Abstract
Superpixel segmentation is a popular image preprocessing technology in image processing. Among the various methods used to calculate uniform superpixel, the performance of linear spectral clustering (LSC) is better than the state-of-the-art superpixel segmentation algorithms. However, this method is slow on images and has low accuracy on non-convex images. In order to improve this problem, we propose a subsampled clustering method that can accelerate LSC. Meanwhile, this paper presents an improved distance measurement method based on non-convex image features and Manhattan distance, which can achieve high accuracy on non-convex images. The proposed method is evaluated on the BSDS500 dataset. The experimental results confirmed that this method runs faster than LSC, and at the same time produces almost the same superpixel segmentation accuracy on the images. In addition, the proposed method improves the accuracy of superpixel segmentation on non-convex images.
Similar content being viewed by others
References
Achanta R, Shaji A, Smith K et al (2012) SLIC superpixel compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 11:2274–2282. https://doi.org/10.1109/TPAMI.2012.120
Achanta R, Susstrunk S (2017) Superpixel and polygons using simple non-iterative clustering. In: IEEE conference on computer vision and pattern recognition. IEEE, pp 4895–490
Alexandre EB, Chowdhury AS, Falcão AX et al (2015) IFT-SLIC: a general framework for superpixel generation based on simple linear iterative clustering and image foresting transform. In: Graphics, patterns and images. IEEE, pp 337–344
Arbeláez P, Maire M, Fowlkes C et al (2011) Contour detection and hierarchical image segmentation. IEEE Trans Pattern Anal Mach Intell 33:898–916. https://doi.org/10.1109/TPAMI.2010.161
Belem FC, Guimaraes SJF, Falcao AX (2020) Superpixel segmentation using dynamic and iterative spanning forest. IEEE Signal Process Lett 27:1440–1444. https://doi.org/10.1109/LSP.2020.3015433
Chen J, Li Z, Bo H (2017) Linear spectral clustering superpixel. IEEE Trans Image Process 7:3317–3330. https://doi.org/10.1109/TIP.2017.2651389
Chen LC, Zhu Y, Papandreou G et al (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) European conference on computer vision. Springer, Cham, pp 833–851
Comaniciu D, Meer P (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 5:603–619. https://doi.org/10.1109/34.1000236
Cour T, Shi J (2007) Recognizing objects by piecing together the segmentation puzzle. In: IEEE conference on computer vision & pattern recognition. IEEE, pp 1–8
Dhillon IS, Guan Y, Kulis B (2007) Weighted graph cuts without eigenvectors: a multilevel approach. IEEE Trans Pattern Anal Mach Intell 29:1944–1957. https://doi.org/10.1109/TPAMI.2007.1115
Feng HW, Xiao F, Bu QR et al (2017) An accelerated superpixel generation algorithm based on 4-labeled-neighbors. In: CCF Chinese conference on computer vision. Springer, pp 539–550
Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Int J Comput Vis 59:167–181. https://doi.org/10.1023/B:VISI.0000022288.19776.77
Haralick R, Shanmugam K et al (1973) Textural features for image classification. Syst Man Cybernet 6:610–621. https://doi.org/10.1109/TSMC.1973.4309314
Levinshtein A, Stere A, Kutulakos KN et al (2009) TurboPixels: fast superpixel using geometric manifolds. IEEE Trans Pattern Anal Mach Intell 12:2290–2297. https://doi.org/10.1109/TPAMI.2009.96
Li Z, Chen J (2015) Superpixel segmentation using linear spectral clustering. In: IEEE conference on computer vision and pattern recognition. IEEE, pp 1356–1363
Liu MY, Tuzel O, Ramalingam S et al (2011) Entropy rate superpixel segmentation. In: Computer vision and pattern recognition. IEEE, pp 2097–2104
Liu YJ, Yu CC, Yu MJ et al (2016) Manifold SLIC: a fast method to compute content-sensitive superpixel. In: Computer vision and pattern recognition. IEEE, pp 651–659
Ma B, Hu H, Shen J et al (2016) Generalized pooling for robust object tracking. IEEE Trans Image Process 9:4199–4208. https://doi.org/10.1109/TIP.2016.2588329
Qian X, Li XM, Zhang C (2019) Weighted superpixel segmentation. Vis Comput 35:985–996. https://doi.org/10.1007/s00371-019-01682-x
Reddy NS, Faruq MSU, Lakshmi KR (2016) Image segmentation by using linear spectral clustering. Int J Adv Res Comput Commun Eng. https://doi.org/10.17148/IJARCCE.2016.51009
Ren XF, Jitendra M (2008) Learning a classification model for segmentation. In: IEEE international conference on computer vision. IEEE, pp 10–17
Shi J, Malik JM (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 8:888–905. https://doi.org/10.1109/34.868688
Tenenbaum JB et al (2000) A Global geometric framework for nonlinear dimensionality reduction. Science 290:2319–2323. https://doi.org/10.1126/science.290.5500.2319
Tian ZQ, Zheng NN, Xue JR, Lan XG (2014) Video object segmentation with shape cue based on spatiotemporal superpixel neighbourhood. IET Comput Vis 8:16–25. https://doi.org/10.1049/iet-cvi.2012.0189
Vedaldi A, Soatto S (2008) Quick shift and kernel methods for mode seeking. In: European conference on computer vision. Springer, pp 705–718
Wang H, Peng X, Xiao X et al (2017) BSLIC: SLIC superpixels based on boundary term. Symmetry 3:31. https://doi.org/10.3390/sym9030031
Zhu L, Kang XJ, Ming AL, Zhang XS (2018) Dynamic Random Walk for Superpixel Segmentation. In: Conference on Asian conference on computer vision. Springer, pp 540–554
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Qiao, N., Di, L. An improved method of linear spectral clustering. Multimed Tools Appl 81, 1287–1311 (2022). https://doi.org/10.1007/s11042-021-11459-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11459-x