Multi-kernel Collaboration-Induced Fuzzy Local Information C-Means Algorithm for Image Segmentation
As an advanced method in the field of image segmentation, the fuzzy local information c-means (FLICM) algorithm has the problem of which segmentation performance is degraded when neighboring pixels are polluted, and it is imperfect for clustering nonlinear data. Focusing on these points, the Multi-kernel Collaboration-induced Fuzzy Local Information C-Means (MCFLICM) algorithm is put forward. To begin with, the concept of multi-kernel collaboration is introduced in image segmentation, and the Euclidean distance of the original space is replaced by multiple kernel-induced distance that are composed of multiple kernels in different proportions. Moreover, a new fuzzy factor is proposed from the viewpoints of pixel mean and local information, so as to increase the noises immunity. Finally, the multi-kernel collaboration and the new fuzzy factor are synthesized, and then the MCFLICM algorithm is put forward. MCFLICM can automatically adjust the requirements of different data points for kernel functions in the iterative procedure and can avoid the uncertainty of the selection of kernel function by the ordinary kernel algorithms. These advantages increase the robustness of the algorithm. In addition, MCFLICM has a stronger denoising performance to improve the ability to retain the original image details. Through comparing experiments with seven related algorithms, it is found that the segmentation performance of MCFLICM in binary image, three-valued image and natural image is superior to other algorithms, and the best results are achieved by MCFLICM from the viewpoints of visual effects and evaluation indexes.
KeywordsMulti-kernel Collaboration FCM Image segmentation
This work was supported by the National Natural Science Foundation of China (Nos. 61673156, 61672202, 61432004, U1613217), the Natural Science Foundation of Anhui Province (Nos. 1408085MKL15, 1508085QF129).
- 5.Tian, Y., Li, Y., Liu, D., et al.: FCM texture image segmentation method based on the local binary pattern. In: 12th World Congress on Intelligent Control and Automation, pp. 92–97. IEEE (2016)Google Scholar
- 7.Dunn, J.C.: A fuzzy relative of the ISO DATA process and its use in detecting compact well-separated clusters. J. Cybern. Syst. 3(3), 33–57 (1973)Google Scholar
- 10.Szilagyi, L., Benyo, Z., Szilagyi, S.M., et al.: MR brain image segmentation using an enhanced fuzzy C-means algorithm. In: Proceedings of Annual International Conference on Engineering in Medicine and Biology Society, vol. 5, no. 12, pp. 724–726 (2003)Google Scholar
- 18.Bach, F.R., Lanckriet, G.R.G, Jordan, M.I.: Multiple kernel learning, conic duality, and the SMO algorithm. In: Proceedings of the Twenty-First International Conference on Machine Learning, Banff, Alberta, Canada, p. 6 (2004)Google Scholar
- 19.Zhao, B., Kwok, J., Zhang, C.: Multiple kernel clustering. In: Proceedings of 9th SIAM International Conference on Data Mining, pp. 638–649 (2009)Google Scholar
- 21.Zhou, J., Philip, C.L., Chen, L.: Maximum-entropy-based multiple kernel, fuzzy c-means clustering algorithm. In: IEEE International Conference on Systems, Man and Cybernetics, 5–8 October, pp. 1198–1203. IEEE, San Diego (2013)Google Scholar
- 22.Bach, F.R., Lanckriet, G.R.G., Jordan, M.I.: Multiple kernel learning, conic duality, and the SMO algorithm. In: Proceedings of 21st International Conference on Machine Learning (2004)Google Scholar