Noisy image segmentation using a self-organizing map network

• Autorzy: Gorjizadeh S , Pasban S , Alipour S

Identyfikatory

DOI

10.12913/22998624/2375

• Języki publikacji: EN

Abstrakty

EN

Image segmentation is an essential step in image processing. Many image segmentation methods are available but most of these methods are not suitable for noisy images or they require priori knowledge, such as knowledge on the type of noise. In order to overcome these obstacles, a new image segmentation algorithm is proposed by using a self-organizing map (SOM) with some changes in its structure and training data. In this paper, we choose a pixel with its spatial neighbors and two statistical features, mean and median, computed based on a block of pixels as training data for each pixel. This approach helps SOM network recognize a model of noise, and consequently, segment noisy image as well by using spatial information and two statistical features. Moreover, a two cycle thresholding process is used at the end of learning phase to combine or remove extra segments. This way helps the proposed network to recognize the correct number of clusters/segments automatically. A performance evaluation of the proposed algorithm is carried out on different kinds of image, including medical data imagery and natural scene. The experimental results show that the proposed algoise in comparison with the well-known unsupervised algothms.

Słowa kluczowe

EN

image segmentation; unsupervised algorithm; noise; statistical features; SOM neural networks

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2015
• Tom: Vol. 9, nr 26
• Strony: 118–--123
• Opis fizyczny: Bibliogr. 23 poz., fig.

Twórcy

autor

Gorjizadeh S

• Student in the Department of Computer Engineering, Islamic Azad University, Sari, Iran

autor

Pasban S

• Department of Computer Engineering at Birjand University, Birjand, Iran

autor

Alipour S

• Department of Electrical and Electronic Engineering at Malek-Ashtar University of Technology, Tehran, Iran

Bibliografia

• 1. Pratt W. , John Wiley & Sons, New York 1991.
• 2. Awad M., An unsupervised artificial neural network method for satellite image segmentation. The International Arab Journal of Information Techno-logy, vol. 7, April 2010.
• 3. Awad M., Nasri A., Satellite image segmentation using self-organizing maps and fuzzy C-Means. IEEE, 2009, 398–402.
• 4. Jesna M., Raimond K., A survey on MR Brain image segmentation using SOM based strategies. International Journal of Computational Engineering Research, vol. 3, 2013.
• 5. Lopes A., Nezry E., Touzi R., Laur H., Maximum a posteriori speckle filtering and first order textural models in SAR images. [In:] Proceedings of International Geoscience and Remote Sensing Symposium, Maryland, 1990, 2409–2412.
• 6. Benediktsson J., Swain P., Ersoy O., Hong D., Neural network approaches versus statistical methods in classification of multisource remote sensing data. Computer Journal of Institute of Electrical and Electronics Engineers, 28(4), 1990, 540–551.
• 7. Perkins S., Theiler J., Brumby S., Harvey N., Porter R., Szymanski J., Bloch J., GENIE: A hybrid genetic algorithm for feature classification in multi spectral images. [In:] Proceedings of SPIE Applications and Science of Neural Networks, Fuzzy Systems and Evolutionary Computation III 4120, USA, 2000, 52–62.
• 8. Zhang P., Verma B., Kumar K., Neural vs statistical classifier in conjunction with genetic algorithm feature selection in digital mammography. IEEE, 2003.
• 9. Zhou Z., Wei S., Zhang X., Zhao X., Remote sensing image segmentation based on self organizing map at multiple scale. Proceedings of SPIE Geoinformatics: Remotely Sensed Data and Information, USA, 2007.
• 10. Kohonen T., Self-organizing maps. Computer Journal of Springer Series in Information Sciences 30(3), 2001, 501–505.
• 11. Wirjadi O., Survey of 3d image segmentation methods. 2010.
• 12. Tian D., Fan L. et al. MR images segmentation method based on SOM neural network. [In:] Proceeding of the First International Conference on Bioinformatics and Biomedical Engineering, ICBBE, China, 2007, 686–689.
• 13. Kohonen T., Kaski S., Lagus K., Salojarvi J., Honkela J., Paatero V., Saarela A., Self organization of a massive document collection. IEEE Transactions on Neural Networks, vol. 11, 2000, 574–585.
• 14. Yeo N.C., Lee K.H., Venkatesh Y.V., Ong S.H., Colour image segmentation using the self-organizing map and adaptive resonance theory. Elsevier, 2005.
• 15. Demirhan A., Guler I. Combining stationary wavelet transform and self-organizing maps for brain MR image segmentation. Engineering Applications of Artificial Intelligence, vol. 24, 2011. 358–367.
• 16. Li Y., Chi Z., MR Brain image segmentation based on self-organizing map network. International Journal of Information Technology, vol. 11, 2005, 45–53.
• 17. Available insight segmentation and registration toolkit ( ITK), an open source and cross platform system: http://www.itk.org/.
• 18. Alipour S., Shanbehzadeh J., Fast automatic medical image segmentation based on spatial kernel fuzzy c-means on level set method. Machine Vision and Applications, vol. 25, 2014, 1469–1488.
• 19. Gilboa G., Osher S., Nonlocal linear image regularization and supervised segmentation. SIAM Multiscale Modeling and Simulation, vol. 6, 2007, 595–630.
• 20. Nadernejad E., Sharifzadeh S., A new method for image segmentation based on Fuzzy C-means algorithm on pixonal images formed by bilateral filtering. Signal Image Video Process, vol. 7, 2013, 855–863.
• 21. Bernard O., Friboulet D., Thévenaz P., Fellow M., Variational B-spline leve l-set: a linear filtering approach for fast deformable model evolution. IEEE Trans. Image Process, vol. 18, 2009, 1179–1191.
• 22. Jain A., Dubes R., Algorithms for clustering data. Englewood Cliffs, NJ: Prentice–Hall, 1988.
• 23. Bezdek J.C., Pattern recognition with fuzzy objective function algorithms. Plenum Press, New York, 1981.