Fuzzy C-Means Algorithm with Divergence-Based Kernel
A Fuzzy C-Means algorithm with a Divergence-based Kernel (FCMDK) for clustering Gaussian Probability Density Function (GPDF) data is proposed in this paper. The proposed FCMDK is based on the Fuzzy C-Means algorithm and employs a kernel method for data transformation. The kernel method adopted in the proposed FCMDK is used to transform input data into a feature space of a higher dimensionality so that the nonlinear problems residing in input space can be linearly solved in the feature space. In order to deal with GPDF data, a divergence-based kernel employing a divergence distance measure for its similarly measure is used for data transformation. The proposed FCMDK is used for clustering GPDF data in an image classification model. Experiments and results on Caltech data sets demonstrate that the proposed FCMDK is more efficient than other conventional algorithms.
KeywordsFeature Space Discrete Cosine Transform Gaussian Mixture Model Kernel Method Membership Grade
Unable to display preview. Download preview PDF.
- 5.Cover, T.M.: Geomeasureal and Statistical Properties of Systems of Linear Inequalities in Pattern Recognition. Electron. Computing EC-14, 326–334 (1965)Google Scholar
- 7.Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machine. Cambridge Univ. Press, Cambridge (2000)Google Scholar
- 12.Huang, Y.L., Chang, R.F.: Texture Features for DCT-Coded Image Retrieval and Classification. In: ICASSP Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, vol. 6, pp. 3013–3016 (1999)Google Scholar