments show considerable improvements in under-segmentation error, specially with a low number of superpixels.
Referências
S. Zhang H. Wang W. Huang Z. You "Plant diseased leaf segmentation and recognition by fusion of superpixel k-means and phog" Optik vol. pp. 866-872 2018.
Y. Li L. Shen "Skin lesion analysis towards melanoma detection using deep learning network" Sensors vol. 18 no. 2 pp. 2018.
R. Achanta A. Shaji K. Smith A. Lucchi P. Fua S. Süsstrunk "SLIC superpixels compared to state-of-the-art superpixel methods" IEEE Trans. Pattern Anal. Mach. Intell. vol. 34 pp. 2274-22012.
Y.-J. Liu M. Yu B.-J. Li Y. He "Intrinsic manifold SLIC: A simple and efficient method for computing content-sensitive superpixels" IEEE Trans. Pattern Anal. Mach. Intell. vol. 40 no. 3 pp. 653-March 2018.
Y.-J. Liu C.-C. Yu M.-J. Yu Y. He "Manifold SLIC: A fast method to compute content-sensitive superpixels" Proc. 29th Conf. Comput. Vis. Pattern Recognit. pp. 651-2016.
Z. Li J. Chen "Superpixel segmentation using linear spectral clustering" Proc. 28th Conf. Comput. Vis. Pattern Recognit. pp. 1356-1June 2015.
J. Shi J. Malik "Normalized cuts and image segmentation" IEEE Trans. Pattern Anal. Mach. Intell. vol. 22 pp. 888-905 2000.
P. Felzenszwalb D. Huttenlocher "Efficient graph-based image segmentation" IntI. Journal Comput. Vis. vol. 59 no. 2 pp. 167-2004.
M.-Y. Liu O. Tuzel S. Ramalingam R. Chellappa "Entropy rate superpixel segmentation" IEEE 24th Conf. Comput. Vis. Pattern Recognit. (CVPR). pp. 2097-22011.
O. Veksler Y. Boykov P. Mehrani "Superpixels and supervoxels in an energy optimization framework" 11th European Conf. Comput. Vis. (ECCV). pp. 211-2010.
A. Rubio L. Yu E. Simo-Serra F. Moreno-Noguer "Bass: boundary-aware superpixel segmentation" IEEE 23rd Intl. Conf. Pattern Recognit.(ICPR). pp. 2824-22016.
J. E. Vargas-Muñoz A. S. Chowdhury E. B. Alexandre F. L. Galvão P. A. V. Miranda A. X. Falcao "An iterative spanning forest framework for superpixel segmentation" IEEE Trans. Image Process. 2019.
A. X. Falcao J. Stolfi R. A. Lotufo "The image foresting transform: Theory algorithms and applications" IEEE Trans. Pattern Anal. Mach. Intell. vol. 26 pp. 19-29 2004.
F. Belém S. Guimarães A. Falcao Superpixel Segmentation by Object-Based Iterative Spanning Forest: 23rd Iberoamerican Congress CIARP 2018 Madrid Spain:Elsevier pp. 334-November 2018.
T. V. Spina A. X. Falcão "Intelligent understanding of user input applied to arc-weight estimation for graph-based foreground segmentation" Proc. 23th Conf. Graphics Pattern Images (SIBGRAPI) pp. 164-2010.
X. Li H. Lu L. Zhang X. Ruan M.-H. Yang "Saliency detection via dense and sparse reconstruction" IEEE 16th Intl. Conf. Comput. Vis. (ICCV) pp. 2976-2983 2013.
H. Jiang J. Wang Z. Yuan Y. Wu N. Zheng S. Li "Salient object detection: A discriminative regional feature integration approach" IEEE 26th Conf. Comput. Vis. Pattern Recognit. (CVPR) pp. 2083-2090 2013.
J. P. Papa A. X. Falcao C. T. Suzuki "Supervised pattern classification based on optimum-path forest" Int. J. Imaging Syst. Technol. vol. 19 no. 2 pp. 120-2009.
T. Liu Z. Yuan J. Sun J. Wang N. Zheng X. Tang H.-Y. Shum "Learning to detect a salient object" IEEE Trans. Pattern Anal. Mach. Intell. vol. 33 no. 2 pp. 353-2011.
L. Mansilla P. Miranda "Oriented image foresting transform segmentation: Connectivity constraints with adjustable width" Proc. 29th Conf. Graphics Pattern Images (SIBGRAPI). pp. 289-2016.
P. Neubert P. Protzel "Superpixel benchmark and comparison" Proc. Forum Bildverarbeitung vol. 6 pp. 1-12 2012.
