Fully Unsupervised Texture Segmentation Using Mean-Shift Clustering With Modified Gray Level Co-Occurrence Matrix

Fatna Zegaoua; Abderrazak Guessoum

doi:10.29284/wezngx58

Authors

Fatna Zegaoua Electronics Department Faculty Of Technology Blida-1 University Blida, 09000, Algeria.
Abderrazak Guessoum Computer Science Department LATSI Laboratory, Faculty Of Technology Blida-1 University Blida, 09000, Algeria.

DOI:

https://doi.org/10.29284/wezngx58

Keywords:

Texture segmentation, Clustering, Classification, Mean-Shift, GLCM.

Abstract

Digital image processing applies a number of computer algorithms to treat and deal with digital images. The outcomes of this process can be either images or a set of representative properties to be used in subsequent applications. In view of the diversity of images and the applications goals, it has been proved in a large literature that using hybrid techniques is more advantageous than relying on a single method. The purpose of this paper is to present an unsupervised cooperative segmentation framework that can shorten the computation cost and segment diverse image types without any prior information. The proposed framework generates, at first, a set of feature vectors using a new Modified Gray Level Co-occurrence Matrix (M-GLCM). Then, it applies the Mean-Shift clustering to estimate the number of textures in the original image and initiate afterward the k-Means algorithm in order to assign each pixel to its corresponding class according to a distance measure. The new proposed M-GLCM helps in overcoming the time consuming and the large memory size needed in the initial GLCM. The Mean-shift by its own is known to be fast and induces good estimated clusters. The core aspect of our approach is its adaptability to the image’s type where the number of calculated attributes and the window size depends on the global uniformity characteristic of the image; more the image is textured, more the window size is larger and the features space is denser. The results of the proposed work are found to be promising, especially when a step of multi-level thresholding is applied beforehand.

References

[1]. Rafael C. Gonzalez, Richard E. Woods. Digital image processing. Fourth Edition, Global Edition. Pearson Education Limited, 2018.

[2]. Mihran Tuceryan, Anil K. Jain. Texture analysis (Chapter 2.1). The Handbook of Pattern Recognition and Computer Vision (2nd Edition), by C. H. Chen, L. F. Pau,P. S. P. Wang (eds.), pp. 207-248, World Scientific Publishing Co., 1998. https://doi.org/10.1142/97898143431380010.

[3]. Angulakshmi M., Lakshmi Priya G.G. Automated brain tumour segmentation - a review. International Journal of Imaging Systems and Technology. Vol. 27, pp 66–77, 2017.

[4]. Rundo L. et al. Combining split-and-merge and multi-seed region growing algorithms for uterine fibroid segmentation in MRgFUS treatments. Medical, & Biological Engineering & Computing. Vol. 54, No. 7, pp. 1071–1084, 2016. https://doi.org/10.1007/s11517-015-1404-6, 2-s2.0-84946151274.

[5]. Liang H. Weller, D. S. Edge-based texture granularity detection. IEEE International Conference on Image Processing (ICIP), pp. 3563-3567, 2016. https://doi.org/10.1109/ICIP.2016.7533023.

[6]. R. Haralick. Statistical and structural approaches to texture. Proceedings of the IEEE, 67:786–804, 1979. https://doi.org/10.1109/PROC.1979.11328.

[7]. L. Armi and S. Fekri-Ershad. Texture image analysis and texture classification methods - a review. International Online Journal of Image Processing and Pattern Recognition, Vol. 2, No.1, pp. 1-29, 2019.

[8]. R. N. Khadse, A. K. Khursange, S. V. Khekare, R. R. Rathod, Prof. Ajay D. Nanure. Texture analysis method – a survey. International Journal of Advanced Research in Science, Communication and Technology (IJARSCT), Volume 3, Issue 1, December 2023.

[9]. A. Eleyan, and H. Demirel. Co-occurrence matrix and its statistical features as a new approach for face recognition. Turkish Journal of Electrical Engineering and Computer Sciences: Vol. 19, No. 1, Article 8. https://doi.org/10.3906/elk-0906-27.

[10]. B. Julesz. Visual pattern discrimination. IRE Transactions on Information Theory, IT-8:84–92, 1962. https://doi.org/10.1109/TIT.1962.1057698.

[11]. T. Randen and J. H. Husoy. Filtering for texture classification: a comparative study. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 4, pp. 291-310, April 1999. https://doi.org/10.1109/34.761261.

[12]. Mircea Cimpoi, Subhransu Maji, Andrea Vedaldi. Deep filter banks for texture recognition and segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.https://doi.org/10.1109/CVPR.2015.7299007.

[13]. J. Zhang, P. Fieguth, and D. Wang. Random field models. In Handbook of Image and Video Processing, pages 301–312. Academic Press, San Diego, CA, 2000.

[14]. G. R. Cross and A. K. Jain. Markov random field texture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-5, no. 1, pp. 25-39, Jan. 1983. https://doi.org/10.1109/TPAMI.1983.4767341.

[15]. Yang P. Yang G. Feature extraction using dual-tree complex wavelet transform and gray level co-occurrence matrix. Neurocomputing. Vol. 197, pp 212-220, 2016.

[16]. Alamgir N. Myeongsu K. Yung-Keun K. Cheol-Hong K. and Jong-Myon K. Hybrid technique for medical image segmentation. Journal of Biomedicine and Biotechnology. Corporation Issue 1, Vol. 2012. https://doi.org/10.1155/2012/830252.

[17]. Robert M. Haralick, K. Shanmugam, and I. Dinstein. Textural features for image classification. IEEE Transaction on Systems, Man and Cybernetics, Vol.SMC-3, No. 6, p.p 610–621, Nov. 1973. Printed in the U.S.A.

[18]. O. Mahmoud, Abu Abbas. Comparisons between data clustering algorithms. International Arab Journal of Information Technology, Vol. 5, No. 3, July 2008, p.p: 320-325.

[19]. Akula Ratna Babu, Miriyala Markandeyulu, Bussa V R R Nagarjuna. Pattern clustering with similarity measures. International Journal of Computer Technology & Applications,Vol. 3, No. 1, p.p 365-369, ISSN:2229-6093.

[20]. S. M. Aqil Burney and H. Tariq. K-Means cluster analysis for image segmentation. International Journal of Computer Applications (0975 – 8887), vol. 96, N° 4, pp: 1–8, Jun. 2014. https://doi.org/10.5120/16779-6360.

[21]. Claude Cariou, Steven Le Moan, Kacem Chehdi. A Novel meanshift algorithm for data clustering. IEEE Access, 2022, 10, pp.14575-14585. ff10.1109/ACCESS.2022.3147951ff. ffhal-03593568.

[22]. Mustafa, M., Taib, M.N., Murat, Z.H. and Hamid, N.H.A. GLCM texture classification for EEG spectrogram image. IEEE EMBS Conference on Biomedical Engineering & Sciences, Kuala Lumpur, 30 November-2 December 2010, 373-376.

[23]. Mireille Pouyap, Laurent Bitjoka, Etienne Mfoumou and Denis Toko. Improved bearing fault diagnosis by feature extraction based on GLCM, fusion of selection methods, and multiclass-naïve bayes classification. Journal of Signal and Information Processing, Vol. 12, No. 4, pp. 7185, 2021.

[24]. O.M. O’Byrne, B. Ghosh, V. Pakrashi and F. Schoefs. Texture analysis based detection and classification of surface features on ageing infrastructure elements. BCRI 2012 Bridge & Concrete Research in Ireland, 2012, Cork, Ireland.

[25]. L.D.O. Bastos, P. Liatsis, and A. Conci. Automatic texture segmentation based on K-Means clustering and efficient calculation of co-occurrence features. In 15th International Conference on Systems, Signals and Image Processing, IWSSIP, June 2008. Bratislava, Slovakia: Inst. of Elec. and Elec. Eng. Computer Society.

[26]. B. S. Garra, et al. Improving the distinction between benign and malignant breast lesions: The value of sonographic texture analysis. Ultrason. Imag., Oct. 1993, Vol. 15, N° 4, pp: 267-285.

[27]. Q. Wu, Y. Gan, B. Lin, Q. Zhang and H. Chang. An active contour model based on fused texture features for image segmentation. Neurocomputing 151, 2015, pp: 1133-1141.

[28]. P. Maillard. Comparing texture analysis methods through classification. Photogrammetric Eng. Remote Sens., vol. 69, no. 4, pp: 357-367, Apr. 2003.

[29]. M F.A Fauzi and P. H Lewis. A Fully unsupervised texture segmentation algorithm. British Machine Vision Conference 2003, Norwich, United Kingdom. Sep 2003. pp. 519-528.

[30]. R. B Vallabhaneni and V. Rajesh. Brain tumour detection using meanshift clustering and GLCM features with edge adaptive total variation denoising technique. Alexandria Engineering Journal, Vol. 57, Issue 4, Dec. 2018, pp: 2387-2392. https://doi.org/10.1016/j.aej.2017.09.011.

[31]. T. Haryanto et al. Multipatch-GLCM for texture feature extraction on classification of the colon histopathology images using deep neural network with GPU acceleration. Journal of Computer Science, 2020, Vol. 16(3), pp: 280.294. https://doi.org/10.3844/jcssp.2020.280.294

[32]. D. J. Marceau, P. J. Howarth, J. M. Dubois and D. J. Gratton. Evaluation of The grey-level co-occurrence matrix method for land-cover classification using spot imagery. in IEEE Transactions on Geoscience and Remote Sensing, vol. 28, no. 4, pp. 513-519, July 1990. https://doi.org/10.1109/TGRS.1990.572937.

[33]. M.E. Hodgson. What size window for image classification? A cognitive perspective. Photogrammetric Engineering 6 Remote Sensing, 1998, Vol. 64(8), pp: 797-807.

[34]. L.V. Dutra and N.D.A. Mascarenhas. Some experiments with spatial feature extraction methods in multispectral classification. International Journal of Remote Sensing, Vol. 5(2), pp: 303-313.

[35]. D. Puig, M.A. García). Pixel-based texture classification by integration of multiple texture feature evaluation windows. In: Perales, F.J., Campilho, A.J.C., de la Blanca, N.P., Sanfeliu, A. (eds). Pattern Recognition and Image Analysis. IbPRIA 2003. Lecture Notes in Computer Science, Vol. 2652. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-44871-6_92.

[36]. P. Dhal and C. Azad. A comprehensive survey on feature selection in the various fields of machine learning. Applied Intelligence, 2022, Vol. 52(4), pp: 4543–4581. https://doi.org/10.1007/s10489-021-02550-9.

[37]. Q. Kanglin, Xu Jiucheng, H. Qincheng, Q. Kangjian and S. Yuanhao. Feature selection using information gain and decision information in neighborhood decision system. Applied Soft Computing, Vol. 136, 2023, ISSN 1568-4946. https://doi.org/10.1016/j.asoc.2023.110100.

[38]. T.K. Florentina, I. Sembiring, A. Setiawan, I. Setyawan and R.R Huizen. GLCM-based feature combination for extraction model optimization in object detection using machine learning. Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI), Vol. 9, No. 4, December 2023, pp. 1196-1205, ISSN: 2338-3070. https://doi.org/10.26555/jiteki.v9i4.27842.

[39]. N. Aggarwal and R. K. Agrawal. First and second order statistics features for classification of magnetic resonance brain images. Journal of Signal and Information Processing, 2012, 3, 146-153. http://dx.doi.org/10.4236/jsip.2012.32019

[40]. A. Materka and M. Strzelecki. Texture analysis methods – a review. Technical University of Lodz, Institute of Electronics, COST B11 report, Brussels 1998

[41]. R. W. Conners and C. A. Harlow. A theoretical comparison of texture algorithms. IEEE Trans. Pattern Anal. Mach. Intell. Vol. PAMI-2, No. 3, pp. 204–222, May 1980.

[42]. Fritz Albregtsen. Statistical texture measures computed from gray level co-occurrence matrices. Image Processing Laboratory. Department of Informatics, University of Oslo. November 5, 2008. Available at the site:

[43]. https://www.uio.no/studier/emner/matnat/ifi/INF4300/h08/undervisningsmateriale/glcm.pdf

[44]. A. Gelzinisa, A. Verikasa, M. Bacauskienea, Increasing the discrimination power of the co-occurrence matrix-based features. Pattern Recognition, vol. 40, pp. 2367–2372, 2004.

[45]. M. O’Byrne, B. Ghosh, V. Pakrashi and F. Schoefs. Texture analysis based detection and classification of surface features on ageing infrastructure elements. BCRI2012 Bridge & Concrete Research in Ireland, 2012, Cork, Ireland. ffhal-01009012f.

[46]. S. Sharma, T. Choudhury and Y. Singh. Advanced feature extraction for mammogram mass classification: a multi-scale multi-orientation framework. International Journal on Smart Sensing And Intelligent Systems. Issue 1, Vol. 18, 2025. https://doi.org/10.2478/ijssis-2025-0022.

[47]. Dorin Comaniciu, Member, IEEE, and Peter Meer, Senior Member, IEEE. MeanShift: A Robust Approach Toward Feature Space Analysis. IEEE Transactions on Pattern Analysis and Machine Intlligence, Vol 24, N°5, May 2002.

[48]. S. Balasubramanian Subbiah and C. Seldev. Image Classification through integrated K- Means Algorithm. IJCSI International Journal of Computer Science Issues, Vol. 9, Issue 2, No 2, March 2012, ISSN (Online): 1694-0814.

[49]. D. Nameirakpam, M. Khumanthem and J.C. Yambem. Image Segmentation using K-means Clustering Algorithm and Subtractive Clustering Algorithm. Procedia Computer Science 54, 2015, pp:764–771. https://doi.org/10.1016/j.procs.2015.06.090.

[50]. J.M.H. du Buf, M. Kardan, M. Spann. Texture feature performance for image segmentation. Pattern Recognition, Vol.23, Issues 3–4, 1990, pp 291-309. ISSN 0031-3203. https://doi.org/10.1016/0031-3203(90)90017-F.

[51]. Levine, M. and Nazif, D. Dynamic measurement of computer generated images segmentation. PAMI, (March 1985), 155-164. https://doi.org/10.1109/TPAMI.1985.4767640

[52]. R. Zeboudj. Filtrage, seuillage automatique, contraste et contours : du pré-traitement à l’analyse d’image. PhD, Université de Saint-Etienne, 1988.

[53]. C. Rosenberger. Mise en œuvre d'un système adaptatif de segmentation d'images. Doctorate thesis, Rennes 1 university, 1999, N°2292.

[54]. Juan Pablo Balarini, Sergio Nesmachnow. A C++ Implementation of Otsu’s Image Segmentation Method. Published in Image Processing On Line, on 2016–07–10, ISSN 2105–1232. Available at the site: http://dx.doi.org/10.5201/ipol.2016.158.

[55]. Elsayed Abd Elaziz. M, Oliva. D and Ewees. A. Multi-level Thresholding-based Gray Scale Image Segmentation Using Multi-objective Multi-verse Optimizer. Expert Systems with Applications. Vol.125, 2019. https://doi.org/10.1016/j.eswa.2019.01.047.

[56]. Deng-Yuan Huang et al. Automatic Multilevel Thresholding based on Two-stage Otsu’s Method with Cluster Determination by Valley estimation. International Journal of Innovative Computing, Information and control, Vol. 7, N°10, October 2011 ISSN 1349-4198, pp 5631-5644. Available at the site: http://www.ijicic.org/ijicic-10-05033.pdf