A Novel Fast FCM Clustering for Segmentation of Salt and Pepper Noise Corrupted Images
The conventional fuzzy C-means (FCM) is most frequently used unsupervised clustering algorithm for image segmentation. However, it is sensitive to noise and cluster center initialization. In order to overcome this problem, a novel fast fuzzy C-means (FFCM) clustering algorithm is proposed with the ability to minimize the effects of impulse noise by incorporating noise detection stage to the clustering algorithm during the segmentation process without degrading the fine details of the image. This method also improves the performance of the FCM algorithm by finding the initial cluster centroids based on histogram analysis, reducing the number of iterations. The advantages of the proposed method are: (1) Minimizes the effect of impulse noise during segmentation, (2) Minimum number of iterations to segment the image. The performance of the proposed approach is tested on different real time noisy images. The experiment results show that the proposed algorithm effectively segment the noisy image.
KeywordsClustering Image segmentation Histogram Salt-and-pepper noise Fuzzy C-means Image processing
- 5.Mat-Isa, N.A., Mashor, M.Y., Othman, N.H.: Automatic seed based region growing for pap smear image segmentation. In: Kuala Lumpur International Conference on Biomedical Engineering, Kuala Lumpur, Malaysia (2002)Google Scholar
- 7.Siyoung, Y., Donghyung, K., Jechang, J.: Fine edge-preserving deinterlacing algorithm for progressive display. IEEE Trans. Consum. Electron. 53(3), 1654–1662 (2009)Google Scholar
- 14.Mat-Isa, N.A., Mashor, M.Y., Othman, N.: Pap smear image segmentation using modified moving k-mean clustering. In: International Conference on Biomedical Engineering, Kuala Lumpur Malaysia (2002)Google Scholar
- 15.Mat-Isa, N.A., Mashor, M.Y., Othman, N.H., Sulaiman, S.N.: Application of moving k-means clustering for pap smear image processing. In: Proceeding of International Conference on Robotics, Vision, Information and Signal Processing, Penang, Malaysia (2002)Google Scholar
- 19.Zhang, J.-H., Ha, M.H., Wu, J.: Implementation of rough fuzzy K-means clustering algorithm in Matlab. In: Proceedings of Ninth International Conference on Machine Learning and Cybernetics, July 2010Google Scholar