##
**Nonparametric clustering for image segmentation.**
*(English)*
Zbl 07260665

Summary: Image segmentation aims at identifying regions of interest within an image by grouping pixels according to their properties. This task resembles the statistical one of clustering, yet many standard clustering methods fail to meet the basic requirements of image segmentation since the identified segments are often biased toward predetermined shapes and their number is rarely determined automatically. Nonparametric clustering is, in principle, free from these limitations and particularly suitable for the task of image segmentation. We discuss the application of nonparametric clustering to image segmentation and provide an algorithm specific for this task. Pixel similarity is evaluated in terms of the density of the color representation. The adjacency structure of the pixels is exploited to introduce a simple, yet effective method to identify image segments as disconnected high-density regions. The proposed method answers to the need of both segmenting an image and detecting its boundaries and can be seen as a generalization to color images of the class of thresholding methods.

PDF
BibTeX
XML
Cite

\textit{G. Menardi}, Stat. Anal. Data Min. 13, No. 1, 83--97 (2020; Zbl 07260665)

### References:

[1] | I. Almodóvar-Rivera and R. Maitra,Kernel-estimated nonparametric overlap-based syncytial clustering, arXiv:1805.09505, 2018. |

[2] | H. Ayala et al.,Image thresholding segmentation based on a novel beta differential evolution approach, Expert Syst. Appl. 42 (2015), 2136-2142. |

[3] | A. Azzalini and G. Menardi,Clustering via nonparametric density estimation: The R package pdfCluster, J. Stat. Softw. 57 (2014), 1-26. · Zbl 1322.62175 |

[4] | A. Azzalini and N. Torelli,Clustering via nonparametric density estimation, Statist. Comput. 17 (2007), 71-80. |

[5] | N. Berry and R. Maitra,Tik-means: Transformation-infused k-means clustering for skewed groups, Stat. Anal. Data Mining: ASA Data Sci. J. 12 (2019), 223-233. |

[6] | M. Bordese and W. Alini:biOps: Image processing and analysis, 2017, available at https://github.com/matiasb/biOps/ |

[7] | M. Carreira-Perpinan,Generalised blurring mean-shift algorithms for nonparametric clustering, inCVPR, IEEE Computer Society, New York, 2008. |

[8] | A. Casa, J. E. Chacón, and G. Menardi,Modal clustering asymptotics with applications to bandwidth selection, arXiv:1901.07300, 2019. · Zbl 1477.62117 |

[9] | J. Chacón and T. Duong,Multivariate kernel smoothing and its applications, Chapman and Hall/CRC Press, Boca Raton, FL, 2018. · Zbl 1402.62003 |

[10] | J. E. Chacón,A population background for nonparametric density-based clustering, Statist. Sci. 30 (2015), 518-532. · Zbl 1426.62181 |

[11] | T. Chan and L. Vese,Active contours without edges, IEEE Trans. Image Process. 10 (2001), 266-277. · Zbl 1039.68779 |

[12] | D. Comaniciu and P. Meer,Mean shift: A robust approach toward feature space analysis, IEEE Trans. Pattern Anal. Mach. Intell. 24 (2002), 603-619. |

[13] | P. Dollár and C. Zitnick,Structured forests for fast edge detection, inProceedings of the International Conference on Computer Vision, IEEE, New York, 2013, 1841-1848. |

[14] | G. Dougherty,Digital image processing for medical applications, Cambridge University Press, Cambridge, 2009. |

[15] | M. El Aziz, A. Ewees, and A. Hassanien,Whale optimization algorithm and moth-flame optimization for multilevel thresholding image segmentation, Expert Syst. Appl. 83 (2017), 242-256. |

[16] | K. Fukunaga and L. D. Hostetler,The estimation of the gradient of a density function, with application in pattern recognition, IEEE Trans. Inform. Theory 21 (1975), 32-40. · Zbl 0297.62025 |

[17] | C. Hennig et al.,Handbook of cluster analysis, CRC Press, Boca Raton, FL, 2015. |

[18] | L. Hubert and P. Arabie,Comparing partitions, J. Classification 2 (1985), 193-218. · Zbl 0587.62128 |

[19] | R. Kimmel and A. Bruckstein,Regularized Laplacian zero crossings as optimal edge integrators, Int. J. Comput. Vision 53 (2003), 225-243. |

[20] | C. Li et al.,Minimization of region-scalable fitting energy for image segmentation, IEEE Trans. Image Process. 17 (2008), 1940-1949. · Zbl 1371.94225 |

[21] | T. Liu et al.,Improving image segmentation by gradient vector flow and mean shift, Pattern Recogn. Lett. 29 (2008), 90-95. |

[22] | R.Maitra,Initializingpartition-optimizationalgorithms, IEEE/ACM Trans. Comput. Biol. Bioinform. 6 (2009), 144-157. |

[23] | R. Maitra, V. Melnykov, and S. Lahiri,Bootstrapping for significance of compact clusters in multidimensional datasets, J. Amer. Statist. Assoc. 107 (2012), 378-392. · Zbl 1261.62060 |

[24] | G. Menardi and A. Azzalini,An advancement in clustering via nonparametric density estimation, Statist. Comput. 24 (2014), 753-767. · Zbl 1322.62175 |

[25] | J. Ning et al.,Interactive image segmentation by maximal similarity based region merging, Pattern Recogn. 43 (2010), 445-456. · Zbl 1187.68485 |

[26] | G. Pau et al.,Ebimage—An R package for image processing with applications to cellular phenotypes, Bioinformatics 26(7) (2010), 979-981. https://doi.org/10.1093/bioinformatics/btq046. |

[27] | A. Peterson, A. Ghosh, and R. Maitra,Merging k-means with hierarchical clustering for identifying general-shaped groups, Stat 7 (2018), 172. |

[28] | R Core Team,R: A language and environment for statistical computing, R Foundation for Statistical Computing, Vienna, Austria, |

[29] | Avaiable https://www.R-project.org/. |

[30] | D. Scott and S. Sain,Multidimensional density estimation, Handbook of Statist. 24 (2005), 229-261. |

[31] | A. Seal, A. Das, and P. Sen,Watershed: An image segmentation approach, Int. J. Comput. Sci. Inform. Technol. 6 (2015), 2295-2297. |

[32] | P. Soille,Morphological image analysis: Principles and applications, Springer Science & Business Media, Berlin, 2013. · Zbl 1012.68212 |

[33] | W. Stuetzle and R. Nugent,A generalized single linkage method for estimating the cluster tree of a density, J. Comput. Graph. Statist. 19 (2010), 397-418. |

[34] | S. Sulaiman and N. Isa,Adaptive fuzzy-k-means clustering algorithm for image segmentation, IEEE Trans. Consumer Electron. 56 (2010), 2661-2668. |

[35] | W. Tao, H. Jin, and Y. Zhang,Color image segmentation based on mean shift and normalized cuts, IEEE Trans. Syst. Man and Cybernet. B: Cybernet. 37 (2007), 1382-1389. |

[36] | M. P. Wand and M. C. Jones,Kernel smoothing, Chapman and Hall/CRC Press, Boca Raton, FL, 1994. · Zbl 0854.62043 |

[37] | Y. Xiang, A. Chung, and J. Ye,An active contour model for image segmentation based on elastic interaction, J. Comput. Phys. 219 (2006), 455-476. · Zbl 1106.94010 |

[38] | X. Yuan, B. Hu, and R. He,Agglomerative mean-shift clustering, IEEE Trans. Knowledge Data Eng. 24 (2012), 209-219. |

[39] | L. Zhang et al.,A novel active contour model for image segmentation using local and global region-based information, Mach. Vision Appl. 28 (2017), 75-89. |

[40] | H. |

This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.