Visual information is the richest probably different existing information sources in our daily lives. The extraction of this information by processing systems and image analysis has attracted growing interest. The image processing is a process involving several stages, that it was born from the need to replace the human observer by the machine. He works in many fields such as medicine. A must in all image analysis process is the segmentation. By providing a compact description of the image, more exploitable than all the pixels, the image segmentation facilitates automatic interpretation of an image similar to human interpretation. Indeed, she was inspired by the human visual perception system that uses the concept of similarity and difference in order to locate and delineate the objects in an image. It can be defined as following: the image segmentation is a low-level process of creating a partition of the image into subsets called regions in a way that no region is empty; the intersection between the two regions is empty and covers all regions throughout the image. A region is a set of connected pixels having common properties that differentiate the pixels neighboring regions. This task although fluently although raised by the human visual system, is actually complex and remains a challenge for the image processing community despite several decades of research. Thus, several segmentation methods have been proposed in the literature, and can be classified into three major approaches: Approach area, Approach contour, cooperative approach. This article studies the problem of segmentation of MRI brain images. We worked precisely on cooperating more automatic classifiers to exploit complementarities between different methods or operators and increase the strength of the segmentation process. Our approach focuses on the FCM algorithm (Fuzzy c-means), the sum of degrees of membership of an individual given to all possible classes being 1. To make the algorithm robust to inaccuracies and ambiguous data that can considerably affect on the classes centers, we introduce the notion of ambiguity rejection.

Segmentation, C-means, MRI brain, thresholding, Otsu

[1]’’Image segmentation ‘’, chapter 10, https: //courses. cs.washington. edu/courses/ cse576/book /ch10.pdf.,Page No (1-51),March 2000.
[2] Rajeshwar Dass, 2Priyanka, 3Swapna Devi,’’ Image Segmentation Techniques’’, ISSN : 2230-7109 (Online) | ISSN : 2230-9543 (Print), International Journal of Electronics & Communication Technology, IJECT Vol. 3, Issue 1,Page No (66-70) ,Jan. - March 2012.
[3] Anna Blasiak,’’ A Comparison of Image Segmentation Methods’’, Senior Thesis in Computer Science Middlebury College, Page No (53-79), May 2007.
[4]‘’Segmentation’’,Chapter 10, http://www.cs.uu.nl /docs /vakken /ibv/reader/chapter10.pdf, Page No (24-69).
[5] A. M. Khan, Ravi. S,’’ Image Segmentation Methods: A Comparative Study’’, International Journal of Soft Computing and Engineering (IJSCE), ISSN: 2231-2307, Volume-3, Issue-4, Page No (1-9),September 2013.
[6] Vinay Lowanshi, Shweta Shrivastava,’’ Two Tier Architecture for Content Based Image Retrieval Using Modified SVM and knn-GA’’, International Journal of Computer Sciences and Engineering, Volume-2Issue-10,Page No (41-45),2014.
[7]Bryan S.Morse ,‘’Thresholding’’, Brigham Young University, 2000, http:// homepages .inf.ed.ac .uk/rbf/ CVonline/LOCAL_COPIES/MORSE/threshold.pdf, Page No (1-23).
[8] Mehmet Sezgin, Bulent Sankur,’’ Survey over image thresholding techniques and quantitative performance evaluation’’, Journal of Electronic Imaging 13(1), 146–165, Page No (1-18), (January 2004).
[9] S. Jansi, P. Subashini,’’ Optimized Adaptive Thresholding based Edge Detection Method for MRI Brain Images’’, International Journal of Computer Applications (0975 – 8887) Volume 51– No.20, Page No (1-8) ,August 2012.
[10] ‘’nonparametric methods’’, contaminated sites statistical applications guidance document no. 12-5,Page No(1-4),April 2001.
[11] Junmo Kim_, John W. Fisher III_, Anthony Yezzi, Jr., Mujdat Cetin_, and Alan S. Willsky,’’ nonparametric methods for image segmentation using information theory and curve evolution’’, this paper appeared in Proceedings of the 2002 IEEE International Conference on Image Processing, Rochester, NY, Page No(1-4),September 2002.
[12] Ahmed Elgammal ,Dept of Computer Science,Rutgers University,’’ CS 534: Computer Vision Segmentation III Statistical Nonparametric Methods for Segmentation’’, http://www.cs.rutgers.edu/~elgammal/classes/cs534/lectures/Segmentation3_meanshift.pdf., Page No(4-14).
[13] Junmo Kim, Member, IEEE, John W. Fisher, III, Member, IEEE, Anthony Yezzi, Member, IEEE, Müjdat Çetin, Member, IEEE, and Alan S. Willsky, Fellow, IEEE,’’ A Nonparametric Statistical Method for Image Segmentation Using Information Theory and Curve Evolution’’, IEEE Transactions On Image Processing, Vol. 14, NO. 10, Page No (1-17),OCTOBER 2005.
[14] DongjuLiu, JianYu,’’ Otsu method and K-means’’, Ninth International Conference on Hybrid Intelligent Systems, 978-0-7695-3745-0/09 $25.00 © 2009 IEEE DOI 10.1109/HIS.2009.74,Page No (344-349), 2009.
[15] Julie DELON, Agnès DESOLNEUX, José-Luis LISANI, Ana-Belén PETRO,’’ A non parametric approach for histogram Segmentation’’, http://desolneux .perso.math.cnrs. fr/ papers /DDLP_HistIP_07.pdf., Page No (1-9).
[16] Giovanna Menardi , ‘’a Nonparametric Clustering Method For Image Segmentation’’, http:// convegni.unica.it/cla dag2015 /files /2015 /10/Menardi.pdf.,Page No (1-4).
[17] Yaoyong Liu, Shuguang Li,’’ Two-Dimensional Arimoto Entropy Image Thresholding based on Ellipsoid Region Search Strategy’’, 978-1-4244-7874-3/10/$26.00 © IEEE,Page No(1-4), 2010 .
[18] Ahmad Adel Abu Shareha, Mandava Rajeswari, Dhanesh Ramachandram,’’ Textured Renyi Entropy for Image Thresholding’’, Fifth International Conference on Computer Graphics, Imaging and Visualisation, DOl 10.1109/CGIV.2008.48 ,978-0-7695-3359_9/08 $25.00 © IEEE ,Page No (185-192),2008 .
[19] Yang Xiao , Zhiguo Cao , Junsong Yuan,’’ Entropic image thresholding based on GLGM histogram ‘’, Pattern Recognition Letters 40 (2014), Elsevier , Page No (47–55),2014 .
[20] Prasanna K. Sahoo, Gurdial Arora,’’ A thresholding method based on two-dimensional Renyi’s entropy’’, Pattern Recognition 37 1149 – 1161, 0031-3203/$30.00 ? 2003 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved, doi: 10.1016/ j. patcog. 2003.10.008, Page No (1149-1161),(2004).
[21] Mohamed. A. El-Sayed, S. Abdel-Khalek, and Eman Abdel-Aziz,’’ Study of Efficient Technique Based On 2D Tsallis Entropy For Image Thresholding’’, International Journal on Computer Science and Engineering (IJCSE), ISSN : 0975-3397 Vol. 3 No. 9 ,Page No (3125-3138),September 2011.
[22] Martin Lindquist,’’ Statistical Methods in functional MRI’’, Overview of fMRI Data Analysis, 04/02/13.Page No (1-8),2013.
[23] Alexei A. S amsn o v ,Ros,s T. Whiti kerE.ug,e ne G. Kholmovki’Chi,i s R. Johnson’, ‘’Parametric Method for Correction of Intensity Inhomogeneity in MRI Data’’, © Proc. Intl. Soc. Mag. Reson. Med. 10 (2002).
[24] Amy herlihy,Lada Krasnosselskaia,Agilent technologies, Yarnton , ‘’MRI methods for collecting and analyzing parametric maps of the mouse brain at 7T ‘’, Page No(1-8),2012.
[25] Vitali Zagorodnov, Member, IEEE, and Arridhana Ciptadi, Student Member, IEEE, Component Analysis Approach to Estimation of Tissue Intensity Distributions of 3D Images’’, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 30, NO. 3,Page No(838-848) ,MARCH 2011.
[26] Jan-Philip Bergeest, Florian Jager,’’ A Comparison of Five Methods for Signal Intensity Standardization in MRI’’,Springer,Page No(36-40) ,2008.
[27] Florian Jäger and Joachim Hornegger, Member, IEEE,’’ Nonrigid Registration of Joint Histograms for Intensity Standardization in Magnetic Resonance Imaging’’, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 28, NO. 1,Page No(137-149) ,JANUARY 2009.
[28] Francisco J. Galdames, Fabrice Jaillet, Claudio A. Perez,’’ An Accurate Skull Stripping Method Based on Simplex Meshes and Histogram Analysis in Magnetic Resonance Images’ ,http://liris.cnrs.fr/Documents/Liris-5295.pdf. , Page No(1-17).
[29] Eugene Weinstein,’’Expectation –Maximization Algorithm and applications’’, Courant Institute of Mathematical Sciences,Page No(1-31) ,Nov 14th, 2006.
[30] Derek Bradley, Gerhard Roth,’’ Adaptive Thresholding Using the Integral Image’’, Page No (1-6), 2007.
[31] T .Romen Singh,Sudipta Roy,O.Imocha Singh,Tejmani Sinam, Kh .Manglem Singh,’’ A New Local Adaptive Thresholding Technique in Binarization’’, IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 6, No 2, Page No(271-277) ,November 2011 ISSN (Online): 1694-0814 www.IJCSI.org,2011.
[32] F. P. Kressler , M. Franzen , K. Steinnocher,’’ SEGMENTATION BASED CLASSIFICATION OF AERIAL IMAGES AND ITS POTENTIAL TO SUPPORT THE UPDATE OF EXISTING LAND USE DATA BASES’’, Page No (1-6),Sep 29, 2014.
[33] Azzeddine Riahi ,’’MRI Image Segmentation by K-Means Clustering Method and Detection of Lesions’’, International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064, Volume 4 Issue 6, Page No(2484-2492),June 2015
[34] Emre Akbas and Narendra Ahuja,’’ Low-level Image Segmentation Based Scene Classification’’, International Conference on Pattern Recognition, 1051-4651/10 $26.00 © 2010 IEEE ,DOI 10.1109/ICPR.2010.884,Page No(3623-3626),2010.
[35] Xiaofeng Ren and Jitendra Malik,’’ Learning a Classification Model for Segmentation’’, http://ttic.uchicago.edu/~xren/publication/xren_iccv03_discrim.pdf.,Page No (1-8).
[36] Chap. 7 — Region Segmentation, Computação Visual e-Multimédia http://www.di .ubi.pt /~agomes/cvm/teoricas/07-regionsegmentation.pdf. , Page No (1-32).
[37] Stephen Gould,Tianshi Gao,Daphne Koller,’’ Region-based Segmentation and Object Detection’’, http://ai.stanford.edu/~koller/Papers/Gould+al:NIPS09.pdf., Page No (1-9).
[38] Bryan S. Morse, ‘’Lecture 18: Segmentation (Region Based)’’, Brigham Young University, Page No (1-6), March 3, 2000.
[39] Yu-Hsiang Wang,’’ Tutorial: Image Segmentation’’, Graduate Institute of Communication Engineering National Taiwan University, Taipei, Taiwan, ROC, http:// disp.ee.ntu.edu.tw/meeting/%E6%98%B1% E7%B %94/ Segmentation %20tutorial.pdf. , Page No (1-36).
[40] YI-WEI YU andJUNG-WA WANG,’’ Image Segmentation Based on Region Growing and Edge Detection’’, 0-7803-5731-0/99$$10.00 01999 IEEE, Page No (798-803),1999.
[41] Yinghua Lu, TinghuaiMa, Changhong Yin, Xiaoyu Xie, Wei Tian and ShuiMing Zhong,’’ Implementation of the Fuzzy C-Means Clustering Algorithm in Meteorological Data’’, International Journal of Database Theory and Application Vol.6, No.6 (2013), pp.1-18 http://dx.doi.org/10.14257/ijdta.2013.6.6.01, ISSN: 2005-4270 IJDTA Copyright 2013 SERSC,Page No(1-18),2013.
[42] Subhagata Chattopadhyay, Dilip Kumar Pratihar, Sanjib Chandra De Sarkar’’ A COMPARATIVE STUDY OF FUZZY C-MEANS ALGORITHM AND ENTROPY-BASED FUZZY CLUSTERING ALGORITHMS’’, Computing and Informatics, Vol. 30, 2011, 701–720, Page No (701-720) ,2012.
[43] Soumi Ghosh, Sanjay Kumar Dubey,’’ Comparative Analysis of K-Means and Fuzzy C-Means Algorithms’’, www.ijacsa.thesai.org, ((IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 4, No.4,Page No (35-39), 2013.
[44] S. Ramathilaga, James Jiunn-Yin Leu, Yueh-Min Huang,’’ Adapted Mean Variable Distance to Fuzzy-Cmeans for Effective Image Clustering’’, First International Conference on Robot, Vision and Signal Processing, 978-0-7695-4581-3/11 $26.00 © 2011 IEEE ,DOI 10.1109 /RVSP.2011.58,Page No(48-51),2011.
[45]chapter4‘’FUZZY CLUSTERING’’ https: //homes. di.unimi.it /valenti/ Slide Corsi/Bioinformatic a05/Fuzzy-Clustering-lecture-Babuska.pdf. ,Page No(55-71).
[46] Xiao Ying Wang, Jon Garibaldi, Turhan Ozen,’’ Application of the Fuzzy C-Means Clustering Method on the Analysis of non Preprocessed FTIR Data for Cancer Diagnosis’’,2003, http://ima.ac.uk/papers/wang2003.pdf., Page No (1-6).
[47] Keh-Shih Chuang , Hong-Long Tzeng , Sharon Chen , Jay Wu , Tzong-Jer Chen,’’ Fuzzy c-means clustering with spatial information for image segmentation’’, 0895-6111/$ - see front matter q 2005 Published by Elsevier Ltd,doi:10.1016/j.compmedimag.2005.10.001,Page No (9-15),2005.
[48] Tina Geweniger, Dietlind Zühlkeand Barbara Hammer and Thomas Villmann,’’ Median Variant of Fuzzy c-Means’’, ESANN'2009 proceedings, European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning. Bruges (Belgium), 22-24 April 2009, d-side publi, ISBN 2-930307-09-9, Page No (523-528), 2009.
[49] Stelios Krinidis and Vassilios Chatzis,’’ A Robust Fuzzy Local Information C-means ClusteringAlgorithm’’, http://infoman.teikav.edu .gr/~stkrini/pdfFiles/journals /2010_TIP.pdf. ,2010. , Page No (2-11),2010.
[50] Mathias Bank and Friedhelm Schwenker,’’ Fuzzification of Agglomerative Hierarchical Crisp Clustering