**Commenced**in January 2007

**Frequency:**Monthly

**Edition:**International

**Paper Count:**31108

##### An Optimal Unsupervised Satellite image Segmentation Approach Based on Pearson System and k-Means Clustering Algorithm Initialization

**Authors:**
Ahmed Rekik,
Mourad Zribi,
Ahmed Ben Hamida,
Mohamed Benjelloun

**Abstract:**

This paper presents an optimal and unsupervised satellite image segmentation approach based on Pearson system and k-Means Clustering Algorithm Initialization. Such method could be considered as original by the fact that it utilised K-Means clustering algorithm for an optimal initialisation of image class number on one hand and it exploited Pearson system for an optimal statistical distributions- affectation of each considered class on the other hand. Satellite image exploitation requires the use of different approaches, especially those founded on the unsupervised statistical segmentation principle. Such approaches necessitate definition of several parameters like image class number, class variables- estimation and generalised mixture distributions. Use of statistical images- attributes assured convincing and promoting results under the condition of having an optimal initialisation step with appropriated statistical distributions- affectation. Pearson system associated with a k-means clustering algorithm and Stochastic Expectation-Maximization 'SEM' algorithm could be adapted to such problem. For each image-s class, Pearson system attributes one distribution type according to different parameters and especially the Skewness 'β1' and the kurtosis 'β2'. The different adapted algorithms, K-Means clustering algorithm, SEM algorithm and Pearson system algorithm, are then applied to satellite image segmentation problem. Efficiency of those combined algorithms was firstly validated with the Mean Quadratic Error 'MQE' evaluation, and secondly with visual inspection along several comparisons of these unsupervised images- segmentation.

**Keywords:**
Segmentation,
satellite image,
Unsupervised Classification,
Pearson system

**Digital Object Identifier (DOI):**
doi.org/10.5281/zenodo.1085479

**References:**

[1] S. Li, T. Fevens, A. Krzyżak and S. Li, "Automatic clinical image segmentation using pathological modelling PCA and SVM", Engineering Applications of Artificial Intelligence, Volume 19, pp. 403-410, June 2006.

[2] A. Schwaighofer, V. Tresp, P. Mayer, A.K. Scheel and G. Muller, "The RA scanner: prediction of rheumatoid joint inflammation based on laser imaging", IEEE Trans. Biomed. Imaging 50, pp. 375-382. 2003.

[3] Y. Zheng, H. Li and D. Doermann, "Machine printed text and handwriting identification in noisy document images", IEEE Trans. Pattern Anal. Mach. Intell. 26, pp. 337-345, 2004.

[4] W.Y. Manjunath, "A framework of boundary detection and image segmentation", IEEE Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, pp. 744-749, 2005.

[5] C.Y. and L.P. Jerry, "Snakes, shapes, and gradient vector flow", IEEE Trans. Image Process. 73, pp. 359-369, 1998.

[6] S.C. and Y. Alan, "Region competition: Unifying snakes, region growing, and Bayes/MDL for multiband image segmentation", IEEE Trans. Pattern Anal. Mach. Intell. 189, pp. 884-900, 1996.

[7] G.-P. and G. Chuang, "Extensive partition operators, gray-level connected operators, and region merging/classification segmentation algorithms: Theoretical links", IEEE Trans. Image Process. 109, pp. 1332-1345, 2001.

[8] K.S. and K.U. Jayaram, "Optimum image thresholding via class uncertainty and region homogeneity", IEEE Trans. Pattern Recog. Mach. Intell. 237, pp. 689-706, 2001.

[9] J.P, "Stochastic relaxation on partitions with connected components and its application to image segmentation", IEEE Trans. Pattern Anal. Mach. Intell. 206, pp. 619-636, 1998.

[10] J. Xie, and H. T. Tsui, "Image segmentation based on maximumlikelihood estimation and optimum entropy-distribution(MLE-OED)", Pattern Recognition Letters, Volume 25, Issue 10 , pp. 1133-1141, July 2004.

[11] Y. Deng, and B.S. Manjunath, "Unsupervised segmentation of color- texture regions in images and video", IEEE Trans. Pattern Anal. Mach. Intell. 238, pp. 800-810, 2001.

[12] M. Zribi and F. Ghorbel, "An unsupervised and non-parametric Bayesian classifier", Pattern Recognition Letters 24, pp. 97-112, 2003.

[13] A. Rekik, M. Zribi, A. Ben Hamida and, M. Benjelloun, "Unsupervised Bayesian Image Segmentation Using Adaptive EM Algorithm based on Pearson ssystem", Vol. V, WMSCI 2006, Florida, USA, pp. 165-169, 2006.

[14] T.R. Reed, J.M.H. Du Buf, "A review of recent texture segmentation, feature extraction techniques", CVGIP Image Understanding 57, pp. 359-372, 1993.

[15] J.A. Richards, "Remote Sensing Digital Image Analysis", second ed., Springer-Verlag, New York, 1993.

[16] L.Bruzzone, D.Fernandez Prieto, "Unsupervised retraining of a maximum-likehood classifier for the analysis of multitemporal remotesensing images", IEEE Transactions on Geoscience and Remote Sensing 39 (2001) pp.456-460.

[17] A. Rekik, M. Zribi, M. Benjelloun and A. ben Hamida, "A k-Means Clustering Algorithm Initialization for Unsupervised Statistical Satellite Image Segmentation", IEEE-International Conference on ELearning in Industrial Electronics, Hammamet - Tunisia, 2006.

[18] H. Frigui and R. Krishnapuram; "Clustering by competitive agglomeration", Pattern Recogntion, Vol. 30, No.7, pp.1109-1119, 1997.

[19] G. McLachlan, D. Peel, "Finite Mixture Models", Wiley, New York, 2000.

[20] G. McLachlan, T. Krishnan, "The EM Algorithm and Extensions", Wiley, New York, 1997.

[21] McCulloch, C. E, "Maximum likelihood algorithms for generalized linear mixed models", Journal of the American Statistical Association, pp. 62-170, 1997.